---
title: "IEEE Computer Society Conference on Computer Vision and"
description: "All 1,667 papers of IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2021 · page 2 of 17, the most cited first…"
canonical: "https://research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/2/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/2/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [IEEE Computer Society Conference on…](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/) / [2021](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/) / [papers](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/) / page 2

# IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2021: all accepted papers

1,667 papers · page 2 of 17 · the most cited first · [← IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2021](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/)

[← prev](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/) [1](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/) **2** [3](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/3/) … [10](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/10/) … [17](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/17/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/3/)

101. **[Open-Vocabulary Object Detection Using Captions ↗](https://doi.org/10.1109/cvpr46437.2021.01416)**Alireza Zareian, Kevin Dela Rosa, Derek Hao Hu et al.*425 citations*
102. **[SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud ↗](https://doi.org/10.1109/cvpr46437.2021.01426)**Zheng Wu, Weiliang Tang, Li Jiang et al.*425 citations*
103. **[PatchmatchNet: Learned Multi-View Patchmatch Stereo ↗](https://doi.org/10.1109/cvpr46437.2021.01397)**Fangjinhua Wang, Silvano Galliani, Christoph A. Vogel et al.*420 citations*
104. **[Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer ↗](https://doi.org/10.1109/cvpr46437.2021.00292)**Yulin Li, Jianfeng He, Tianzhu Zhang et al.*419 citations*
105. **[Counterfactual VQA: A Cause-Effect Look at Language Bias ↗](https://doi.org/10.1109/cvpr46437.2021.01251)**Yulei Niu, Kaihua Tang, Hanwang Zhang et al.*418 citations*
106. **[Involution: Inverting the Inherence of Convolution for Visual Recognition ↗](https://doi.org/10.1109/cvpr46437.2021.01214)**Duo Li, Jie Hu, Changhu Wang et al.*416 citations*
107. **[Unsupervised Degradation Representation Learning for Blind Super-Resolution ↗](https://doi.org/10.1109/cvpr46437.2021.01044)**Longguang Wang, Yingqian Wang, Xiaoyu Dong et al.*412 citations*
108. **[Track to Detect and Segment: An Online Multi-Object Tracker ↗](https://doi.org/10.1109/cvpr46437.2021.01217)**Jialian Wu, Jiale Cao, Liangchen Song et al.*406 citations*
109. **[HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation ↗](https://doi.org/10.1109/cvpr46437.2021.00339)**Jiefeng Li, Chao Xu, Zhicun Chen et al.*402 citations*
110. **[Prototype Augmentation and Self-Supervision for Incremental Learning ↗](https://doi.org/10.1109/cvpr46437.2021.00581)**Fei Zhu, Xu-Yao Zhang, Chuang Wang et al.*402 citations*
111. **[Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression ↗](https://doi.org/10.1109/cvpr46437.2021.01444)**Zigang Geng, Ke Sun, Bin Xiao et al.*401 citations*
112. **[SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration ↗](https://doi.org/10.1109/cvpr46437.2021.01158)**Sheng Ao, Qingyong Hu, Bo Yang et al.*397 citations*
113. **[StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation ↗](https://doi.org/10.1109/cvpr46437.2021.01267)**Zongze Wu, Dani Lischinski, Eli Shechtman*389 citations*
114. **[Unbiased Mean Teacher for Cross-domain Object Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00408)**Jinhong Deng, Wen Li, Yuhua Chen et al.*381 citations*
115. **[FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation ↗](https://doi.org/10.1109/cvpr46437.2021.00302)**Yisheng He, Haibin Huang, Haoqiang Fan et al.*376 citations*
116. **[PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors ↗](https://doi.org/10.1109/cvpr46437.2021.00710)**Zeyuan Chen, Yang‐Chao Wang, Yang Yang et al.*370 citations*
117. **[Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation ↗](https://doi.org/10.1109/cvpr46437.2021.00416)**Hang Zhou, Yasheng Sun, Wayne Wu et al.*370 citations*
118. **[PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency ↗](https://doi.org/10.1109/cvpr46437.2021.01560)**Xuyang Bai, Zixin Luo, Lei Zhou et al.*366 citations*
119. **[Few-Shot Incremental Learning with Continually Evolved Classifiers ↗](https://doi.org/10.1109/cvpr46437.2021.01227)**Chi Zhang, Nan Song, Guosheng Lin et al.*364 citations*
120. **[Interpreting Super-Resolution Networks with Local Attribution Maps ↗](https://doi.org/10.1109/cvpr46437.2021.00908)**Jinjin Gu, Chao Dong*361 citations*
121. **[Dense Label Encoding for Boundary Discontinuity Free Rotation Detection ↗](https://doi.org/10.1109/cvpr46437.2021.01556)**Xue Yang, Liping Hou, Yue Zhou et al.*360 citations*
122. **[STMTrack: Template-free Visual Tracking with Space-time Memory Networks ↗](https://doi.org/10.1109/cvpr46437.2021.01356)**Zhihong Fu, Qingjie Liu, Zehua Fu et al.*359 citations*
123. **[TediGAN: Text-Guided Diverse Face Image Generation and Manipulation ↗](https://doi.org/10.1109/cvpr46437.2021.00229)**Weihao Xia, Yujiu Yang, Jing‐Hao Xue et al.*359 citations*
124. **[Space-time Neural Irradiance Fields for Free-Viewpoint Video ↗](https://doi.org/10.1109/cvpr46437.2021.00930)**Wenqi Xian, Jia‐Bin Huang, Johannes Kopf et al.*357 citations*
125. **[Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset ↗](https://doi.org/10.1109/cvpr46437.2021.00366)**Zhimeng Zhang, Lincheng Li, Yu Ding et al.*355 citations*
126. **[Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors ↗](https://doi.org/10.1109/cvpr46437.2021.00569)**Tao Yu, Zerong Zheng, Kaiwen Guo et al.*355 citations*
127. **[MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection ↗](https://doi.org/10.1109/cvpr46437.2021.01379)**Jia-Chang Feng, Fa-Ting Hong, Wei‐Shi Zheng*355 citations*
128. **[Rainbow Memory: Continual Learning with a Memory of Diverse Samples ↗](https://doi.org/10.1109/cvpr46437.2021.00812)**Jihwan Bang, Heesu Kim, Youngjoon Yoo et al.*354 citations*
129. **[Reducing Domain Gap by Reducing Style Bias ↗](https://doi.org/10.1109/cvpr46437.2021.00858)**Hyeonseob Nam, HyunJae Lee, Jongchan Park et al.*353 citations*
130. **[CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching ↗](https://doi.org/10.1109/cvpr46437.2021.01369)**Zhelun Shen, Yuchao Dai, Zhibo Rao*351 citations*
131. **[Anomaly Detection in Video via Self-Supervised and Multi-Task Learning ↗](https://doi.org/10.1109/cvpr46437.2021.01255)**Mariana-Iuliana Georgescu, Antonio Bărbălau, Radu Tudor Ionescu et al.*350 citations*
132. **[General Multi-label Image Classification with Transformers ↗](https://doi.org/10.1109/cvpr46437.2021.01621)**Jack Lanchantin, Tianlu Wang, Vicente Ordóñez et al.*350 citations*
133. **[Checkerboard Context Model for Efficient Learned Image Compression ↗](https://doi.org/10.1109/cvpr46437.2021.01453)**Dailan He, Yaoyan Zheng, Baocheng Sun et al.*349 citations*
134. **[Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning ↗](https://doi.org/10.1109/cvpr46437.2021.01641)**Zhenda Xie, Yutong Lin, Zheng Zhang et al.*349 citations*
135. **[Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation ↗](https://doi.org/10.1109/cvpr46437.2021.01354)**Fenglin Liu, Xian Wei Wu, Shen Ge et al.*348 citations*
136. **[Few-Shot Classification with Feature Map Reconstruction Networks ↗](https://doi.org/10.1109/cvpr46437.2021.00792)**Davis Wertheimer, Luming Tang, Bharath Hariharan*348 citations*
137. **[Mutual Graph Learning for Camouflaged Object Detection ↗](https://doi.org/10.1109/cvpr46437.2021.01280)**Qiang Zhai, Xin Li, Fan Yang et al.*345 citations*
138. **[SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction ↗](https://doi.org/10.1109/cvpr46437.2021.00888)**Liushuai Shi, Le Wang, Chengjiang Long et al.*345 citations*
139. **[Cross-Modal Contrastive Learning for Text-to-Image Generation ↗](https://doi.org/10.1109/cvpr46437.2021.00089)**Han Zhang, Jing Yu Koh, Jason Baldridge et al.*343 citations*
140. **[VirTex: Learning Visual Representations from Textual Annotations ↗](https://doi.org/10.1109/cvpr46437.2021.01101)**Karan Desai, Justin M. Johnson*342 citations*
141. **[BoxInst: High-Performance Instance Segmentation with Box Annotations ↗](https://doi.org/10.1109/cvpr46437.2021.00540)**Zhi Tian, Chunhua Shen, Xinlong Wang et al.*341 citations*
142. **[Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00639)**Jiaming Li, Hongtao Xie, Jiahong Li et al.*338 citations*
143. **[RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening ↗](https://doi.org/10.1109/cvpr46437.2021.01141)**Sungha Choi, Sanghun Jung, Huiwon Yun et al.*329 citations*
144. **[Exploring Sparsity in Image Super-Resolution for Efficient Inference ↗](https://doi.org/10.1109/cvpr46437.2021.00488)**Longguang Wang, Xiaoyu Dong, Yingqian Wang et al.*320 citations*
145. **[Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification ↗](https://doi.org/10.1109/cvpr46437.2021.00431)**Qiong Wu, Pingyang Dai, Jie Chen et al.*313 citations*
146. **[NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video ↗](https://doi.org/10.1109/cvpr46437.2021.01534)**Jiaming Sun, Yiming Xie, Linghao Chen et al.*313 citations*
147. **[VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization ↗](https://doi.org/10.1109/cvpr46437.2021.01391)**Seung-Hwan Choi, Sunghyun Park, Minsoo Lee et al.*312 citations*
148. **[Fourier Contour Embedding for Arbitrary-Shaped Text Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00314)**Yiqin Zhu, Jianyong Chen, Lingyu Liang et al.*311 citations*
149. **[HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching ↗](https://doi.org/10.1109/cvpr46437.2021.01413)**Vladimir Tankovich, Christian Häne, Yinda Zhang et al.*309 citations*
150. **[Objects are Different: Flexible Monocular 3D Object Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00330)**Yunpeng Zhang, Jiwen Lu, Jie Zhou*306 citations*
151. **[SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation ↗](https://doi.org/10.1109/cvpr46437.2021.01427)**Siqi Fan, Qiulei Dong, Fenghua Zhu et al.*306 citations*
152. **[PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting ↗](https://doi.org/10.1109/cvpr46437.2021.00541)**Kai Zhang, Fujun Luan, Qianqian Wang et al.*305 citations*
153. **[Graph Stacked Hourglass Networks for 3D Human Pose Estimation ↗](https://doi.org/10.1109/cvpr46437.2021.01584)**Tianhan Xu, Wataru Takano*302 citations*
154. **[NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions ↗](https://doi.org/10.1109/cvpr46437.2021.00965)**Junbin Xiao, Xindi Shang, Angela Yao et al.*302 citations*
155. **[Distribution Alignment: A Unified Framework for Long-tail Visual Recognition ↗](https://doi.org/10.1109/cvpr46437.2021.00239)**Songyang Zhang, Zeming Li, Shipeng Yan et al.*300 citations*
156. **[CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning ↗](https://doi.org/10.1109/cvpr46437.2021.01071)**Chen Wei, Kihyuk Sohn, Clayton Mellina et al.*298 citations*
157. **[Back to the Feature: Learning Robust Camera Localization from Pixels to Pose ↗](https://doi.org/10.1109/cvpr46437.2021.00326)**Paul-Edouard Sarlin, Ajaykumar Unagar, Mans Larsson et al.*297 citations*
158. **[Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification ↗](https://doi.org/10.1109/cvpr46437.2021.00100)**Peng Wang, Kai Han, Xiu-Shen Wei et al.*294 citations*
159. **[GAN Prior Embedded Network for Blind Face Restoration in the Wild ↗](https://doi.org/10.1109/cvpr46437.2021.00073)**Tao Yang, Peiran Ren, Xuansong Xie et al.*294 citations*
160. **[Learning the Best Pooling Strategy for Visual Semantic Embedding ↗](https://doi.org/10.1109/cvpr46437.2021.01553)**Jiacheng Chen, Hexiang Hu, Hao Wu et al.*293 citations*
161. **[Pose Recognition with Cascade Transformers ↗](https://doi.org/10.1109/cvpr46437.2021.00198)**Ke Li, Shijie Wang, Xiang Zhang et al.*292 citations*
162. **[Contrastive Embedding for Generalized Zero-Shot Learning ↗](https://doi.org/10.1109/cvpr46437.2021.00240)**Zongyan Han, Zhenyong Fu, Shuo Chen et al.*291 citations*
163. **[HOTR: End-to-End Human-Object Interaction Detection with Transformers ↗](https://doi.org/10.1109/cvpr46437.2021.00014)**Bumsoo Kim, Junhyun Lee, Jaewoo Kang et al.*291 citations*
164. **[WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition ↗](https://doi.org/10.1109/cvpr46437.2021.01035)**Zheng Dong Zhu, Guan Huang, Jiankang Deng et al.*290 citations*
165. **[Learning Salient Boundary Feature for Anchor-free Temporal Action Localization ↗](https://doi.org/10.1109/cvpr46437.2021.00333)**Chuming Lin, Chengming Xu, Donghao Luo et al.*289 citations*
166. **[FSDR: Frequency Space Domain Randomization for Domain Generalization ↗](https://doi.org/10.1109/cvpr46437.2021.00682)**Jiaxing Huang, Dayan Guan, Aoran Xiao et al.*288 citations*
167. **[Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark ↗](https://doi.org/10.1109/cvpr46437.2021.01355)**Xiao Wang, Xiujun Shu, Zhipeng Zhang et al.*286 citations*
168. **[Uncertainty-aware Joint Salient Object and Camouflaged Object Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00994)**Aixuan Li, Jing Zhang, Yunqiu Lv et al.*286 citations*
169. **[DexYCB: A Benchmark for Capturing Hand Grasping of Objects ↗](https://doi.org/10.1109/cvpr46437.2021.00893)**Yu-Wei Chao, Wei Yang, Xiang Yu et al.*285 citations*
170. **[Deep Stable Learning for Out-Of-Distribution Generalization ↗](https://doi.org/10.1109/cvpr46437.2021.00533)**Xingxuan Zhang, Peng Cui, Renzhe Xu et al.*284 citations*
171. **[Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts ↗](https://doi.org/10.1109/cvpr46437.2021.01533)**Ji Hou, Benjamin Graham, Matthias Nießner et al.*283 citations*
172. **[UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles ↗](https://doi.org/10.1109/cvpr46437.2021.01600)**Tianjiao Li, Jun Liu, Wei Zhang et al.*283 citations*
173. **[Improving Calibration for Long-Tailed Recognition ↗](https://doi.org/10.1109/cvpr46437.2021.01622)**Zhisheng Zhong, Jiequan Cui, Shu Liu et al.*282 citations*
174. **[Improving Sign Language Translation with Monolingual Data by Sign Back-Translation ↗](https://doi.org/10.1109/cvpr46437.2021.00137)**Hao Zhou, Wengang Zhou, Weizhen Qi et al.*282 citations*
175. **[PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation ↗](https://doi.org/10.1109/cvpr46437.2021.00283)**Tal Reiss, Niv Cohen, Liron Bergman et al.*281 citations*
176. **[Large-capacity Image Steganography Based on Invertible Neural Networks ↗](https://doi.org/10.1109/cvpr46437.2021.01067)**Shao-Ping Lu, Rong Wang, Tao Zhong et al.*279 citations*
177. **[Calibrated RGB-D Salient Object Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00935)**Wei Ji, Jingjing Li, Shuang Yu et al.*276 citations*
178. **[PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks ↗](https://doi.org/10.1109/cvpr46437.2021.01151)**Guocheng Qian, Abdulellah Abualshour, Guohao Li et al.*276 citations*
179. **[RSTNet: Captioning with Adaptive Attention on Visual and Non-Visual Words ↗](https://doi.org/10.1109/cvpr46437.2021.01521)**Xuying Zhang, Xiaoshuai Sun, Yunpeng Luo et al.*275 citations*
180. **[Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion ↗](https://doi.org/10.1109/cvpr46437.2021.00180)**Shi Qiu, Saeed Anwar, Nick M. Barnes*275 citations*
181. **[FVC: A New Framework towards Deep Video Compression in Feature Space ↗](https://doi.org/10.1109/cvpr46437.2021.00155)**Zhihao Hu, Guo Sheng Lu, Dong Xu*273 citations*
182. **[Source-Free Domain Adaptation for Semantic Segmentation ↗](https://doi.org/10.1109/cvpr46437.2021.00127)**Yuang Liu, Wei Zhang, Jun Wang*273 citations*
183. **[Representative Forgery Mining for Fake Face Detection ↗](https://doi.org/10.1109/cvpr46437.2021.01468)**Chengrui Wang, Weihong Deng*269 citations*
184. **[Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation ↗](https://doi.org/10.1109/cvpr46437.2021.00406)**Jungbeom Lee, Eunji Kim, Sungroh Yoon*268 citations*
185. **[Delving into Localization Errors for Monocular 3D Object Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00469)**Xinzhu Ma, Yinmin Zhang, Dan Xu et al.*268 citations*
186. **[GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution ↗](https://doi.org/10.1109/cvpr46437.2021.01402)**Kelvin C. K. Chan, Xintao Wang, Xiangyu Xu et al.*268 citations*
187. **[PLOP: Learning without Forgetting for Continual Semantic Segmentation ↗](https://doi.org/10.1109/cvpr46437.2021.00403)**Arthur Douillard, Yifu Chen, Arnaud Dapogny et al.*267 citations*
188. **[Distilling Object Detectors via Decoupled Features ↗](https://doi.org/10.1109/cvpr46437.2021.00219)**Jianyuan Guo, Kai Han, Yunhe Wang et al.*266 citations*
189. **[(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network ↗](https://doi.org/10.1109/cvpr46437.2021.01236)**Ran Cheng, Ryan Razani, Ehsan Taghavi et al.*264 citations*
190. **[Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition ↗](https://doi.org/10.1109/cvpr46437.2021.00618)**Jiahui She, Yibo Hu, Hailin Shi et al.*264 citations*
191. **[Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback ↗](https://doi.org/10.1109/cvpr46437.2021.01115)**Hui Wu, Yupeng Gao, Xiaoxiao Guo et al.*264 citations*
192. **[Neural Scene Graphs for Dynamic Scenes ↗](https://doi.org/10.1109/cvpr46437.2021.00288)**Julian Ost, Fahim Mannan, Nils Thuerey et al.*263 citations*
193. **[Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation ↗](https://doi.org/10.1109/cvpr46437.2021.00545)**Seungho Lee, Minhyun Lee, Jongwuk Lee et al.*263 citations*
194. **[ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows ↗](https://doi.org/10.1109/cvpr46437.2021.00092)**Jie An, Siyu Huang, Yibing Song et al.*262 citations*
195. **[Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral Learning ↗](https://doi.org/10.1109/cvpr46437.2021.01592)**Zhuoran Zheng, Wenqi Ren, Xiaochun Cao et al.*262 citations*
196. **[Beyond Bounding-Box: Convex-hull Feature Adaptation for Oriented and Densely Packed Object Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00868)**Zonghao Guo, Chang Liu, Xiaosong Zhang et al.*258 citations*
197. **[General Instance Distillation for Object Detection ↗](https://doi.org/10.1109/cvpr46437.2021.00775)**Xing Dai, Zeren Jiang, Zhao Wu et al.*258 citations*
198. **[LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search ↗](https://doi.org/10.1109/cvpr46437.2021.01493)**Bin Yan, Houwen Peng, Kan Wu et al.*256 citations*
199. **[Neural Prototype Trees for Interpretable Fine-grained Image Recognition ↗](https://doi.org/10.1109/cvpr46437.2021.01469)**Meike Nauta, Ron van Bree, Christin Seifert*256 citations*
200. **[Probabilistic Embeddings for Cross-Modal Retrieval ↗](https://doi.org/10.1109/cvpr46437.2021.00831)**Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende et al.*256 citations*

[← prev](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/) [1](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/) **2** [3](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/3/) … [10](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/10/) … [17](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/17/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/papers/page/3/)

- [← back to](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/) — IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2021