www.arxivdaily.com”即可拜访 cs.CV 方向，今天合计68篇 [检测分类相关]： 【1】 Group Collaborative Learning for Co…
www.arxivdaily.com”即可拜访
cs.CV 方向，今天合计68篇
【1】 Group Collaborative Learning for Co-Salient Object Detection
：Qi Fan,Deng-Ping Fan,Huazhu Fu,Chi Keung Tang,Ling Shao,Yu-Wing Tai
组织：HKUST , Inception Institute of AI (IIAI) , Kwai Inc.
补白：Accepted to CVPR 2021. Project page: this https URL
链接：https://arxiv.org/abs/2104.01108
【2】 End-to-end learning of keypoint detection and matching for relative pose estimation
：Antoine Fond,Luca Del Pero,Nikola Sivacki,Marco Paladini
链接：https://arxiv.org/abs/2104.01085
【3】 TubeR: Tube-Transformer for Action Detection
标题：TUBER：用于动作检测的管Transformer
：Jiaojiao Zhao,Arthur Li,Chunhui Liu,Shuai Bing,Hao Chen,Cees G. M. Snoek,Joseph Tighe
组织：Cees G.M. Snoekl, University of Amsterdam, Amazon Web Service
链接：https://arxiv.org/abs/2104.00969
【4】 HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection
：Jongyoun Noh,Sanghoon Lee,Bumsub Ham
链接：https://arxiv.org/abs/2104.00902
【5】 Adaptive Class Suppression Loss for Long-Tail Object Detection
：Tong Wang,Yousong Zhu,Chaoyang Zhao,Wei Zeng,Jinqiao Wang,Ming Tang
组织：National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, ObjectEye Inc., Beijing, China, Peking University, Beijing, China, Peng Cheng Laboratory, Shenzhen, China, NEXWISE Co., Ltd., Guangzhou, China
补白：CVPR2021 camera ready version
链接：https://arxiv.org/abs/2104.00885
【6】 Unconstrained Face Recognition using ASURF and Cloud-Forest Classifier optimized with VLAD
标题：根据ASURF和VLAD优化的云林分类器的无约束人脸辨认
：A Vinay,Aviral Joshi,Hardik Mahipal Surana,Harsh Garg,K N BalasubramanyaMurthy,S Natarajan
组织：Center for Pattern Recognition and Machine Intelligence, PES University, Bangalore , India
链接：https://arxiv.org/abs/2104.00842
【7】 A study on the effects of compression on hyperspectral image classification
：Kiran Mantripragada,Phuong D. Dao,Yuhong He,Faisal Z. Qureshi
链接：https://arxiv.org/abs/2104.00788
【8】 Remote Sensing Image Classification with the SEN12MS Dataset
：Michael Schmitt,Yu-Lun Wu
补白：accepted for publication in the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (online from July 2021)
链接：https://arxiv.org/abs/2104.00704
【1】 Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
：Karl Stelzner,Kristian Kersting,Adam R. Kosiorek
补白：15 pages, 3 figures. For project page with videos, see this http URL
链接：https://arxiv.org/abs/2104.01148
【2】 Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Network
标题：Plot2API：经过语义解析引导神经网络引荐PLOT中的图形API
：Zeyu Wang,Sheng Huang,Zhongxin Liu,Meng Yan,Xin Xia,Bei Wang,Dan Yang
组织：Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University)., Ministry of Education, China, Chongqing University, Chongqing, China, College of Computer Science and Technology, Zhejiang University, Hangzhou,China, Monash University, Australia
链接：https://arxiv.org/abs/2104.01032
【3】 Visual Semantic Role Labeling for Video Understanding
：Arka Sadhu,Tanmay Gupta,Mark Yatskar,Ram Nevatia,Aniruddha Kembhavi
组织：University of Southern California ,University of Pennsylvania ,PRIOR Allen Institute for Al, vidsitu. org, Seconds, Verb: deflect (block, void), Argo(deflector) woman with shield, Event , Arg, (thing deflected) boulder, Os-,s, Scene, city park, Ev, is enabled by, Verb: talk(speak), Argo(talker), Arg,(hearer), ArgM(manner)ur, Ev, is a, reaction to Ev, Argo (iumper), Arg,(obstacle), ArgM (direction), wards shirtless man, ArgM(goal), to attack sh, Verb: punch( hit), Argo(agent), Arg, (entity punched) man with trident, EvS is unrelated, Verb: punch (to hit), Argo (agent), Arg, (entity punched) w, ArgM(direction) do, down the stairs
链接：https://arxiv.org/abs/2104.00990
【4】 Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
：Youngmin Oh,Beomjun Kim,Bumsub Ham
链接：https://arxiv.org/abs/2104.00905
【5】 Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation
：Zilong Huang,Wentian Hao,Xinggang Wang,Mingyuan Tao,Jianqiang Huang,Wenyu Liu,Xian-Sheng Hua
组织：Huazhong University of Science and Technology, Alibaba Group
链接：https://arxiv.org/abs/2104.00875
【6】 Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction
：Feng Liu,Luan Tran,Xiaoming Liu
组织：Michigan State University, East Lansing MI
链接：https://arxiv.org/abs/2104.00858
【7】 Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation
：Alessandra Lumini,Loris Nanni,Gianluca Maguolo
组织：DEI, University of Padua, viale Gradenigo , Padua, Italy
链接：https://arxiv.org/abs/2104.00850
【8】 Glioblastoma Multiforme Prognosis: MRI Missing Modality Generation, Segmentation and Radiogenomic Survival Prediction
标题：多形性胶质母细胞瘤的预后：MRI缺失形状的发生、切割和放射基因组生计猜测
：Mobarakol Islam,Navodini Wijethilake,Hongliang Ren
组织：Available MRI modalities, Radiomic Feature Extraction, Volume features, Fractal dimension, Genomics, Intensity features, Proposed FCN based, Feature Selection, GAN synthesis model, Kurtosis, Recursive Feature Elimination, Entropy, Histogram, Regression Model, Geometrical features, Length Coordinates, Missing MRI modality, First axis, -Second axis, -Third axis, Centroid coordinates, Prediction, Eigen values, Equatorial eccentricity, Meridional eccentricity, Overall Survival, Segmentation, in days
补白：Under review for a journal
链接：https://arxiv.org/abs/2104.01149
【9】 Prediction of Tuberculosis using U-Net and segmentation techniques
：Dennis Núñez-Fernández,Lamberto Ballan,Gabriel Jiménez-Avalos,Jorge Coronel,Patricia Sheen,Mirko Zimic
组织：Laboratorio de Bioinformatica y Biologia Molecular, Universidad Peruana Cayetano Heredia, Peru, Visual Intelligence and Machine Perception Group, University of Padova, Italy
补白：AI for Public Health Workshop at ICLR 2021. arXiv admin note: text overlap with arXiv:2007.02482
链接：https://arxiv.org/abs/2104.01071
【10】 Brain Tumor Segmentation and Survival Prediction using 3D Attention UNet
：Mobarakol Islam,Vibashan VS,V Jeya Maria Jose,Navodini Wijethilake,Uppal Utkarsh,Hongliang Ren
组织： NUS Graduate School for Integrative Sciences and Engineering, NUS, Singapore, Dept. of Biomedical Engineering, National University of Singapore, Singapore, Dept. of Instrumentation and Control Engineering NIT, Tiruchirappalli, India, Dept. of Electronics and Telecommunications, University of Moratuwa, Srilanka, Dept. of Electrical Engineering, Punjab Engineering College, Chandigarh, India, mobarakolQu. nus. edu, renOnus. edu.sg
补白：MICCAI-BrainLes Workshop
链接：https://arxiv.org/abs/2104.00985
【11】 Glioma Prognosis: Segmentation of the Tumor and Survival Prediction using Shape, Geometric and Clinical Information
标题：胶质瘤预后：根据形状、几许和临床信息的肿瘤切割和生计猜测
：Mobarakol Islam,V Jeya Maria Jose,Hongliang Ren
组织： NUS Graduate School for Integrative Sciences and Engineering (NGS), National, Dept. of Biomedical Engineering, National University of Singapore, Singapore, Dept. of Instrumentation and Control Engineering, National Institute of, Technology, Tiruchirappalli, India
补白：MICCAI-BrainLes Workshop
链接：https://arxiv.org/abs/2104.00980
【1】 NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition
标题：NAS-TC：杂乱动作辨认的时刻卷积神经结构查找
：Pengzhen Ren,Gang Xiao,Xiaojun Chang,Yun Xiao,Zhihui Li,Xiaojiang Chen
链接：https://arxiv.org/abs/2104.01110
【1】 Towards High Fidelity Face Relighting with Realistic Shadows
：Andrew Hou,Ze Zhang,Michel Sarkis,Ning Bi,Yiying Tong,Xiaoming Liu
组织：Michigan State University,Qualcomm Technologies Inc.
链接：https://arxiv.org/abs/2104.00825
【1】 Defending Against Image Corruptions Through Adversarial Augmentations
：Dan A. Calian,Florian Stimberg,Olivia Wiles,Sylvestre-Alvise Rebuffi,Andras Gyorgy,Timothy Mann,Sven Gowal
链接：https://arxiv.org/abs/2104.01086
【2】 Partition-Guided GANs
：Mohammadreza Armandpour,Ali Sadeghian,Chunyuan Li,Mingyuan Zhou
组织：ITexas AM University ,University of Florida, Microsoft Research ,The University of Texas at Austin
链接：https://arxiv.org/abs/2104.00816
【1】 Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstruction
标题：用于三维人体姿势和形状重建的学习型可搬运运动学词典
：Ze Ma,Yifan Yao,Pan Ji,Chao Ma
组织： Shanghai Jiao Tong University, OPPO US Research Center
链接：https://arxiv.org/abs/2104.00953
【2】 UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
标题：无人机-人类：无人驾驶飞行器人类行为了解的大型基准
：Tianjiao Li,Jun Liu,Wei Zhang,Yun Ni,Wenqian Wang,Zhiheng Li
组织：Shandong University, Jinan, Shandong
链接：https://arxiv.org/abs/2104.00946
【3】 Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning
标题：根据回忆对齐学习的回想长时间运动情境的视频猜测
：Sangmin Lee,Hak Gu Kim,Dae Hwi Choi,Hyung-Il Kim,Yong Man Ro
组织：EPFL, Switzerland , ETRI, South Korea
链接：https://arxiv.org/abs/2104.00924
【4】 Self-supervised Video Representation Learning by Context and Motion Decoupling
：Lianghua Huang,Yu Liu,Bin Wang,Pan Pan,Yinghui Xu,Rong Jin
组织：Machine Intelligence Technology Lab, Alibaba Group, xuangen. hlh, ly, ganfu. wb, panpan. pp, renji. xyh, jinrong. jralibaba-inc. com
链接：https://arxiv.org/abs/2104.00862
【1】 Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation
：Octave Mariotti,Hakan Bilen
组织：University of Edinburgh, United Kingdom
链接：https://arxiv.org/abs/2104.01103
【2】 LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
标题：LatentCLR：一种无监督发现可解释方向的比照学习办法
：Oğuz Kaan Yüksel,Enis Simsar,Ezgi Gülperi Er,Pinar Yanardag
组织：EPFL ,TUM ,Bogazici University, [StyleGAN,] Eye style change on FFHQ, [StyleGAN,] Car type on LSUN Cars, [StyleGAN,] Fluffiness on LSUN Cats, [StyleGAN,] Window on LSUN Bedrooms
链接：https://arxiv.org/abs/2104.00820
【1】 Learning to Filter: Siamese Relation Network for Robust Tracking
：Siyuan Cheng,Bineng Zhong,Guorong Li,Xin Liu,Zhenjun Tang,Xianxian Li,Jing Wang
组织：Guangxi Key Lab of Multi-Source Information Mining Security, Guangxi Normal University, Guilin , China, University of Chinese Academy of Sciences, China, Seetatech Technology, Beijing, China
链接：https://arxiv.org/abs/2104.00829
【1】 AI Fairness via Domain Adaptation
链接：https://arxiv.org/abs/2104.01109
【2】 Enhancing Underwater Image via Adaptive Color and Contrast Enhancement, and Denoising
标题：根据自适应色彩和比照度增强及去噪的水下图画增强
：Xinjie Li,Guojia Hou,Kunqian Li
链接：https://arxiv.org/abs/2104.01073
【3】 Low Dose Helical CBCT denoising by using domain filtering with deep reinforcement learning
标题：根据深度强化学习的区域滤波在低剂量螺旋CBCT去噪中的运用
：Wooram Kang,Mayank Patwari
组织：Friedrich Alexander Universitat Erlangen-Nirnberg, Germany
补白：Research project report. 5 pages, 6 figures, 2 tables
链接：https://arxiv.org/abs/2104.00889
【4】 Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation
：Subhankar Roy,Evgeny Krivosheev,Zhun Zhong,Nicu Sebe,Elisa Ricci
组织：University of Trento, Italy ,Fondazione Bruno Kessler, Italy
链接：https://arxiv.org/abs/2104.00808
【5】 Confidence Adaptive Anytime Pixel-Level Recognition
：Zhuang Liu,Trevor Darrell,Evan Shelhamer
组织：UC Berkeley, Adobe Research
链接：https://arxiv.org/abs/2104.00749
【6】 Confidence Calibration for Domain Generalization under Covariate Shift
：Yunye Gong,Xiao Lin,Yi Yao,Thomas G. Dietterich,Ajay Divakaran,Melinda Gervasio
组织：SRI International, Oregon State University
链接：https://arxiv.org/abs/2104.00742
【1】 Network Quantization with Element-wise Gradient Scaling
：Junghyup Lee,Dohyung Kim,Bumsub Ham
链接：https://arxiv.org/abs/2104.00903
【1】 AAformer: Auto-Aligned Transformer for Person Re-Identification
标题：AAformer：用于人员从头辨认的主动对准Transformer
：Kuan Zhu,Haiyun Guo,Shiliang Zhang,Yaowei Wang,Gaopan Huang,Honglin Qiao,Jing Liu,Jinqiao Wang,Ming Tang
组织：Institute of Automation, Chinese Academy of Sciences, Peng Cheng Laboratory, SPeking University ba Group
链接：https://arxiv.org/abs/2104.00921
【1】 S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation
标题：S2R-DepthNet：学习可泛化的特定深度结构表明
：Xiaotian Chen,Yuwang Wang,Xuejin Chen,Wenjun Zeng
组织： University of Science and Technology of China , Microsoft Research Asia
补白：Accepted by CVPR2021(oral)
链接：https://arxiv.org/abs/2104.00877
【1】 NPMs: Neural Parametric Models for 3D Deformable Shapes
：Pablo Palafox,Aljaž Božič,Justus Thies,Matthias Nießner,Angela Dai
组织：Technical University of Munich, Latent, Code, Optimization, P, P, PN, +, ●●, Shape, MLP, tN, Monocular Depth Sequence, Posed Reconstruction
链接：https://arxiv.org/abs/2104.00702
【1】 Developing a New Autism Diagnosis Process Based on a Hybrid Deep Learning Architecture Through Analyzing Home Videos
标题：经过剖析家庭视频开发根据混合深度学习架构的自闭症确诊新流程
补白：11 pages, 3 figures, 4 tables Accepted by International Conference on Artificial Intelligence and Machine Learning for Healthcare Applications (ICAIMLHA 2021)
链接：https://arxiv.org/abs/2104.01137
【2】 Language-based Video Editing via Multi-Modal Multi-Level Transformer
：Tsu-Jui Fu,Xin Eric Wang,Scott T. Grafton,Miguel P. Eckstein,William Yang Wang
组织：UC Santa Barbara UC Santa Cruz
链接：https://arxiv.org/abs/2104.01122
【3】 A Combined Deep Learning based End-to-End Video Coding Architecture for YUV Color Space
标题：一种根据组合深度学习的YUV色彩空间端到端视频编码结构
：Ankitesh K. Singh,Hilmi E. Egilmez,Reza Pourreza,Muhammed Coban,Marta Karczewicz,Taco S. Cohen
组织：Qualcomm Technologies, Inc., San Diego, USA, Qualcomm Technologies Netherlands B., Amsterdam, Netherlands
补白：5 pages, submitted to as a conference paper. arXiv admin note: text overlap with arXiv:2103.01760
链接：https://arxiv.org/abs/2104.00807
【1】 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
标题：Levit：ConvNet服装中的视觉转换器，用于更快的推理
：Ben Graham,Alaaeldin El-Nouby,Hugo Touvron,Pierre Stock,Armand Joulin,Hervé Jégou,Matthijs Douze
组织：Herve Jegou, Matthijs douze
链接：https://arxiv.org/abs/2104.01136
【2】 Scene Graphs: A Survey of Generations and Applications
：Xiaojun Chang,Pengzhen Ren,Pengfei Xu,Zhihui Li,Xiaojiang Chen,Alex Hauptmann
链接：https://arxiv.org/abs/2104.01111
【3】 Geodesic B-Score for Improved Assessment of Knee Osteoarthritis
：Felix Ambellan,Stefan Zachow,Christoph von Tycowicz
组织：Visual and Data-centric Computing, Zuse Institute Berlin, Berlin, Germany
补白：To be published in: Proc. International Conference on Information Processing in Medical Imaging (IPMI) 2021
链接：https://arxiv.org/abs/2104.01107
【4】 Legibility Enhancement of Papyri Using Color Processing and Visual Illusions: A Case Study in Critical Vision
标题：运用色彩处理和视觉幻觉进步纸质资料的易读性--以批判性视觉为例
：Vlad Atanasiu,Isabelle Marthot-Santaniello
补白：Article accepted with minor revisions by the International Journal on Document Analysis and Recognition (IJDAR) on 2021.03.11. Open Source software accessible at this https URL
链接：https://arxiv.org/abs/2104.01106
【5】 MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
标题：MOST：一种面向多方向的本地化细化场景文本检测器
：Minghang He,Minghui Liao,Zhibo Yang,Humen Zhong,Jun Tang,Wenqing Cheng,Cong Yao,Yongpan Wang,Xiang Bai
组织：Huazhong University of Science and Technology, Alibaba Group? Nanjing University
链接：https://arxiv.org/abs/2104.01070
【6】 LiftPool: Bidirectional ConvNet Pooling
：Jiaojiao Zhao,Cees G. M. Snoek
组织：Video Image Sense Lab, University of Amsterdam
补白：published on ICLR 2021
链接：https://arxiv.org/abs/2104.00996
【7】 A Detector-oblivious Multi-arm Network for Keypoint Matching
：Xuelun Shen,Cheng Wang,Xin Li,qian hu,Jingyi Zhang
组织：Xiamen University Louisiana State University
链接：https://arxiv.org/abs/2104.00947
【8】 VisQA: X-raying Vision and Language Reasoning in Transformers
标题：VisQA：“Transformer”中的X射线视觉和言语推理
：Theo Jaunet,Corentin Kervadec,Romain Vuillemot,Grigory Antipov,Moez Baccouche,Christian Wolf
组织：tail , mert tiny init oracle pretra, k-ok,k,k,k,k-, top part of the photo?, acle-pretrain, RESET SELECTION Masked Heads:,, What is that knife in?, What's the knife in?, min med max, Is the bowl to the leftof broccoli?, Language Self-Attention, Is there a spoon that is made of wood?, ood: head GT: no, Is the spoon both sily, d metallic?, nol H--(,%), ]yes T-(,%), man|M, blueIM, orangeIM, Attention Map for head lv__, Global statistics for head lv__, k=, Per Operation, anyen, apple, stem, Per group, Fig. ,. Opening the black box of neural models for vision and language reasoning given an open-ended question and an image, VISQA enables to investigate whether a trained model resorts to reasoning or to bias exploitation to provide its answer. This can be, achieved by exploring the behavior of a set of attention heads each producing an attention map , which manage how differ, items of the problem relate to each other. Heads can be selected , for instance, based on color-coded activity statistics. Their
链接：https://arxiv.org/abs/2104.00926
【9】 Data Augmentation with Manifold Barycenters
：Iaroslav Bespalov,Nazar Buzun,Oleg Kachan,Dmitry V. Dylov
补白：11 pages, 4 figures, 3 tables. I.B., N.B., O.K. contributed equally. D.V.D. is the corresponding author
链接：https://arxiv.org/abs/2104.00925
【10】 Datacentric analysis to reduce pedestrians accidents: A case study in Colombia
标题：削减行人事端的数据中心剖析：哥伦比亚事例研讨
：Michael Puentes,Diana Novoa,John Delgado Nivia,Carlos Barrios Hernández,Oscar Carrillo,Frédéric Le Mouël
组织：Nivia, Carlos J. Barrios Hernandez ,[,-,-,], Oscar, ari-- nd Frederic Le, Universidad Industrial de Santander, Univ Lyon, CPE, INSA Lyon, Inria, CITI, EA, F-, Villeurbanne, France, Univ Lyon, INSA Lyon, Inria, CITI, EA, F-, Villeurbanne, France
链接：https://arxiv.org/abs/2104.00912
【11】 Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
标题：多头比一头好：与多名本地化专家协作生成很少的字体
：Song Park,Sanghyuk Chun,Junbum Cha,Bado Lee,Hyunjung Shim
组织：Yonsei University , NAVER AI Lab , NAVER CLOVA
链接：https://arxiv.org/abs/2104.00887
【12】 Inference of Recyclable Objects with Convolutional Neural Networks
：Jaime Caballero,Francisco Vergara,Randal Miranda,José Serracín
补白：11 pages, preprint version, comments are welcome!
链接：https://arxiv.org/abs/2104.00868
【13】 The Spatially-Correlative Loss for Various Image Translation Tasks
：Chuanxia Zheng,Tat-Jen Cham,Jianfei Cai
组织：Nanyang Technological University, Singapore, Monash University, Australia
链接：https://arxiv.org/abs/2104.00854
【14】 Analyzing and Quantifying Generalization in Convolutional Neural Networks
链接：https://arxiv.org/abs/2104.00851
【15】 SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom
标题：SDAN：用于学习未对准光学变焦的平方可变形对准网络
：Kangfu Mei,Shenglong Ye,Rui Huang
组织：Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen
补白：ICME21. Code is available at this https URL
链接：https://arxiv.org/abs/2104.00848
