---
title: "ICCV 2021 — all accepted papers, page 12 — the most cited first"
description: "All 1,615 papers of ICCV 2021 · page 12 of 17, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/12/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/12/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [ICCV](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/) / [2021](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/) / [papers](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/) / page 12

# ICCV 2021: all accepted papers

1,615 papers · page 12 of 17 · the most cited first · [← ICCV 2021](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/)

[← prev](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/11/) [1](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/) … [10](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/10/) [11](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/11/) **12** [13](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/13/) … [17](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/17/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/13/)

1101. **[Contrastive Coding for Active Learning under Class Distribution Mismatch ↗](https://doi.org/10.1109/iccv48922.2021.00880)**Pan Du, Suyun Zhao, Hui Chen et al.*29 citations*
1102. **[Cross-Descriptor Visual Localization and Mapping ↗](https://doi.org/10.1109/iccv48922.2021.00600)**Mihai Dusmanu, Ondřej Mikšík, Johannes L. Schönberger et al.*29 citations*
1103. **[Few-Shot and Continual Learning with Attentive Independent Mechanisms ↗](https://doi.org/10.1109/iccv48922.2021.00932)**Eugene Lee, Cheng‐Han Huang, Chen‐Yi Lee*29 citations*
1104. **[Frequency-Aware Spatiotemporal Transformers for Video Inpainting Detection ↗](https://doi.org/10.1109/iccv48922.2021.00808)**Bingyao Yu, Wanhua Li, Xiu Li et al.*29 citations*
1105. **[Generative Compositional Augmentations for Scene Graph Prediction ↗](https://doi.org/10.1109/iccv48922.2021.01553)**Boris A. Knyazev, Harm de Vries, Cătălina Cangea et al.*29 citations*
1106. **[Inferring high-resolution traffic accident risk maps based on satellite imagery and GPS trajectories ↗](https://doi.org/10.1109/iccv48922.2021.01176)**Songtao He, Mohammad Amin Sadeghi, Sanjay Chawla et al.*29 citations*
1107. **[Likelihood-Based Diverse Sampling for Trajectory Forecasting ↗](https://doi.org/10.1109/iccv48922.2021.01303)**Yecheng Jason Ma, Jeevana Priya Inala, Dinesh Jayaraman et al.*29 citations*
1108. **[Lipschitz Continuity Guided Knowledge Distillation ↗](https://doi.org/10.1109/iccv48922.2021.01050)**Yuzhang Shang, Bin Duan, Ziliang Zong et al.*29 citations*
1109. **[Me-Momentum: Extracting Hard Confident Examples from Noisily Labeled Data ↗](https://doi.org/10.1109/iccv48922.2021.00918)**Yingbin Bai, Tongliang Liu*29 citations*
1110. **[NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization ↗](https://doi.org/10.1109/iccv48922.2021.00821)**Haoyue Bai, Fengwei Zhou, Lanqing Hong et al.*29 citations*
1111. **[Normalization Matters in Weakly Supervised Object Localization ↗](https://doi.org/10.1109/iccv48922.2021.00341)**Jeesoo Kim, Junsuk Choe, Sangdoo Yun et al.*29 citations*
1112. **[ODAM: Object Detection, Association, and Mapping using Posed RGB Video ↗](https://doi.org/10.1109/iccv48922.2021.00594)**Kejie Li, Daniel DeTone, Steven Chen et al.*29 citations*
1113. **[SLAMP: Stochastic Latent Appearance and Motion Prediction ↗](https://doi.org/10.1109/iccv48922.2021.01446)**Adil Kaan Akan, Erkut Erdem, Aykut Erdem et al.*29 citations*
1114. **[Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild ↗](https://doi.org/10.1109/iccv48922.2021.00228)**Zhiyu Zhu, Hui Liu, Junhui Hou et al.*29 citations*
1115. **[Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery ↗](https://doi.org/10.1109/iccv48922.2021.00850)**Zhenbo Yu, Jun‐Jie Wang, Jingwei Xu et al.*29 citations*
1116. **[TkML-AP: Adversarial Attacks to Top-k Multi-Label Learning ↗](https://doi.org/10.1109/iccv48922.2021.00755)**Shu Hu, Lipeng Ke, Xin Wang et al.*29 citations*
1117. **[Transforms based Tensor Robust PCA: Corrupted Low-Rank Tensors Recovery via Convex Optimization ↗](https://doi.org/10.1109/iccv48922.2021.00118)**Canyi Lu*29 citations*
1118. **[Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching ↗](https://doi.org/10.1109/iccv48922.2021.01224)**Chao Chen, Zhizhong Han, Yu-Shen Liu et al.*29 citations*
1119. **[Visual Scene Graphs for Audio Source Separation ↗](https://doi.org/10.1109/iccv48922.2021.00124)**Moitreya Chatterjee, Jonathan Le Roux, Narendra Ahuja et al.*29 citations*
1120. **[Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective ↗](https://doi.org/10.1109/iccv48922.2021.00772)**Philipp Benz, Chaoning Zhang, In So Kweon*28 citations*
1121. **[Bayesian Deep Basis Fitting for Depth Completion with Uncertainty ↗](https://doi.org/10.1109/iccv48922.2021.01584)**Chao Qu, Wenxin Liu, Camillo Jose Taylor*28 citations*
1122. **[Continual Learning for Image-Based Camera Localization ↗](https://doi.org/10.1109/iccv48922.2021.00324)**Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov et al.*28 citations*
1123. **[Contrast and Classify: Training Robust VQA Models ↗](https://doi.org/10.1109/iccv48922.2021.00163)**Yash Kant, Abhinav Moudgil, Dhruv Batra et al.*28 citations*
1124. **[DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training ↗](https://doi.org/10.1109/iccv48922.2021.00302)**Kun Yuan, Yiming Chen, Xinmeng Huang et al.*28 citations*
1125. **[Distillation-guided Image Inpainting ↗](https://doi.org/10.1109/iccv48922.2021.00248)**Maitreya Suin, Kuldeep Purohit, Ambasamudram Narayanan Rajagopalan*28 citations*
1126. **[FOVEA: Foveated Image Magnification for Autonomous Navigation ↗](https://doi.org/10.1109/iccv48922.2021.01525)**Chittesh Thavamani, Mengtian Li, Nicolas Cebron et al.*28 citations*
1127. **[Hypergraph Neural Networks for Hypergraph Matching ↗](https://doi.org/10.1109/iccv48922.2021.00130)**Xiaowei Liao, Yong Xu, Haibin Ling*28 citations*
1128. **[Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents ↗](https://doi.org/10.1109/iccv48922.2021.01565)**Shivansh Patel, Saim Wani, Unnat Jain et al.*28 citations*
1129. **[Learning Dual Priors for JPEG Compression Artifacts Removal ↗](https://doi.org/10.1109/iccv48922.2021.00405)**Xueyang Fu, Xi Wang, Aiping Liu et al.*28 citations*
1130. **[Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process ↗](https://doi.org/10.1109/iccv48922.2021.01052)**Fei Ye, Adrian G. Borş*28 citations*
1131. **[Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts ↗](https://doi.org/10.1109/iccv48922.2021.00237)**Bruno Lecouat, Jean Ponce, Julien Mairal*28 citations*
1132. **[MBA-VO: Motion Blur Aware Visual Odometry ↗](https://doi.org/10.1109/iccv48922.2021.00550)**Peidong Liu, Xingxing Zuo, Viktor Larsson et al.*28 citations*
1133. **[ME-PCN: Point Completion Conditioned on Mask Emptiness ↗](https://doi.org/10.1109/iccv48922.2021.01226)**Bingchen Gong, Yinyu Nie, Yiqun Lin et al.*28 citations*
1134. **[Parallel Multi-Resolution Fusion Network for Image Inpainting ↗](https://doi.org/10.1109/iccv48922.2021.01429)**Wentao Wang, Jianfu Zhang, Li Niu et al.*28 citations*
1135. **[Q-Match: Iterative Shape Matching via Quantum Annealing ↗](https://doi.org/10.1109/iccv48922.2021.00749)**Marcel Seelbach Benkner, Zorah Lähner, Vladislav Golyanik et al.*28 citations*
1136. **[Robust Object Detection via Instance-Level Temporal Cycle Confusion ↗](https://doi.org/10.1109/iccv48922.2021.00901)**Xin Wang, Thomas E. Huang, Benlin Liu et al.*28 citations*
1137. **[Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving ↗](https://doi.org/10.1109/iccv48922.2021.01544)**Xuanchi Ren, Tao Yang, Li Erran Li et al.*28 citations*
1138. **[Self-Supervised 3D Face Reconstruction via Conditional Estimation ↗](https://doi.org/10.1109/iccv48922.2021.01304)**Yandong Wen, Weiyang Liu, Bhiksha Raj et al.*28 citations*
1139. **[Unifying Nonlocal Blocks for Neural Networks ↗](https://doi.org/10.1109/iccv48922.2021.01207)**Lei Zhu, Qi She, Duo Li et al.*28 citations*
1140. **[Visual-Textual Attentive Semantic Consistency for Medical Report Generation ↗](https://doi.org/10.1109/iccv48922.2021.00395)**Yi Zhou, Lei Huang, Tao Zhou et al.*28 citations*
1141. **[ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning ↗](https://doi.org/10.1109/iccv48922.2021.01011)**Sangho Lee, Jiwan Chung, Youngjae Yu et al.*27 citations*
1142. **[Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial Attack ↗](https://doi.org/10.1109/iccv48922.2021.01588)**Chin-Yuan Yeh, Hsi-Wen Chen, Hong-Han Shuai et al.*27 citations*
1143. **[BV-Person: A Large-scale Dataset for Bird-view Person Re-identification ↗](https://doi.org/10.1109/iccv48922.2021.01076)**Yan Cheng, Guansong Pang, Lei Wang et al.*27 citations*
1144. **[Confidence Calibration for Domain Generalization under Covariate Shift ↗](https://doi.org/10.1109/iccv48922.2021.00883)**Yunye Gong, Xiao Lin, Yi Yao et al.*27 citations*
1145. **[DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders ↗](https://doi.org/10.1109/iccv48922.2021.01147)**Nicola Garau, Niccolò Bisagno, Piotr Bródka et al.*27 citations*
1146. **[Deep Hybrid Self-Prior for Full 3D Mesh Generation ↗](https://doi.org/10.1109/iccv48922.2021.00575)**Xingkui Wei, Zhengqing Chen, Yanwei Fu et al.*27 citations*
1147. **[Defending against Universal Adversarial Patches by Clipping Feature Norms ↗](https://doi.org/10.1109/iccv48922.2021.01612)**Yu Cheng, Jiansheng Chen, Youze Xue et al.*27 citations*
1148. **[Indoor Scene Generation from a Collection of Semantic-Segmented Depth Images ↗](https://doi.org/10.1109/iccv48922.2021.01492)**Mingjia Yang, Yuxiao Guo, Bin Zhou et al.*27 citations*
1149. **[Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization ↗](https://doi.org/10.1109/iccv48922.2021.01473)**Wei Zhu, Haitian Zheng, Haofu Liao et al.*27 citations*
1150. **[Learning Deep Local Features with Multiple Dynamic Attentions for Large-Scale Image Retrieval ↗](https://doi.org/10.1109/iccv48922.2021.01122)**Hui Wu, Min Wang, Wengang Zhou et al.*27 citations*
1151. **[Learning Instance-level Spatial-Temporal Patterns for Person Re-identification ↗](https://doi.org/10.1109/iccv48922.2021.01466)**Min Ren, Lingxiao He, Xingyu Liao et al.*27 citations*
1152. **[Localize to Binauralize: Audio Spatialization from Visual Sound Source Localization ↗](https://doi.org/10.1109/iccv48922.2021.00194)**Kranthi Kumar Rachavarapu, Aakanksha Aakanksha, Vignesh Sundaresha et al.*27 citations*
1153. **[Long Short View Feature Decomposition via Contrastive Video Representation Learning ↗](https://doi.org/10.1109/iccv48922.2021.00911)**Nadine Behrmann, Mohsen Fayyaz, Jüergen Gall et al.*27 citations*
1154. **[Meta-Attack: Class-agnostic and Model-agnostic Physical Adversarial Attack ↗](https://doi.org/10.1109/iccv48922.2021.00769)**Weiwei Feng, Baoyuan Wu, Tianzhu Zhang et al.*27 citations*
1155. **[Multiple Pairwise Ranking Networks for Personalized Video Summarization ↗](https://doi.org/10.1109/iccv48922.2021.00174)**Yassir Saquil, Da Chen, Yuan He et al.*27 citations*
1156. **[PIAP-DF: Pixel-Interested and Anti Person-Specific Facial Action Unit Detection Net with Discrete Feedback Learning ↗](https://doi.org/10.1109/iccv48922.2021.01266)**Yang Shan Tang, Wangding Zeng, Dafei Zhao et al.*27 citations*
1157. **[Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network ↗](https://doi.org/10.1109/iccv48922.2021.00920)**Yuecong Xu, Jianfei Yang, Haozhi Cao et al.*27 citations*
1158. **[S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation ↗](https://doi.org/10.1109/iccv48922.2021.00742)**Harsh Rangwani, Arihant Jain, Sumukh K Aithal et al.*27 citations*
1159. **[T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging ↗](https://doi.org/10.1109/iccv48922.2021.00393)**Dong Yang, Andriy Myronenko, Xiaosong Wang et al.*27 citations*
1160. **[Time-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systems ↗](https://doi.org/10.1109/iccv48922.2021.00269)**Edwin Vargas, Julien Martel, Gordon Wetzstein et al.*27 citations*
1161. **[Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation ↗](https://doi.org/10.1109/iccv48922.2021.00853)**Zhenbo Yu, Bingbing Ni, Jingwei Xu et al.*27 citations*
1162. **[Towards Efficient Graph Convolutional Networks for Point Cloud Handling ↗](https://doi.org/10.1109/iccv48922.2021.00373)**Yawei Li, He Henry Chen, Zhaopeng Cui et al.*27 citations*
1163. **[Unaligned Image-to-Image Translation by Learning to Reweight ↗](https://doi.org/10.1109/iccv48922.2021.01391)**Shaoan Xie, Mingming Gong, Yanwu Xu et al.*27 citations*
1164. **[Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition ↗](https://doi.org/10.1109/iccv48922.2021.01083)**Xiaodan Hu, Narendra Ahuja*27 citations*
1165. **[iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis ↗](https://doi.org/10.1109/iccv48922.2021.01444)**Andreas Blattmann, Timo Milbich, Michael Dorkenwald et al.*27 citations*
1166. **[A Simple Baseline for Weakly-Supervised Scene Graph Generation ↗](https://doi.org/10.1109/iccv48922.2021.01608)**Jing Shi, Yiwu Zhong, Ning Xu et al.*26 citations*
1167. **[ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer ↗](https://doi.org/10.1109/iccv48922.2021.01180)**Boseung Jeong, Jicheol Park, Suha Kwak*26 citations*
1168. **[Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion ↗](https://doi.org/10.1109/iccv48922.2021.01253)**Lam Huynh, Phong Nguyen-Ha, Jiřı́ Matas et al.*26 citations*
1169. **[Contrasting Contrastive Self-Supervised Representation Learning Pipelines ↗](https://doi.org/10.1109/iccv48922.2021.00980)**Klemen Kotar, Gabriel Ilharco, Ludwig Schmidt et al.*26 citations*
1170. **[Event Stream Super-Resolution via Spatiotemporal Constraint Learning ↗](https://doi.org/10.1109/iccv48922.2021.00444)**Siqi Li, Yutong Feng, Yipeng Li et al.*26 citations*
1171. **[Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes ↗](https://doi.org/10.1109/iccv48922.2021.00776)**Mingjun Yin, Shasha Li, Zikui Cai et al.*26 citations*
1172. **[Impact of Aliasing on Generalization in Deep Convolutional Networks ↗](https://doi.org/10.1109/iccv48922.2021.01036)**Cristina Nader Vasconcelos, Hugo Larochelle, Vincent Dumoulin et al.*26 citations*
1173. **[Pose Correction for Highly Accurate Visual Localization in Large-scale Indoor Spaces ↗](https://doi.org/10.1109/iccv48922.2021.01567)**Janghun Hyeon, Joohyung Kim, Nakju Lett Doh*26 citations*
1174. **[Real-time Instance Segmentation with Discriminative Orientation Maps ↗](https://doi.org/10.1109/iccv48922.2021.00722)**Wentao Du, Zhiyu Xiang, Shuya Chen et al.*26 citations*
1175. **[Robustness via Cross-Domain Ensembles ↗](https://doi.org/10.1109/iccv48922.2021.01197)**Teresa Yeo, Oğuzhan Fatih Kar, Amir Zamir*26 citations*
1176. **[Salient Object Ranking with Position-Preserved Attention ↗](https://doi.org/10.1109/iccv48922.2021.01602)**Hao Fang, Daoxin Zhang, Yi Zhang et al.*26 citations*
1177. **[Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statistics ↗](https://doi.org/10.1109/iccv48922.2021.01401)**Zhiwei Jia, Bodi Yuan, Kangkang Wang et al.*26 citations*
1178. **[Uncertainty-Aware Human Mesh Recovery from Video by Learning Part-Based 3D Dynamics ↗](https://doi.org/10.1109/iccv48922.2021.01215)**Gunhee Lee, Seong–Whan Lee*26 citations*
1179. **[Video Object Segmentation with Dynamic Memory Networks and Adaptive Object Alignment ↗](https://doi.org/10.1109/iccv48922.2021.00796)**Shuxian Liang, Xu Shen, Jianqiang Huang et al.*26 citations*
1180. **[Bit-Mixer: Mixed-precision networks with runtime bit-width selection ↗](https://doi.org/10.1109/iccv48922.2021.00514)**Adrian Bulat, Georgios Tzimiropoulos*25 citations*
1181. **[BlockPlanner: City Block Generation with Vectorized Graph Representation ↗](https://doi.org/10.1109/iccv48922.2021.00503)**Linning Xu, Yuanbo Xiangli, Anyi Rao et al.*25 citations*
1182. **[Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency ↗](https://doi.org/10.1109/iccv48922.2021.00999)**Haiping Wu, Xiaolong Wang*25 citations*
1183. **[Egocentric Pose Estimation from Human Vision Span ↗](https://doi.org/10.1109/iccv48922.2021.01082)**Hao Jiang, Vamsi Krishna Ithapu*25 citations*
1184. **[Exploration and Estimation for Model Compression ↗](https://doi.org/10.1109/iccv48922.2021.00054)**Yanfu Zhang, Shangqian Gao, Heng Huang*25 citations*
1185. **[Extreme-Quality Computational Imaging via Degradation Framework ↗](https://doi.org/10.1109/iccv48922.2021.00263)**Shiqi Chen, Huajun Feng, Keming Gao et al.*25 citations*
1186. **[Factorizing Perception and Policy for Interactive Instruction Following ↗](https://doi.org/10.1109/iccv48922.2021.00190)**Kunal Pratap Singh, Suvaansh Bhambri, Byeonghwi Kim et al.*25 citations*
1187. **[Full-Velocity Radar Returns by Radar-Camera Fusion ↗](https://doi.org/10.1109/iccv48922.2021.01589)**Y. F. Long, Daniel Morris, Xiaoming Liu et al.*25 citations*
1188. **[Gravity-Aware Monocular 3D Human-Object Reconstruction ↗](https://doi.org/10.1109/iccv48922.2021.01214)**Rishabh Dabral, Soshi Shimada, Arjun Jain et al.*25 citations*
1189. **[Neural Strokes: Stylized Line Drawing of 3D Shapes ↗](https://doi.org/10.1109/iccv48922.2021.01394)**Difan Liu, Matthew Fisher, Aaron Hertzmann et al.*25 citations*
1190. **[PoGO-Net: Pose Graph Optimization with Graph Neural Networks ↗](https://doi.org/10.1109/iccv48922.2021.00584)**Xinyi Li, Haibin Ling*25 citations*
1191. **[Robustness and Generalization via Generative Adversarial Training ↗](https://doi.org/10.1109/iccv48922.2021.01542)**Omid Poursaeed, Tianxing Jiang, Harry C. Yang et al.*25 citations*
1192. **[Self-Supervised Representation Learning from Flow Equivariance ↗](https://doi.org/10.1109/iccv48922.2021.01003)**Yuwen Xiong, Mengye Ren, Wenyuan Zeng et al.*25 citations*
1193. **[TransView: Inside, Outside, and Across the Cropping View Boundaries ↗](https://doi.org/10.1109/iccv48922.2021.00418)**Zhiyu Pan, Zhiguo Cao, Kewei Wang et al.*25 citations*
1194. **[Weakly Supervised Segmentation of Small Buildings with Point Labels ↗](https://doi.org/10.1109/iccv48922.2021.00731)**Jae-Hun Lee, ChanYoung Kim, Sanghoon Sull*25 citations*
1195. **[Weakly-Supervised Action Segmentation and Alignment via Transcript-Aware Union-of-Subspaces Learning ↗](https://doi.org/10.1109/iccv48922.2021.00798)**Zijia Lu, Ehsan Elhamifar*25 citations*
1196. **[Active Learning for Lane Detection: A Knowledge Distillation Approach ↗](https://doi.org/10.1109/iccv48922.2021.01487)**Fengchao Peng, Chao Wang, Jianzhuang Liu et al.*24 citations*
1197. **[Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference ↗](https://doi.org/10.1109/iccv48922.2021.00188)**Juncheng Li, Siliang Tang, Linchao Zhu et al.*24 citations*
1198. **[CaT: Weakly Supervised Object Detection with Category Transfer ↗](https://doi.org/10.1109/iccv48922.2021.00306)**Tianyue Cao, Lianyu Du, Xiaoyun Zhang et al.*24 citations*
1199. **[Efficient Action Recognition via Dynamic Knowledge Propagation ↗](https://doi.org/10.1109/iccv48922.2021.01346)**Hanul Kim, Mihir Jain, Jun-Tae Lee et al.*24 citations*
1200. **[End-to-End Video Instance Segmentation via Spatial-Temporal Graph Neural Networks ↗](https://doi.org/10.1109/iccv48922.2021.01062)**Tao Wang, Ning Xu, Kean Chen et al.*24 citations*

[← prev](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/11/) [1](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/) … [10](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/10/) [11](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/11/) **12** [13](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/13/) … [17](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/17/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/13/)

- [← back to](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/) — ICCV 2021