计算机视觉与模式识别学术速递[2022.9.20]

Transformer(12篇)

【1】 Real-time Online Video Detection with Temporal Smoothing Transformers
标题：基于时间平滑变换的实时在线视频检测
链接：https://arxiv.org/abs/2209.09236
作者：Yue Zhao,Philipp Krähenbühl
机构：and Philipp Kr¨ahenb¨uhl, University of Texas at Austin, Austin TX , USA
备注：ECCV 2022; Code available at this https URL

【2】 Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization
标题：用于弱监督目标定位的自监督Transformer中建议的判别抽样
链接：https://arxiv.org/abs/2209.09209
作者：Shakeeb Murtaza,Soufiane Belharbi,Marco Pedersoli,Aydin Sarraf,Eric Granger
机构： LIVIA, École de Technologie Supérieure, Montreal, Canada, Ericsson, Global AI Accelerator, Montreal, Canada

【3】 Multi-Task Vision Transformer for Semi-Supervised Driver Distraction Detection
标题：用于半监督驾驶员分心检测的多任务视觉转换器
链接：https://arxiv.org/abs/2209.09178
作者：Yunsheng Ma,Ziran Wang
机构： Wang are both with Purdue University College of Engi-neering

【4】 TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation
标题：任务：基于Transformer的对抗性学习，用于使用可穿戴传感器通过自我知识蒸馏识别人类活动
链接：https://arxiv.org/abs/2209.09092
作者：Sungho Suh,Vitor Fortes Rey,Paul Lukowicz
机构：German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany, Department of Computer Science, TU Kaiserslautern, Kaiserslautern, Germany
备注：17 pages, 5 figures, Submitted to Knowledge-Based Systems, Elsevier. arXiv admin note: substantial text overlap with arXiv:2110.12163

【5】 Panoramic Vision Transformer for Saliency Detection in 360° Videos
标题：用于360°视频显著检测的全景视觉转换器
链接：https://arxiv.org/abs/2209.08956
作者：Heeseung Yun,Sehun Lee,Gunhee Kim
机构：Seoul National University, Seoul, Korea
备注：Published to ECCV2022

【6】 A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird’s-Eye-View
标题：一种用于鸟瞰统一道路布局估计和三维目标检测的双周期交叉视场Transformer网络
链接：https://arxiv.org/abs/2209.08844
作者：Curie Kim,Ue-Hwan Kim
机构： theseThis work was supported in part by the Institute for Information &communications Technology Promotion (IITP) grant funded by the Koreagovernment (MSIT) (No

【7】 Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
标题：与Transformers实现密集通信的集成功能和成本聚合
链接：https://arxiv.org/abs/2209.08742
作者：Sunghwan Hong,Seokju Cho,Seungryong Kim,Stephen Lin
机构：Korea University, Microsoft Research Asia

【8】 Axially Expanded Windows for Local-Global Interaction in Vision Transformers
标题：视觉变形器中局部-全局交互的轴向扩展窗口
链接：https://arxiv.org/abs/2209.08726
作者：Zhemin Zhang,Xun Gong
机构：Southwest Jiaotong University

【9】 Uncertainty Aware Multitask Pyramid Vision Transformer For UAV-Based Object Re-Identification
标题：基于不确定性感知的无人机目标再识别多任务金字塔视觉转换器
链接：https://arxiv.org/abs/2209.08686
作者：Syeda Nyma Ferdous,Xin Li,Siwei Lyu
机构：West Virginia University, Lane Dept. of Comp. Sci. and Elec. Engr., Morgantown, WV ,-, State University of New York at Buffalo, Department of Computer Science and Engineering, Davis Hall, Buffalo, NY

【10】 ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding
标题：Ernie-MmLayout：面向文档理解的多粒度多模式转换器
链接：https://arxiv.org/abs/2209.08569
作者：Wenjin Wang,Zhengjie Huang,Bin Luo,Qianglong Chen,Qiming Peng,Yinxu Pan,Weichong Yin,Shikun Feng,Yu Sun,Dianhai Yu,Yin Zhang
机构：Zhejiang University, Hangzhou, China, Baidu Inc.
备注：Accepted by ACM Multimedia 2022

【11】 TODE-Trans: Transparent Object Depth Estimation with Transformer
标题：TODE-TRANS：基于Transformer的透明物体深度估计
链接：https://arxiv.org/abs/2209.08455
作者：Kang Chen,Shaochen Wang,Beihao Xia,Dongxu Li,Zhen Kan,Bin Li
机构： still can not provide satisfactory depth Contribute equally 1 University of Science and Technology of China, China 2 Huazhong University of Science and Technology
备注：Submitted to ICRA2023

【12】 PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation
标题：PPT：用于单目和多视角人体姿态估计的令牌剪枝姿态转换器
链接：https://arxiv.org/abs/2209.08194
作者：Haoyu Ma,Zhe Wang,Yifei Chen,Deying Kong,Liangjian Chen,Xingwei Liu,Xiangyi Yan,Hao Tang,Xiaohui Xie
机构： University of California, Irvine, Tencent Inc, Meta Reality Lab, Meta AI
备注：ECCV 2022. Code is available at this https URL

检测相关(16篇)

【1】 Table Detection in the Wild: A Novel Diverse Table Detection Dataset and Method
标题：野外表格检测：一种新的多样性表格检测数据集和方法
链接：https://arxiv.org/abs/2209.09207
作者：Mrinal Haloi,Shashank Shekhar,Nikhil Fande,Siddhant Swaroop Dash,Sanjay G
机构：Subex AI Labs
备注：Open source Table detection dataset and baseline results

【2】 Improving Mitosis Detection Via UNet-based Adversarial Domain Homogenizer
标题：基于UNT的对抗性结构域均质器改进有丝分裂检测
链接：https://arxiv.org/abs/2209.09193
作者：Tirupati Saketh Chandr,Sahar Almahfouz Nasser,Nikhil Cherian Kurian,Amit Sethi
机构：Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India, -,-,-

【3】 Fairness in Face Presentation Attack Detection
标题：人脸呈现攻击检测中的公平性
链接：https://arxiv.org/abs/2209.09035
作者：Meiling Fang,Wufei Yang,Arjan Kuijper,Vitomir Struc,Naser Damer
机构：Fraunhofer Institute for Computer Graphics Research, Darmstadt, Germany, Department of Computer Science, TU Darmstadt, Darmstadt, Germany, University of Ljubljana, Ljubljana, Slovenia

【4】 An Overview on the Generation and Detection of Synthetic and Manipulated Satellite Images
标题：合成和操纵卫星图像的生成和检测综述
链接：https://arxiv.org/abs/2209.08984
作者：Lydia Abady,Edoardo Daniele Cannas,Paolo Bestagini,Benedetta Tondi,Stefano Tubaro,Mauro Barni
机构： Universitádi Siena
备注：25 pages, 17 figures, 5 tables, APSIPA 2022

【5】 GLARE: A Dataset for Traffic Sign Detection in Sun Glare
标题：眩光：一种用于日光下交通标志检测的数据集
链接：https://arxiv.org/abs/2209.08716
作者：Nicholas Gray,Megan Moraes,Jiang Bian,Allen Tian,Alex Wang,Haoyi Xiong,Zhishan Guo
机构：¶University of Central Florida, ‡Baidu Research Lab , §Local High Schools, †NC State University

【6】 An Adaptive Threshold for the Canny Edge Detection with Actor-Critic Algorithm
标题：一种基于Actor-Critic算法的自适应Canny边缘检测阈值
链接：https://arxiv.org/abs/2209.08699
作者：Keong-Hun Choi,Jong-Eun Ha
机构：Seoul National University of Science and Technology, Seoul , Korea (e-, In our previous work [,], we have proposed an algorithm that, automatically determines values of two thresholds in the Canny, algorithm using the Deep Q-Network (DQN) [,]. We used a

【7】 RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection
标题：RankFeat：用于分布外检测的秩1特征去除
链接：https://arxiv.org/abs/2209.08590
作者：Yue Song,Nicu Sebe,Wei Wang
机构：Department of Information Engineering and Computer Science, University of Trento, Italy
备注：NeurIPS22

【8】 RDD2022: A multi-national image dataset for automatic Road Damage Detection
标题：RDD2022：一种用于道路损伤自动检测的多国家图像数据集
链接：https://arxiv.org/abs/2209.08538
作者：Deeksha Arya,Hiroya Maeda,Sanjay Kumar Ghosh,Durga Toshniwal,Yoshihide Sekimoto
机构：Sekimoto, Centre for Transportation Systems (CTRANS), Indian Institute of Technology Roorkee, Roorkee, India, Centre for Spatial Information Science, The University of Tokyo, Tokyo, Japan, UrbanX Technologies, Inc., Tokyo, Japan
备注：16 pages, 20 figures, IEEE BigData Cup - Crowdsensing-based Road damage detection challenge (CRDDC’2022)

【9】 StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks
标题：StereoVoxelNet：基于深度神经网络的立体摄像机占用体素的实时障碍物检测
链接：https://arxiv.org/abs/2209.08459
作者：Hongyu Li,Zhengang Li,Neset Unver Akmandor,Huaizu Jiang,Yanzhi Wang,Taskin Padir
机构： even the lightweight deep learning stereo 1Institute for Experiential Robotics, Northeastern University

【10】 Evolution of a Web-Scale Near Duplicate Image Detection System
标题：一种网络规模的近似重复图像检测系统的发展
链接：https://arxiv.org/abs/2209.08433
作者：Andrey Gusev,Jiajing Xu
机构：Pinterest, San Francisco, CA

【11】 RGB-Event Fusion for Moving Object Detection in Autonomous Driving
标题：基于RGB-事件融合的自动驾驶运动目标检测
链接：https://arxiv.org/abs/2209.08323
作者：Zhuyun Zhou,Zongwei Wu,Rémi Boutteau,Fan Yang,Cédric Demonceaux,Dominique Ginhac
机构： Universit´e Bourgogne Franche-Comt´e

【12】 Changer: Feature Interaction is What You Need for Change Detection
标题：Change：功能交互是变更检测所需的
链接：https://arxiv.org/abs/2209.08290
作者：Sheng Fang,Kaiyu Li,Zhe Li
机构：Shandong University of Science and Technology, China
备注：11 pages, 5 figures

【13】 Understanding the Impact of Image Quality and Distance of Objects to Object Detection Performance
标题：了解图像质量和目标距离对目标检测性能的影响
链接：https://arxiv.org/abs/2209.08237
作者：Yu Hao,Haoyang Pei,Yixuan Lyu,Zhongzheng Yuan,John-Ross Rizzo,Yao Wang,Yi Fang
机构：NYU Multimedia and Visual Computing Lab, NYU Tandon School of Engineering, New York University, USA, New York University Abu Dhabi, UAE, NYU Langone Health, USA

【14】 OysterNet: Enhanced Oyster Detection Using Simulation
标题：OysterNet：基于模拟的增强牡蛎检测
链接：https://arxiv.org/abs/2209.08176
作者：Xiaomin Lin,Nitin J. Sanket,Nare Karapetyan,Yiannis Aloimonos
机构： University of Maryland Institute forAdvanced Computer Studies
备注：None

【15】 Uncertainty Quantification of Collaborative Detection for Self-Driving
标题：自动驾驶协同检测的不确定性量化
链接：https://arxiv.org/abs/2209.08162
作者：Sanbao Su,Yiming Li,Sihong He,Songyang Han,Chen Feng,Caiwen Ding,Fei Miao
备注：6 pages, 3 figures

【16】 Robust Ensemble Morph Detection with Domain Generalization
标题：基于区域泛化的稳健集成形态检测
链接：https://arxiv.org/abs/2209.08130
作者：Hossein Kashiani,Shoaib Meraj Sami,Sobhan Soleymani,Nasser M. Nasrabadi
机构：West Virginia University
备注：Accepted in IJCB 2022

分类|识别相关(16篇)

【1】 Use Classifier as Generator
标题：使用分类器作为生成器
链接：https://arxiv.org/abs/2209.09210
作者：Haoyang Li
机构：Cornell University

【2】 Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition
标题：基于可差分频率解缠的航空视频动作识别
链接：https://arxiv.org/abs/2209.09194
作者：Divya Kothandaraman,Ming Lin,Dinesh Manocha
机构：University of Maryland College Park

【3】 Improving Accuracy and Explainability of Online Handwriting Recognition
标题：提高在线手写识别的准确性和可解释性
链接：https://arxiv.org/abs/2209.09102
作者：Hilda Azimi,Steven Chang,Jonathan Gold,Koray Karabina
机构：National Research Council Canada, University of Waterloo
备注：20 pages, 8 figures, 2 tables,

【4】 Audio-Visual Fusion for Emotion Recognition in the Valence-Arousal Space Using Joint Cross-Attention
标题：联合交叉注意用于配价-唤醒空间情感识别的视听融合
链接：https://arxiv.org/abs/2209.09068
作者：R Gnana Praveen,Eric Granger,Patrick Cardinal
备注：arXiv admin note: substantial text overlap with arXiv:2203.14779, arXiv:2111.05222

【5】 MSA-GCN:Multiscale Adaptive Graph Convolution Network for Gait Emotion Recognition
标题：MSA-GCN：多尺度自适应图形卷积网络的步态情感识别
链接：https://arxiv.org/abs/2209.08988
作者：Yunfei Yin,Li Jing,Faliang Huang,Guangchao Yang,Zhuowei Wang
机构： Nanning Normal University

【6】 HiMFR: A Hybrid Masked Face Recognition Through Face Inpainting
标题：HiMFR：一种基于人脸修复的混合蒙版人脸识别算法
链接：https://arxiv.org/abs/2209.08930
作者：Md Imran Hosen,Md Baharul Islam
机构：Department of Computer Engineering, Bahcesehir University, Istanbul, Turkey, College of Data Science & Engineering, American University of Malta, Bormla, Malta
备注：7 pages, 6 figures, International Conference on Pattern Recognition Workshop: Deep Learning for Visual Detection and Recognition

【7】 TANDEM3D: Active Tactile Exploration for 3D Object Recognition
标题：TANDEM3D：三维物体识别的主动触觉探索
链接：https://arxiv.org/abs/2209.08772
作者：Jingxi Xu,Han Lin,Shuran Song,Matei Ciocarlie

【8】 S${}^3$R: Self-supervised Spectral Regression for Hyperspectral Histopathology Image Classification
标题：S${}^3$R：用于高光谱组织病理学图像分类的自监督光谱回归
链接：https://arxiv.org/abs/2209.08770
作者：Xingran Xie,Yan Wang,Qingli Li
机构：Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai , China

【9】 Ensembles of Compact, Region-specific & Regularized Spiking Neural Networks for Scalable Place Recognition
标题：用于可伸缩位置识别的紧凑、区域特定和正则化的尖峰神经网络集成
链接：https://arxiv.org/abs/2209.08723
作者：Somayeh Hussaini,Michael Milford,Tobias Fischer
备注：8 pages, 6 figures, under review

【10】 Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness
标题：为什么深部手术模型失败？：通过健壮性镜头重新审视手术动作三联体识别
链接：https://arxiv.org/abs/2209.08647
作者：Yanqi Cheng,Lihao Liu,Shujun Wang,Yueming Jin,Carola-Bibiane Schönlieb,Angelica I. Aviles-Rivero
机构： Aviles-Rivero are withthe Department of Applied Mathematics and Theoretical Physics, Universityof Cambridge; {yc 4 4 3

【11】 Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification
标题：直导式Few-Shot分类的自适应降维和变分推理
链接：https://arxiv.org/abs/2209.08527
作者：Yuqing Hu,Stéphane Pateux,Vincent Gripon
机构：Orange Labs, Cesson-Sévigné, France, IMT-Atlantique, Brest, France

【12】 VisTaNet: Attention Guided Deep Fusion for Surface Roughness Classification
标题：VisTaNet：注意力引导的深度融合表面粗糙度分类
链接：https://arxiv.org/abs/2209.08516
作者：Prasanna Kumar Routray,Aditya Sanjiv Kanade,Jay Bhanushali,Manivannan Muniyandi
机构： Indian Institute ofTechnology Madras

【13】 Imbalanced Nodes Classification for Graph Neural Networks Based on Valuable Sample Mining
标题：基于有价值样本挖掘的图神经网络不平衡节点分类
链接：https://arxiv.org/abs/2209.08514
作者：Min Liu,Siwen Jin,Luo Jin,Shuohan Wang,Yu Fang,Yuliang Shi
机构：School of Software, Beijing University of Technology, Beijing, China, Computer Department, Beijing Technology and Business, Department of Computer Science, Wenzhou-Kean University, Wenzhou, Zhejiang Province, School of Electronic Information, Engineering, Sias University
备注：6 pages,3 figures

【14】 GaitFM: Fine-grained Motion Representation for Gait Recognition
标题：GaitFM：面向步态识别的细粒度运动表示
链接：https://arxiv.org/abs/2209.08470
作者：Lei Wang,Fangfang Liang,Bincheng Wang,Bo Liu
机构：Hebei Agricultural University, Baoding , Hebei, China

【15】 Data Efficient Visual Place Recognition Using Extremely JPEG-Compressed Images
标题：基于JPEG超压缩图像的高效视觉位置识别
链接：https://arxiv.org/abs/2209.08343
作者：Mihnea-Alexandru Tomita,Bruno Ferrarini,Michael Milford,Klaus McDonald-Maier,Shoaib Ehsan
备注：8 pages, 8 figures

【16】 Few-Shot Classification with Contrastive Learning
标题：基于对比学习的Few-Shot分类
链接：https://arxiv.org/abs/2209.08224
作者：Zhanyuan Yang,Jinghua Wang,Yingying Zhu
机构： College of Computer Science and Software Engineering, Shenzhen University, School of Computer Science and Technology, Harbin Institute of Technology, (Shenzhen), Shenzhen, China
备注：To appear in ECCV 2022

分割|语义相关(18篇)

【1】 OCR for TIFF Compressed Document Images Directly in Compressed Domain Using Text segmentation and Hidden Markov Model
标题：基于文本分割和隐马尔可夫模型的TIFF压缩文档图像直接OCR
链接：https://arxiv.org/abs/2209.09118
作者：Dikshit Sharma,Mohammed Javed
机构：Department of IT, Indian Institute of Information Technology Allahabad, India
备注：The paper has 14 figures and 1 table

【2】 VS-CAM: Vertex Semantic Class Activation Mapping to Interpret Vision Graph Neural Network
标题：VS-CAM：用于视觉图神经网络解释的顶点语义类激活映射
链接：https://arxiv.org/abs/2209.09104
作者：Zhenpeng Feng,Xiyang Cui,Hongbing Ji,Mingzhe Zhu,Ljubisa Stankovic
机构：School of Electronic Engineering, Xidian University, Xi’an, China, University of Montenegro, Podgorica, Montenegro, A R T I C L E I N F O
备注：10 pages, 10 figures

【3】 SFS-A68: a dataset for the segmentation of space functions in apartment buildings
标题：SFS-A68：用于公寓建筑空间功能划分的数据集
链接：https://arxiv.org/abs/2209.09094
作者：Amir Ziaee,Georg Suter
备注：None

【4】 Attentive Symmetric Autoencoder for Brain MRI Segmentation
标题：用于脑MRI分割的注意力对称自动编码器
链接：https://arxiv.org/abs/2209.08887
作者：Junjia Huang,Haofeng Li,Guanbin Li,Xiang Wan
机构： Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Pazhou Lab, Guangzhou, China
备注：MICCAI 2022, code:this https URL

【5】 NeRF-SOS: Any-View Self-supervised Object Segmentation from Complex Real-World Scenes
标题：NERF-SOS：复杂场景中任意视点的自监督目标分割
链接：https://arxiv.org/abs/2209.08776
作者：Zhiwen Fan,Peihao Wang,Xinyu Gong,Yifan Jiang,Dejia Xu,Zhangyang Wang
机构：Department of Electrical and Computer Engineering, University of Texas at Austin

【6】 Semantic Segmentation using Neural Ordinary Differential Equations
标题：基于神经常微分方程组的语义切分
链接：https://arxiv.org/abs/2209.08667
作者：Seyedalireza Khoshsirat,Chandra Kambhamettu
机构：Kambhamettu[,−,−,−,], VIMS Lab, University of Delaware, Newark DE , USA

【7】 Energy Efficient Automatic Streetlight Controlling System using Semantic Segmentation
标题：基于语义分割的节能路灯自动控制系统
链接：https://arxiv.org/abs/2209.08633
作者：Md Sakib Ullah Sourav,Huidong Wang
机构：School of Management Science and Engineering, Shandong University of Finance and, Economics, Jinan, Shandong, China.

【8】 SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
标题：SegNeXt：重新思考语义分割的卷积注意力设计
链接：https://arxiv.org/abs/2209.08575
作者：Meng-Hao Guo,Cheng-Ze Lu,Qibin Hou,Zhengning Liu,Ming-Ming Cheng,Shi-Min Hu
机构：Zheng-Ning Liu, BNRist, Department of Computer Science and Technology, Tsinghua University, TMCC, CS, Nankai University, Fitten Tech, Beijing, China
备注：SegNeXt, a simple CNN for semantic segmentation. Code is available

【9】 DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments
标题：DytanVO：动态环境下视觉里程计和运动分割的联合改进
链接：https://arxiv.org/abs/2209.08430
作者：Shihao Shen,Yilin Cai,Wenshan Wang,Sebastian Scherer
机构： Scherer are with the Robotics Institute, Carnegie Mellon University
备注：Submitted to ICRA 2023

【10】 Automated Segmentation and Recurrence Risk Prediction of Surgically Resected Lung Tumors with Adaptive Convolutional Neural Networks
标题：基于自适应卷积神经网络的肺肿瘤自动分割及复发风险预测
链接：https://arxiv.org/abs/2209.08423
作者：Marguerite B. Basta,Sarfaraz Hussein,Hsiang Hsu,Flavio P. Calmon
机构：John A. Paulson School of Engineering and Applied Sciences, Harvard University, Center for Research in Computer Vision (CRCV), University of Central Florida
备注：9 pages, 5 figures

【11】 Differentiable Topology-Preserved Distance Transform for Pulmonary Airway Segmentation
标题：基于可微拓扑保持距离变换的肺气道分割
链接：https://arxiv.org/abs/2209.08355
作者：Minghui Zhang,Guang-Zhong Yang,Yun Gu
机构：Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China, A R T I C L E I N F O, Article history:, MSC:, Pulmonary, Airway, Segmen-, Learning, Differentiable Distance Trans-, A B S T R A C T
备注：12 pages, 7 figures

【12】 SoftGroup++: Scalable 3D Instance Segmentation with Octree Pyramid Grouping
标题：SoftGroup++：使用八叉树金字塔分组的可伸缩3D实例分割
链接：https://arxiv.org/abs/2209.08263
作者：Thang Vu,Kookhoi Kim,Tung M. Luu,Thanh Nguyen,Junyeong Kim,Chang D. Yoo
机构：Department of Electrical Engineering, Korea Advanced Institute of Science and Technology
备注：Technical report

【13】 Can segmentation models be trained with fully synthetically generated data?
标题：分割模型可以用完全合成的数据来训练吗？
链接：https://arxiv.org/abs/2209.08256
作者：Virginia Fernandez,Walter Hugo Lopez Pinaya,Pedro Borges,Petru-Daniel Tudosiu,Mark S Graham,Tom Vercauteren,M Jorge Cardoso
机构：Tudosiu,[,−,−,−,], Mark S. Graham,[,−,−,−,], Tom, Vercauteren,[,−,−,−,], and M. Jorge Cardoso,[,−,−,−,], King’s College London, London WC,R ,LS, UK
备注：12 pages, 2 (+2 App.) figures, 3 tables. Accepted at Simulation and Synthesis in Medical Imaging workshop (MICCAI 2022)

【14】 Weakly Supervised Medical Image Segmentation With Soft Labels and Noise Robust Loss
标题：具有软标签和噪声鲁棒性损失的弱监督医学图像分割
链接：https://arxiv.org/abs/2209.08172
作者：Banafshe Felfeliyan,Abhilash Hareendranathan,Gregor Kuntze,Stephanie Wichuk,Nils D. Forkert,Jacob L. Jaremko,Janet L. Ronsky
机构：∗Department of Biomedical Engineering, University of Calgary, Calgary, Alberta, Canada, †McCaig Institute for Bone and Joint Health University of Calgary, Calgary, Alberta, Canada

【15】 Belief Revision based Caption Re-ranker with Visual Semantic Information
标题：基于可信度修正的视觉语义字幕重排算法
链接：https://arxiv.org/abs/2209.08163
作者：Ahmed Sabir,Francesc Moreno-Noguer,Pranava Madhyastha,Lluís Padró
机构： Computer Science Department, Universitat Politècnica de Catalunya, Barcelona, Spain, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, Barcelona, Spain, City, University of London, London, UK
备注：COLING 2022

【16】 Automatic Tooth Segmentation from 3D Dental Model using Deep Learning: A Quantitative Analysis of what can be learnt from a Single 3D Dental Model
标题：基于深度学习的三维牙体模型牙齿自动分割：从单个三维牙体模型中学习的定量分析
链接：https://arxiv.org/abs/2209.08132
作者：Ananya Jana,Hrebesh Molly Subhash,Dimitris Metaxas
机构：Colgate-Palmolive Company, Piscataway,USA, Dept. of Computer Science, Rutgers University, New Brunswick, USA
备注：accepted to SIPAIM 2022

【17】 AutoPET Challenge 2022: Step-by-Step Lesion Segmentation in Whole-body FDG-PET/CT
标题：AutoPET挑战2022：在全身FDG-PET/CT中逐步分割病变
链接：https://arxiv.org/abs/2209.09199
作者：Zhantao Liu,Shaonan Zhong,Junyang Mo
机构：School of Biomedical Engineering, Shenzhen University, Shenzhen Guangdong, China
备注：arXiv admin note: substantial text overlap with arXiv:2209.01212

【18】 3D Cross Pseudo Supervision (3D-CPS): A semi-supervised nnU-Net architecture for abdominal organ segmentation
标题：3D交叉伪监督(3D-CPS)：一种用于腹部器官分割的半监督NNU网络结构
链接：https://arxiv.org/abs/2209.08939
作者：Yongzhi Huang,Hanwen Zhang,Yan Yan,Haseeb Hassan,Bingding Huang
机构： College of Big Data and Internet, Shenzhen Technology University, Shenzhen, College of Applied Sciences, Shenzhen University, Shenzhen, China
备注：13 pages, 5 figures

Zero/Few Shot|迁移|域适配|自适应(11篇)

【1】 3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling
标题：3D-PL：3D感知伪标记域自适应深度估计
链接：https://arxiv.org/abs/2209.09231
作者：Yu-Ting Yen,Chia-Ni Lu,Wei-Chen Chiu,Yi-Hsuan Tsai
机构：National Chiao Tung University, Taiwan ,Phiar Technologies
备注：Accepted in ECCV 2022. Project page: this https URL

【2】 Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving
标题：统一自主驾驶多任务协同训练中的有效适应
链接：https://arxiv.org/abs/2209.08953
作者：Xiwen Liang,Yangxin Wu,Jianhua Han,Hang Xu,Chunjing Xu,Xiaodan Liang
机构：Shenzhen Campus of Sun Yat-Sen University,Huawei Noah’s Ark Lab
备注：Accepted at NeurIPS 2022

【3】 Zero-shot Active Visual Search (ZAVIS): Intelligent Object Search for Robotic Assistants
标题：Zero-Shot主动视觉搜索(ZAVIS)：机器人助手的智能对象搜索
链接：https://arxiv.org/abs/2209.08803
作者：Jeongeun Park,Taerim Yoon,Jejoon Hong,Youngjae Yu,Matthew Pan,Sungjoon Choi
机构： 2Jejoon Hong is with the Department of Mechanical Engineering, KoreaUniversity

【4】 Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model
标题：基于潜在空间能量模型学习的自适应多级密度比估计
链接：https://arxiv.org/abs/2209.08739
作者：Zhisheng Xiao,Tian Han
机构：University of Chicago, Chicago, IL, Stevens Institute of Technology, Hoboken, NJ
备注：Accepted to NeurIPS 2022

【5】 Neural Wavelet-domain Diffusion for 3D Shape Generation
标题：基于神经小波域扩散的三维形状生成
链接：https://arxiv.org/abs/2209.08725
作者：Ka-Hei Hui,Ruihui Li,Jingyu Hu,Chi-Wing Fu
机构：The Chinese University of Hong Kong, HK SAR, China, Hunan University

【6】 MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain
标题：Meccano：用于工业领域中人类行为理解的多模式自我中心数据集
链接：https://arxiv.org/abs/2209.08691
作者：Francesco Ragusa,Antonino Furnari,Giovanni Maria Farinella
机构：Next Vision s.r.l., Spin-off of the University of Catania
备注：arXiv admin note: text overlap with arXiv:2010.05654

【7】 Deep Adaptation of Adult-Child Facial Expressions by Fusing Landmark Features
标题：融合标志性特征的成人-儿童面部表情深度适应
链接：https://arxiv.org/abs/2209.08614
作者：Megan A. Witherow,Manar D. Samad,Norou Diawara,Haim Y. Bar,Khan M. Iftekharuddin
机构： Diawara is with the Department of Mathematics & Statistics, Old Dominion University

【8】 ASAP: Adaptive Scheme for Asynchronous Processing of Event-based Vision Algorithms
标题：ASAP：基于事件的视觉算法的自适应异步处理方案
链接：https://arxiv.org/abs/2209.08597
作者：Raul Tapia,Augusto Gómez Eguíluz,José Ramiro Martínez-de Dios,Anibal Ollero
机构：GRVC Robotics Lab., Universidad de Sevilla, Jos´e Ramiro Mart´ınez-de Dios

【9】 Lightweight Spatial-Channel Adaptive Coordination of Multilevel Refinement Enhancement Network for Image Reconstruction
标题：用于图像重建的多级细化增强网络的轻量级空间-通道自适应协调
链接：https://arxiv.org/abs/2209.08337
作者：Yuxi Cai,Huicheng Lai,Zhenghong Jia
机构：College of Information Science and Engineering, Xinjiang University, Urumqi , China

【10】 Mitigating Both Covariate and Conditional Shift for Domain Generalization
标题：减少区域泛化的协变量和条件移位
链接：https://arxiv.org/abs/2209.08253
作者：Jianxin Lin,Yongqiang Tang,Junping Wang,Wensheng Zhang
机构： University of Chinese Academy of Sciences

【11】 Noise transfer for unsupervised domain adaptation of retinal OCT images
标题：基于噪声传递的视网膜OCT图像无监督区域自适应
链接：https://arxiv.org/abs/2209.08097
作者：Valentin Koch,Olle Holmberg,Hannah Spitzer,Johannes Schiefelbein,Ben Asani,Michael Hafner,Fabian J Theis
机构： Technical University of Munich, Munich, Germany, Institute of Computational Biology, Helmholtz Munich, Munich, Germany, Institute of AI for Health, Helmholtz Munich, Munich, Germany
备注：published at MICCAI 2022

半弱无监督|主动学习|不确定性(10篇)

【1】 Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization
标题：约束采样用于类不可知的弱监督目标定位
链接：https://arxiv.org/abs/2209.09195
作者：Shakeeb Murtaza,Soufiane Belharbi,Marco Pedersoli,Aydin Sarraf,Eric Granger
机构： LIVIA, Dept. of Systems Engineering, ÉTS, Montreal, Canada, Ericsson, Global AI Accelerator, Montreal, Canada
备注：3 pages, 2 figures

【2】 On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation
标题：自监督单目深度估计中的稳健横视一致性研究
链接：https://arxiv.org/abs/2209.08747
作者：Haimei Zhao,Jing Zhang,Zhuo Chen,Bo Yuan,Dacheng Tao

【3】 Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fields
标题：密度感知神经网络集成：量化神经辐射场中的预测不确定性
链接：https://arxiv.org/abs/2209.08718
作者：Niko Sünderhauf,Jad Abou-Chakra,Dimity Miller
机构：The authors are with Queensland University of Technology (QUT) inBrisbane

【4】 RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning
标题：RVSL：基于半监督学习的真实危险场景下稳健的车辆相似性学习
链接：https://arxiv.org/abs/2209.08630
作者：Wei-Ting Chen,I-Hsiang Chen,Chih-Yuan Yeh,Hao-Hsiang Yang,Hua-En Chang,Jian-Jiun Ding,Sy-Yen Kuo
机构： Graduate Institute of Electronics Engineering, National Taiwan University, Taiwan, Department of Electrical Engineering, National Taiwan University, Taiwan
备注：Accepted by ECCV 2022

【5】 ActiveNeRF: Learning where to See with Uncertainty Estimation
标题：ActiveNeRF：了解不确定性评估的用武之地
链接：https://arxiv.org/abs/2209.08546
作者：Xuran Pan,Zihang Lai,Shiji Song,Gao Huang
机构： Tsinghua University, Beijing , China, Carnegie Mellon University, Pennsylvania , United States
备注：Accepted by ECCV2022

【6】 Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields
标题：基于神经辐射场的机器人主动三维重建不确定性引导策略
链接：https://arxiv.org/abs/2209.08409
作者：Soomin Lee,Le Chen,Jiahao Wang,Alexander Liniger,Suryansh Kumar,Fisher Yu
备注：8 pages, 9 figure; Accepted for publication at IEEE Robotics and Automation Letters (RA-L) 2022

【7】 Active-Passive SimStereo – Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods
标题：主动-被动模拟立体–基于深度学习的立体方法交叉泛化能力的标杆
链接：https://arxiv.org/abs/2209.08305
作者：Laurent Jospin,Allen Antony,Lian Xu,Hamid Laga,Farid Boussaid,Mohammed Bennamoun
机构：University of Western Australia, Murdoch University
备注：22 pages, 12 figures, accepted in NeurIPS 2022 Datasets and Benchmarks Track

【8】 GedankenNet: Self-supervised learning of hologram reconstruction using physics consistency
标题：GedankenNet：利用物理一致性进行全息重建的自监督学习
链接：https://arxiv.org/abs/2209.08288
作者：Luzhe Huang,Hanlong Chen,Tairan Liu,Aydogan Ozcan
机构： Electrical and Computer Engineering Department, University of California, Los Angeles, Bioengineering Department, University of California, Los Angeles, CA , USA, California NanoSystems Institute (CNSI), University of California, Los Angeles, CA, USA.
备注：30 pages, 6 Figures

【9】 Confidence-Guided Data Augmentation for Deep Semi-Supervised Training
标题：用于深度半监督训练的置信度引导数据增强
链接：https://arxiv.org/abs/2209.08174
作者：Fadoua Khmaissia,Hichem Frigui
机构：University of Louisville, Louisville, KY, USA
备注：7 pages

【10】 Hybrid Parallel Imaging and Compressed Sensing MRI Reconstruction with GRAPPA Integrated Multi-loss Supervised GAN
标题：GRAPPA集成多损耗有监督GaN的并行成像和压缩传感混合成像
链接：https://arxiv.org/abs/2209.08807
作者：Farhan Sadik,Md. Kamrul Hasan
机构：Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka , Bangladesh, A R T I C L E I N F O
备注：12 pages, 11 figures

时序|行为识别|姿态|视频|运动估计(6篇)

【1】 AutoLV: Automatic Lecture Video Generator
标题：AutoLV：讲座视频自动生成器
链接：https://arxiv.org/abs/2209.08795
作者：Wenbin Wang,Yang Song,Sanjay Jha
机构：School of Computer Science and Engineering, University of New South Wales, Australia
备注：4 pages, 4 figures, ICIP 2022

【2】 Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising
标题：百度视频广告中基于树形文本视觉的视频搜索
链接：https://arxiv.org/abs/2209.08759
作者：Tan Yu,Jie Liu,Yi Yang,Yi Li,Hongliang Fei,Ping Li
机构：Cognitive Computing Lab, Baidu Research, Baidu Search Ads (Phoenix Nest), Baidu Inc., NE ,th St. Bellevue, Washington , USA, No. , Xibeiwang East Road, Beijing , China
备注：This revision is based on a manuscript submitted in October 2020, to ICDE 2021. We thank the Program Committee for their valuable comments

【3】 SDFE-LV: A Large-Scale, Multi-Source, and Unconstrained Database for Spotting Dynamic Facial Expressions in Long Videos
标题：SDFE-LV：一个大规模、多源、无约束的长视频动态人脸表情数据库
链接：https://arxiv.org/abs/2209.08445
作者：Xiaolin Xu,Yuan Zong,Wenming Zheng,Yang Li,Chuangao Tang,Xingxun Jiang,Haolin Jiang
机构：School of Biological Science and Medical Engineering, Southeast University, Nanjing, China, Key Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, China

【4】 Spatial-Temporal Deep Embedding for Vehicle Trajectory Reconstruction from High-Angle Video
标题：基于时空深度嵌入的高角视频车辆轨迹重建算法
链接：https://arxiv.org/abs/2209.08417
作者：Tianya T. Zhang Ph. D.,Peter J. Jin Ph. D.,Han Zhou,Benedetto Piccoli,Ph. D
机构：Mathematics, Department, of, Mathematical, Sciences., (E-mail:, Spatial-Temporal Deep Embedding for Vehicle, Trajectory Reconstruction from High-Angle Video

【5】 Continuously Controllable Facial Expression Editing in Talking Face Videos
标题：语音人脸视频中的连续可控表情编辑
链接：https://arxiv.org/abs/2209.08289
作者：Zhiyao Sun,Yu-Hui Wen,Tian Lv,Yanan Sun,Ziyang Zhang,Yaoyuan Wang,Yong-Jin Liu
备注：Demo video: this https URL

【6】 6DOF Pose Estimation of a 3D Rigid Object based on Edge-enhanced Point Pair Features
标题：基于边缘增强点对特征的三维刚体六自由度姿态估计
链接：https://arxiv.org/abs/2209.08266
作者：Chenyi Liu,Fei Chen,Lu Deng,Renjiao Yi,Lintao Zheng,Chenyang Zhu,Jia Wang,Kai Xu
机构：© The Author(s)
备注：16 pages,20 figures

医学相关(2篇)

【1】 Development and Clinical Evaluation of an AI Support Tool for Improving Telemedicine Photo Quality
标题：提高远程医疗影像质量的人工智能支持工具的开发与临床评价
链接：https://arxiv.org/abs/2209.09105
作者：Kailas Vodrahalli,Justin Ko,Albert S. Chiou,Roberto Novoa,Abubakar Abid,Michelle Phung,Kiana Yekrang,Paige Petrone,James Zou,Roxana Daneshjou
机构：These authors contributed equally, Correspondence:, . Department of Electrical Engineering, Stanford University, Stanford, CA, . Department of Dermatology, Stanford School of Medicine, Redwood City, CA
备注：24 pages, 7 figures

【2】 CLAIRE – Parallelized Diffeomorphic Image Registration for Large-Scale Biomedical Imaging Applications
标题：克莱尔–大规模生物医学成像应用中的并行微分图像配准
链接：https://arxiv.org/abs/2209.08189
作者：Naveen Himthani,Malte Brunn,Jae-Youn Kim,Miriam Schulte,Andreas Mang,George Biros
机构： Oden Institute, The University of Texas at Austin, Austin, TX, USA, Institute for Parallel and Distributed Systems, University of Stuttgart, Stuttgart, DE, Department of Mathematics, University of Houston, Houston, TX, USA
备注：32 pages, 9 tables, 8 figures

GAN|对抗|攻击|生成相关(8篇)

【1】 Generating detailed saliency maps using model-agnostic methods
标题：使用与模型无关的方法生成详细的显著图
链接：https://arxiv.org/abs/2209.09202
作者：Maciej Sakowicz
机构：Cycle of studies: postgraduate, Mode of study: Full-time studies, Field of study: Informatics, Specialization: Distributed Applications and Internet Systems, MASTER’S THESIS, Title of thesis: Detailed saliency maps generation using model-agnostic methods
备注：85 pages, 70 figures, Master’s thesis, defended on 2021-12-23 (Gdansk University of Technology)

【2】 DMMGAN: Diverse Multi Motion Prediction of 3D Human Joints using Attention-Based Generative Adverserial Network
标题：DMMGAN：基于注意力的产生式逆序网络三维人体关节多种运动预测
链接：https://arxiv.org/abs/2209.09124
作者：Payam Nikdel,Mohammad Mahdavian,Mo Chen
机构： we assume multiple future motionSchool of Computing Science, Simon Fraser University (SFU)

【3】 Part-Based Models Improve Adversarial Robustness
标题：基于部分的模型提高了对手攻击的稳健性
链接：https://arxiv.org/abs/2209.09117
作者：Chawin Sitawarin,Kornrapat Pongmala,Yizheng Chen,Nicholas Carlini,David Wagner
机构： EECS Department, University of California, Berkeley, Google
备注：Code can be found at this https URL

【4】 MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation
标题：MoVQ：用于高保真图像生成的调制量化矢量
链接：https://arxiv.org/abs/2209.09002
作者：Chuanxia Zheng,Long Tung Vuong,Jianfei Cai,Dinh Phung
机构：Monash University, VinAI

【5】 A model-agnostic approach for generating Saliency Maps to explain inferred decisions of Deep Learning Models
标题：一种与模型无关的方法，用于生成显著图来解释深度学习模型的推断决策
链接：https://arxiv.org/abs/2209.08906
作者：Savvas Karatsiolis,Andreas Kamilaris
机构： CYENS Centre of Excellence, Nicosia, Cyprus, University of Twente, Department of Computer Science, Enschede, The Netherlands

【6】 The Biased Artist: Exploiting Cultural Biases via Homoglyphs in Text-Guided Image Generation Models
标题：有偏见的艺术家：在文本引导的图像生成模型中通过同形文字利用文化偏见
链接：https://arxiv.org/abs/2209.08891
作者：Lukas Struppek,Dominik Hintersdorf,Kristian Kersting
机构：Department of Computer Science, Technical University of Darmstadt, Germany, Centre for Cognitive Science, TU Darmstadt, Germany, Hessian Center for AI (hessian.AI), Darmstadt, Germany
备注：31 pages, 19 figures, 4 tables

【7】 Keypoint-GraspNet: Keypoint-based 6-DoF Grasp Generation from the Monocular RGB-D input
标题：KeyPoint-GraspNet：基于KeyPoint的单目RGB-D输入的6自由度抓取生成
链接：https://arxiv.org/abs/2209.08752
作者：Yiye Chen,Yunzhi Lin,Patricio Vela
机构： Vela are with the School of Electrical andComputer Engineering, and the Institute for Robotics and Intelligent Ma-chines, Georgia Institute of Technology
备注：Submitted to ICRA2023

【8】 A study on the deviations in performance of FNNs and CNNs in the realm of grayscale adversarial images
标题：模糊神经网络和神经网络在灰度对抗性图像领域的性能偏差研究
链接：https://arxiv.org/abs/2209.08262
作者：Durga Shree Nagabushanam,Steve Mathew,Chiranji Lal Chowdhary
机构：Department of Software and Systems Engineering, School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, India - , Data Science and Applications, Indian Institute of Technology Madras, Chennai, India - , Corresponding Author
备注：19 pages, 12 tables, 4 figures

自动驾驶|车辆|车道检测等(1篇)

【1】 Decentralized Vehicle Coordination: The Berkeley DeepDrive Drone Dataset
标题：分散的车辆协调：伯克利DeepDrive无人机数据集
链接：https://arxiv.org/abs/2209.08763
作者：Fangyu Wu,Dequan Wang,Minjune Hwang,Chenhui Hao,Jiawei Lu,Jiamu Zhang,Christopher Chou,Trevor Darrell,Alexandre Bayen
机构： It records rich dynamics of human driving behaviors 1University of California
备注：6 pages, 10 figures, 1 table

OCR|文本相关(1篇)

【1】 A Masked Bounding-Box Selection Based ResNet Predictor for Text Rotation Prediction
标题：一种基于屏蔽边界框选择的ResNet文本旋转预测方法
链接：https://arxiv.org/abs/2209.09198
作者：Michael Yang,Yuan Lin,ChiuMan Ho
机构：OPPO

Attention注意力(4篇)

【1】 EcoFormer: Energy-Saving Attention with Linear Complexity
标题：EcoFormer：具有线性复杂性的节能注意
链接：https://arxiv.org/abs/2209.09004
作者：Jing Liu,Zizheng Pan,Haoyu He,Jianfei Cai,Bohan Zhuang
机构：Department of Data Science & AI, Monash University, Australia
备注：Accepted to NeurIPS 2022; First two authors contributed equally

【2】 Masked Face Inpainting Through Residual Attention UNet
标题：基于残差注意力的蒙面人脸修复技术
链接：https://arxiv.org/abs/2209.08850
作者：Md Imran Hosen,Md Baharul Islam
机构：Department of Computer Engineering, Bahcesehir University, Istanbul, Turkey, American University of Malta
备注：5 pages, 8 figures, Innovations in Intelligent Systems and Applications Conference

【3】 Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation
标题：深度面孔表征学习的尺度注意：一种针对视觉尺度变化的研究
链接：https://arxiv.org/abs/2209.08788
作者：Hailin Shi,Hang Du,Yibo Hu,Jun Wang,Dan Zeng,Ting Yao
机构：JD AI Research, Shanghai University

【4】 EMA-VIO: Deep Visual-Inertial Odometry with External Memory Attention
标题：EMA-VIO：注意外部记忆的深度视觉惯性里程计
链接：https://arxiv.org/abs/2209.08490
作者：Zheming Tu,Changhao Chen,Xianfei Pan,Ruochen Liu,Jiarui Cui,Jun Mao
机构：Pose, Feature, fusion, R,t, External, Memory, Visual
备注：Accepted by IEEE Sensors Journal

人脸|人群计数(5篇)

【1】 BareSkinNet: De-makeup and De-lighting via 3D Face Reconstruction
标题：BareSkinNet：通过3D人脸重建来去妆和去光照
链接：https://arxiv.org/abs/2209.09029
作者：Xingchao Yang,Takafumi Taketomi
机构：CyberAgent, AI Lab, Japan, makeup face image, bare skin image, (de-makeup and de-lighting), example results of texture inference for avatar creation
备注：accepted at PG2022

【2】 T2V-DDPM: Thermal to Visible Face Translation using Denoising Diffusion Probabilistic Models
标题：T2V-DDPM：基于去噪扩散概率模型的热到可见光人脸转换
链接：https://arxiv.org/abs/2209.08814
作者：Nithin Gopalakrishnan Nair,Vishal M. Patel
机构：Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, USA
备注：Accepted at The IEEE conference series on Automatic Face and Gesture Recognition 2023

【3】 D&D: Learning Human Dynamics from Dynamic Camera
标题：D&D：从动态相机中学习人体动力学
链接：https://arxiv.org/abs/2209.08790
作者：Jiefeng Li,Siyuan Bian,Chao Xu,Gang Liu,Gang Yu,Cewu Lu
机构： Shanghai Jiao Tong University, Tencent
备注：ECCV 2022 (Oral)

【4】 Human Performance Modeling and Rendering via Neural Animated Mesh
标题：基于神经动画网格的人体行为建模与绘制
链接：https://arxiv.org/abs/2209.08468
作者：Fuqiang Zhao,Yuheng Jiang,Kaixin Yao,Jiakai Zhang,Liao Wang,Haizhao Dai,Yuhui Zhong,Yingliang Zhang,Minye Wu,Lan Xu,Jingyi Yu
机构：Neural Rendering, AR & VR Application, Neural Animated Mesh
备注：18 pages, 17 figures

【5】 Human Pose Driven Object Effects Recommendation
标题：人体姿势驱动的对象效果推荐
链接：https://arxiv.org/abs/2209.08353
作者：Zhaoxin Fan,Fengxin Li,Hongyan Liu,Jun He,Xiaoyong Du
机构：Renmin university of china, Tinghua university

跟踪(1篇)

【1】 HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking
标题：HVC-Net：统一的单应学习、可见性学习和置信度学习用于平面目标跟踪
链接：https://arxiv.org/abs/2209.08924
作者：Haoxian Zhang,Yonggen Ling
机构： Tencent AI Lab, China, Tencent Robotics X, China
备注：Accepted to ECCV 2022

图像视频检索|Re-id相关(1篇)

【1】 Structure-Aware 3D VR Sketch to 3D Shape Retrieval
标题：基于结构感知的三维虚拟现实草图到三维形状检索
链接：https://arxiv.org/abs/2209.09043
作者：Ling Luo,Yulia Gryaditskaya,Tao Xiang,Yi-Zhe Song
机构：SketchX, CVSSP, University of Surrey, United Kingdom, FlyTek-Surrey Joint Research Centre on Artificial Intelligence, Surrey Institute for People Centred AI and CVSSP, University of Surrey, United Kingdom
备注：Accepted by 3DV 2022

裁剪|量化|加速|压缩相关(1篇)

【1】 PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems
标题：PIM-QAT：用于记忆中处理系统的神经网络量化
链接：https://arxiv.org/abs/2209.08617
作者：Qing Jin,Zhiyu Chen,Jian Ren,Yanyu Li,Yanzhi Wang,Kaiyuan Yang
机构：Northeastern University,Rice Univeristy,Snap Inc.
备注：25 pages, 12 figures, 8 tables

视觉解释|视频理解VQA|caption等(2篇)

【1】 Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances
标题：通过区分表面相似实例克服视觉问答中的语言先验
链接：https://arxiv.org/abs/2209.08529
作者：Yike Wu,Yu Zhao,Shiwan Zhao,Ying Zhang,Xiaojie Yuan,Guoqing Zhao,Ning Jiang
机构： Nankai University, Tianjin, China, Mashang Consumer Finance Co, Ltd
备注：Published in COLING 2022

【2】 Learning Distinct and Representative Modes for Image Captioning
标题：学习图像字幕的不同模式和代表性模式
链接：https://arxiv.org/abs/2209.08231
作者：Qi Chen,Chaorui Deng,Qi Wu
机构：Australian Institute for Machine Learning, University of Adelaide
备注：To be appeared in NeurIPS 2022

超分辨率|去噪|去模糊|去雾(3篇)

【1】 MMSR: Multiple-Model Learned Image Super-Resolution Benefiting From Class-Specific Image Priors
标题：MMSR：受益于特定类别图像先验的多模型学习图像超分辨率
链接：https://arxiv.org/abs/2209.08568
作者：Cansu Korkmaz,A. Murat Tekalp,Zafer Dogan
机构：Koc¸ University, Dept. of Electrical and Electronics Engineering, Istanbul, Turkey
备注：5 pages, 4 figures, accepted for publication in IEEE ICIP 2022 Conference

【2】 Multi-channel Nuclear Norm Minus Frobenius Norm Minimization for Color Image Denoising
标题：彩色图像去噪的多通道核范数减Frobenius范数最小化方法
链接：https://arxiv.org/abs/2209.08094
作者：Yiwen Shan,Dong Hu,Zhi Wang,Tao Jia
机构：College of Computer and Information Science, Southwest University, Chongqing, PR China

【3】 Deep Variation Prior: Joint Image Denoising and Noise Variance Estimation without Clean Data
标题：深度变异先验：无清洁数据的联合图像去噪和噪声方差估计
链接：https://arxiv.org/abs/2209.09214
作者：Rihuan Ke
机构：School of Mathematics, University of Bristol, Bristol, UK

点云|SLAM|雷达|激光|深度RGBD相关(6篇)

【1】 Crowdsourced-based Deep Convolutional Networks for Urban Flood Depth Mapping
标题：基于众包的城市洪水深度测绘的深卷积网络
链接：https://arxiv.org/abs/2209.09200
作者：Bahareh Alizadeh,Amir H. Behzadan
机构：Texas A&M University, College Station, Texas, U.S.
备注：2022 European Conference on Computing in Construction

【2】 LMBAO: A Landmark Map for Bundle Adjustment Odometry in LiDAR SLAM
标题：LMBao：LiDAR SLAM束调里程计的标志性地图
链接：https://arxiv.org/abs/2209.08810
作者：Letian Zhang,Jinping Wang,Lu Jie,Nanjie Chen,Xiaojun Tan,Zhifei Duan
机构： Nanjie Chen and Xiaojun Tan arewith the School of Intelligent Systems Engineering, Sun Yat-sen University
备注：9 pages, 3 tables, 6 figures

【3】 OA-SLAM: Leveraging Objects for Camera Relocalization in Visual SLAM
标题：OA-SLAM：在视觉SLAM中利用对象进行摄像机重新定位
链接：https://arxiv.org/abs/2209.08338
作者：Matthieu Zins,Gilles Simon,Marie-Odile Berger
机构：Universit´e de Lorraine, Inria, LORIA, CNRS
备注：ISMAR 2022

【4】 CARNet:Compression Artifact Reduction for Point Cloud Attribute
标题：CARNET：点云属性的压缩伪影减少
链接：https://arxiv.org/abs/2209.08276
作者：Dandan Ding,Junzhe Zhang,Jianqiang Wang,Zhan Ma
机构： Zhang are with the School of Information Science and Tech-nology, Hangzhou Normal University, Ma is with the School of Electronic Science and Engineer-ing, Nanjing University
备注：13pages, 8figures

【5】 Fast, Accurate and Object Boundary-Aware Surface Normal Estimation from Depth Maps
标题：从深度图快速、准确和物体边界感知的表面法线估计
链接：https://arxiv.org/abs/2209.08241
作者：Saed Moradi,Alireza Memarmoghadam,Denis Laurendeau
机构：Computer Vision and Systems Laboratory (CVSL), Laval University Quebec, QC G,V,A, Canada, Department of Electrical Engineering, University of Isfahan, Isfahan, Iran

【6】 Lossless SIMD Compression of LiDAR Range and Attribute Scan Sequences
标题：激光雷达距离和属性扫描序列的SIMD无损压缩
链接：https://arxiv.org/abs/2209.08196
作者：Jeff Ford,Jordan Ford
机构：CarnegieMellonUniversity

3D|3D重建等相关(1篇)

【1】 DifferSketching: How Differently Do People Sketch 3D Objects?
标题：DifferSketting：人们绘制3D对象的方式有多大不同？
链接：https://arxiv.org/abs/2209.08791
作者：Chufeng Xiao,Wanchao Su,Jing Liao,Zhouhui Lian,Yi-Zhe Song,Hongbo Fu
机构： City University of Hong Kong, School of Creative Media & Department of Computer Science, Wangxuan Institute of Computer Technology, Peking University
备注：SIGGRAPH Asia 2022 (Journal Track)

其他神经网络|深度学习|模型|建模(13篇)

【1】 Look where you look! Saliency-guided Q-networks for visual RL tasks
标题：看看你往哪里看！视觉RL任务的显著导引Q-网络
链接：https://arxiv.org/abs/2209.09203
作者：David Bertoin,Adil Zouitine,Mehdi Zouitine,Emmanuel Rachelson
机构：IRT Saint-Exup´ery, ISAE-SUPAERO, IMT, INSA Toulouse, ANITI, Toulouse, France, IMT, Universit´e Paul Sabatier, Universit´e de Toulouse
备注：None

【2】 Low-Energy Convolutional Neural Networks (CNNs) using Hadamard Method
标题：基于Hadamard方法的低能量卷积神经网络(CNN)
链接：https://arxiv.org/abs/2209.09106
作者：Varun Mannam
机构：Department of Electrical Engineering, University of Notre Dame, Notre Dame, IN

【3】 Disentangling Shape and Pose for Object-Centric Deep Active Inference Models
标题：以对象为中心的深度主动推理模型的形位解缠
链接：https://arxiv.org/abs/2209.09097
作者：Stefano Ferraro,Toon Van de Maele,Pietro Mazzaglia,Tim Verbelen,Bart Dhoedt
机构：IDLab, Department of Information Technology, Ghent University - imec, Ghent, Belgium

【4】 Deep Metric Learning with Chance Constraints
标题：机会约束下的深度度量学习
链接：https://arxiv.org/abs/2209.09060
作者：Yeti Z. Gurbuz,Ogul Can,A. Aydin Alatan
备注：Under review at IEEE Transactions on Neural Networks and Learning Systems

【5】 EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamics
标题：EDO-Net：从图动力学中学习可变形物体的弹性性质
链接：https://arxiv.org/abs/2209.08996
作者：Alberta Longhini,Marco Moletta,Alfredo Reichlin,Michael C. Welle,David Held,Zackory Erickson,Danica Kragic
机构：at KTH Royal Institute of Technology, se 2The authors are with are with Carnegie Mellon University

【6】 Latent Plans for Task-Agnostic Offline Reinforcement Learning
标题：任务无关离线强化学习的潜在计划
链接：https://arxiv.org/abs/2209.08959
作者：Erick Rosete-Beas,Oier Mees,Gabriel Kalweit,Joschka Boedecker,Wolfram Burgard
机构：University of Freiburg ,University of Technology Nuremberg
备注：CoRL 2022. Project website: this http URL

【7】 NeuralMarker: A Framework for Learning General Marker Correspondence
标题：NeuralMarker：学习通用标记通信的框架
链接：https://arxiv.org/abs/2209.08896
作者：Zhaoyang Huang,Xiaokun Pan,Weihong Pan,Weikang Bian,Yan Xu,Ka Chun Cheung,Guofeng Zhang,Hongsheng Li
机构： The Chinese University of Hong Kong and NVIDIA, Zhejiang University
备注：Accepted by ToG (SIGGRAPH Asia 2022). Project Page: this https URL

【8】 Learn the Time to Learn: Replay Scheduling in Continual Learning
标题：学会学习的时间：持续学习中的重播日程安排
链接：https://arxiv.org/abs/2209.08660
作者：Marcus Klasson,Hedvig Kjellström,Cheng Zhang
机构：Silo AI, Stockholm, Sweden

【9】 Perception-Distortion Trade-off in the SR Space Spanned by Flow Models
标题：流动模型跨越的随机共振空间的感知-失真权衡
链接：https://arxiv.org/abs/2209.08564
作者：Cansu Korkmaz,A. Murat Tekalp,Zafer Dogan,Erkut Erdem,Aykut Erdem
机构：a College of Engineering and KUIS AI Center, Koc¸ University, Istanbul, Turkey, b Department of Computer Engineering, Hacettepe University, Ankara, Turkey
备注：5 pages, 4 figures, accepted for publication in IEEE ICIP 2022 Conference

【10】 MetaDIP: Accelerating Deep Image Prior with Meta Learning
标题：MetaDIP：利用元学习加速深度图像处理
链接：https://arxiv.org/abs/2209.08452
作者：Kevin Zhang,Mingyang Xie,Maharshi Gor,Yi-Ting Chen,Yvonne Zhou,Christopher A. Metzler
机构：University of Maryland, College Park

【11】 Introspective Learning : A Two-Stage Approach for Inference in Neural Networks
标题：内省学习：神经网络推理的两阶段方法
链接：https://arxiv.org/abs/2209.08425
作者：Mohit Prabhushankar,Ghassan AlRegib
备注：Accepted at NeurIPS 2022

【12】 Learning to Weight Samples for Dynamic Early-exiting Networks
标题：动态早退网络的样本加权学习
链接：https://arxiv.org/abs/2209.08310
作者：Yizeng Han,Yifan Pu,Zihang Lai,Chaofei Wang,Shiji Song,Junfen Cao,Wenhui Huang,Chao Deng,Gao Huang
机构： Tsinghua University, Beijing , China, Carnegie Mellon University, Pennsylvania , United States, China Mobile Research Institute, Beijing , China
备注：ECCV 2022

【13】 Magnetic Resonance Fingerprinting with compressed sensing and distance metric learning
标题：基于压缩感知和距离度量学习的磁共振指纹识别
链接：https://arxiv.org/abs/2209.08734
作者：Zhe Wang,Hongsheng Li,Qinwei Zhang,Jing Yuan,Xiaogang Wang
机构：a Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong, b Department of Imaging and Interventional Radiology, the Chinese University of Hong Kong, Shatin, Hong Kong, a r t i c l e i n f o, Article history:

其他(25篇)

【1】 Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold
标题：归一化特征的神经崩溃：黎曼流形上的几何分析
链接：https://arxiv.org/abs/2209.09211
作者：Can Yaras,Peng Wang,Zhihui Zhu,Laura Balzano,Qing Qu
机构：Department of Electrical Engineering & Computer Science, University of Michigan, Department of Computer Science & Engineering, Ohio State University
备注：The first two authors contributed to this work equally; 38 pages, 13 figures. Accepted at NeurIPS’22

【2】 Optimized Design Method for Satellite Constellation Configuration Based on Real-time Coverage Area Evaluation
标题：基于实时覆盖面积评估的卫星星座构型优化设计方法
链接：https://arxiv.org/abs/2209.09131
作者：Jiahao Zhou,Boheng Li,Qingxiang Meng
机构：School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China, School of Cyber Science and Engineering, Wuhan University, Wuhan, China, †Equal technical contribution
备注：the 29th International Conference on Geoinformatics, EI

【3】 A Closer Look at Novel Class Discovery from the Labeled Set
标题：基于标号集的新奇类发现研究
链接：https://arxiv.org/abs/2209.09120
作者：Ziyun Li,Jona Otholt,Ben Dai,Di hu,Christoph Meinel,Haojin Yang
机构：Hasso Plattner Institute (HPI), The Chinese University of Hong Kong (CUHK), Renmin University of China (RUC)
备注：18 pages, 13 tables

【4】 Compositional Law Parsing with Latent Random Functions
标题：基于潜在随机函数的构成律分析
链接：https://arxiv.org/abs/2209.09115
作者：Fan Shi,Bin Li,Xiangyang Xue
机构：Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University

【5】 DeePhy: On Deepfake Phylogeny
标题：DeePhy：论Deepfac的系统发展
链接：https://arxiv.org/abs/2209.09111
作者：Kartik Narayan,Harsh Agarwal,Kartik Thakral,Surbhi Mittal,Mayank Vatsa,Richa Singh
机构：IIT Jodhpur, India
备注：Accepted at 2022, International Joint Conference on Biometrics (IJCB 2022)

【6】 Scene Graph Modification as Incremental Structure Expanding
标题：基于增量结构扩展的场景图修改
链接：https://arxiv.org/abs/2209.09093
作者：Xuming Hu,Zhijiang Guo,Yu Fu,Lijie Wen,Philip S. Yu
机构：Tsinghua University, University of Cambridge, University of Illinois at Chicago
备注：In COLING 2022 as a long paper. Code and data available at this https URL

【7】 SOCRATES: A Stereo Camera Trap for Monitoring of Biodiversity
标题：苏格拉底：一种监测生物多样性的立体相机陷阱
链接：https://arxiv.org/abs/2209.09070
作者：Timm Haucke,Hjalmar Kühl,Volker Steinhage
机构：University of Bonn, Institute of Computer Science IV, Friedrich-Hirzebruch-Allee , Bonn, Max Planck Institute for Evolutionary Anthropology, Department of Primatology, Deutscher Platz , Leipzig , Germany

【8】 LAVIS: A Library for Language-Vision Intelligence
标题：Lavis：语言-视觉智能的图书馆
链接：https://arxiv.org/abs/2209.09019
作者：Dongxu Li,Junnan Li,Hung Le,Guangsen Wang,Silvio Savarese,Steven C. H. Hoi
机构：Salesforce Research
备注：Preprint of LAVIS technical report

【9】 Fairness on Synthetic Visual and Thermal Mask Images
标题：合成视觉和热敏蒙版图像的公平性
链接：https://arxiv.org/abs/2209.08762
作者：Kenneth Lai,Vlad Shmerko,Svetlana Yanushkevich
机构：Biometric Technologies Laboratory, Dept. Electrical & Somputer Engineering, University of Calgary
备注：6 pages, 3 figures

【10】 Meta-simulation for the Automated Design of Synthetic Overhead Imagery
标题：合成高空影像自动化设计的元仿真
链接：https://arxiv.org/abs/2209.08685
作者：Handi Yu,Leslie M. Collins,Jordan M. Malof
机构：Department of Electrical and Computer Engineering, Duke University, Durham, NC , USA, Department of Computer Science, University of Montana, Missoula, MT , USA

【11】 Through a fair looking-glass: mitigating bias in image datasets
标题：透过一面公平的镜子：减轻图像数据集中的偏见
链接：https://arxiv.org/abs/2209.08648
作者：Amirarsalan Rajabi,Mehdi Yazdani-Jahromi,Ozlem Ozmen Garibay,Gita Sukthankar
机构： Department of Computer Science, University of Central Florida, Orlando, Florida, USA, Department of Industrial Engineering, and Management Systems

【12】 SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection
标题：SF2SE3：将场景流聚类为SE(3)-通过建议和选择进行运动
链接：https://arxiv.org/abs/2209.08532
作者：Leonhard Sommer,Philipp Schröppel,Thomas Brox
机构：University of Freiburg, Germany
备注：German Conference on Pattern Recognition 2022, Konstanz, Germany

【13】 Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution
标题：卷帘束调整再探：精准快速解决
链接：https://arxiv.org/abs/2209.08503
作者：Bangyan Liao,Delin Qu,Yifei Xue,Huiqing Zhang,Yizhen Lao
机构： Hunan University

【14】 LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF
标题：Latitude：基于城市尺度神经网络的截断动态低通滤波机器人全局定位
链接：https://arxiv.org/abs/2209.08498
作者：Zhenxin Zhu,Yuantao Chen,Zirui Wu,Chao Hou,Yongliang Shi,Chuxuan Li,Pengfei Li,Hao Zhao,Guyue Zhou
机构：Ours, NeRF, t=, Observed Images
备注：7 pages, 6 figures, submitted to ICRA 2023

【15】 Bootstrap Generalization Ability from Loss Landscape Perspective
标题：损失景观视角下的Bootstrap泛化能力
链接：https://arxiv.org/abs/2209.08473
作者：Huanran Chen,Shitong Shao,Ziyi Wang,Zirui Shang,Jin Chen,Xiaofeng Ji,Xinxiao Wu
机构： Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, China, Southeast University, Nanjing, China
备注：18 pages, 4 figures

【16】 MIPI 2022 Challenge on RGBW Sensor Re-mosaic: Dataset and Report
标题：MIPI 2022关于RGBW传感器重新镶嵌的挑战：数据集和报告
链接：https://arxiv.org/abs/2209.08471
作者：Qingyu Yang,Guang Yang,Jun Jiang,Chongyi Li,Ruicheng Feng,Shangchen Zhou,Wenxiu Sun,Qingpeng Zhu,Chen Change Loy,Jinwei Gu
机构：Sun, Rongyuan Wu, Qiaosi Yi, Rongjian Xu, Xiaohui Liu, Zhilu Zhang, Xiaohe, Wu, Ruohao Wang, Junyi Li, Wangmeng Zuo, and Faming Fang
备注：ECCV 2022 Mobile Intelligent Photography and Imaging (MIPI) Workshop–RGBW Sensor Re-mosaic Challenge Report. MIPI workshop website: this http URL arXiv admin note: substantial text overlap with arXiv:2209.07060, arXiv:2209.07530, arXiv:2209.07057

【17】 Shape Completion with Points in the Shadow
标题：使用阴影中的点完成形状
链接：https://arxiv.org/abs/2209.08345
作者：Bowen Zhang,Xi Zhao,He Wang,Ruizhen Hu
机构： Xi’an Jiaotong University, University of Leeds, Shenzhen University, School of Computer Science and Technology, Xi’anJiaotong University (xi
备注：SIGGRAPH Aisa 2022 Conference Paper

【18】 MiNL: Micro-images based Neural Representation for Light Fields
标题：MiNL：基于显微图像的光场神经表示
链接：https://arxiv.org/abs/2209.08277
作者：Hanxin Zhu,Henan Wang,Zhibo Chen
机构：University of Science and Technology of China

【19】 Neural Implicit Surface Reconstruction using Imaging Sonar
标题：基于成像声纳的神经隐式曲面重建
链接：https://arxiv.org/abs/2209.08221
作者：Mohamad Qadri,Michael Kaess,Ioannis Gkioulekas
机构： Gkioulekas are with The RoboticsInstitute, CarnegieMellonUniversity
备注：8 pages, 8 figures. This paper is under review

【20】 Delving Globally into Texture and Structure for Image Inpainting
标题：图像修复中的全局纹理和结构研究
链接：https://arxiv.org/abs/2209.08217
作者：Haipeng Liu,Yang Wang,Meng Wang,Yong Rui
机构：School of Computer Science and Information Engineering, Hefei, China, Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education, Hefei University of Technology, Lenovo Research, Beijing, China, (b) PENNet [,], © BAT [,], (d) CTSDG [,], (e) Ours
备注：9 pages, 10 figures, accepted by ACM Multimedia 2022

【21】 ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots
标题：ScreenQA：手机应用上的大规模问答对截图
链接：https://arxiv.org/abs/2209.08199
作者：Yu-Chung Hsiao,Fedir Zubach,Maria Wang,Jindong,Chen
机构：Google Research

【22】 Evons: A Dataset for Fake and Real News Virality Analysis and Prediction
标题：Evons：一个用于假新闻和真新闻病毒分析和预测的数据集
链接：https://arxiv.org/abs/2209.08129
作者：Kriste Krstovski,Angela Soomin Ryu,Bruce Kogut
机构：Columbia Business School, Columbia University, Data Science Institute, Columbia University, Department of Sociology, Columbia University

【23】 Efficient Subgraph Isomorphism using Graph Topology
标题：基于图拓扑的高效子图同构
链接：https://arxiv.org/abs/2209.09090
作者：Arpan Kusari,Wenbo Sun
机构：University of Michigan Transportation Research Institute, Ann Arbor
备注：Authors contributed equally. Names listed in alphabetical order

【24】 Estimating Brain Age with Global and Local Dependencies
标题：用全局相关性和局部相关性估计脑年龄
链接：https://arxiv.org/abs/2209.08933
作者：Yanwu Yang,Xutao Guo,Zhikai Chang,Chenfei Ye,Yang Xiang,Haiyan Lv,Ting Ma
机构：∗Harbin Institute of Technology at Shenzhen, China, †Peng Cheng Laboratory, Shenzhen, China, ‡Advanced Innovation Center for Human Brain Protection, Capital Medical University, Beijing, China, §Xuanwu Hospital Capital Medical University, Beijing, China

【25】 Deep Plug-and-Play Prior for Hyperspectral Image Restoration
标题：高光谱图像恢复的深度即插即用先验算法
链接：https://arxiv.org/abs/2209.08240
作者：Zeqiang Lai,Kaixuan Wei,Ying Fu
机构：School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.
备注：None