---
title: "ICCV 2021 — all accepted papers, page 6 — the most cited first"
description: "All 1,615 papers of ICCV 2021 · page 6 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/6/"
---
[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/6/)

[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 6

# ICCV 2021: all accepted papers

1,615 papers · page 6 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/5/) [1](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/) … [5](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/5/) **6** [7](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/7/) … [10](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/10/) … [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/7/)

501. **[Omniscient Video Super-Resolution ↗](https://doi.org/10.1109/iccv48922.2021.00439)**Peng Yi, Zhongyuan Wang, Kui Jiang et al.*89 citations*
502. **[Waypoint Models for Instruction-guided Navigation in Continuous Environments ↗](https://doi.org/10.1109/iccv48922.2021.01488)**Jacob Krantz, Aaron Gokaslan, Dhruv Batra et al.*89 citations*
503. **[Context Reasoning Attention Network for Image Super-Resolution ↗](https://doi.org/10.1109/iccv48922.2021.00424)**Yulun Zhang, Donglai Wei, Can Qin et al.*88 citations*
504. **[Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation ↗](https://doi.org/10.1109/iccv48922.2021.00711)**Jiabo Huang, Yang Liu, Shaogang Gong et al.*88 citations*
505. **[Hierarchical Object-to-Zone Graph for Object Navigation ↗](https://doi.org/10.1109/iccv48922.2021.01485)**Sixian Zhang, Xinhang Song, Yubing Bai et al.*88 citations*
506. **[Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment ↗](https://doi.org/10.1109/iccv48922.2021.00438)**Lin Zhang, Yong Luo, Yan Bai et al.*87 citations*
507. **[Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation ↗](https://doi.org/10.1109/iccv48922.2021.01376)**Weilun Wang, Wengang Zhou, Jianmin Bao et al.*87 citations*
508. **[LOKI: Long Term and Key Intentions for Trajectory Prediction ↗](https://doi.org/10.1109/iccv48922.2021.00966)**Harshayu Girase, Haiming Gang, Srikanth Malla et al.*87 citations*
509. **[NPMs: Neural Parametric Models for 3D Deformable Shapes ↗](https://doi.org/10.1109/iccv48922.2021.01246)**Pablo R. Palafox, Aljaž Božič, Justus Thies et al.*87 citations*
510. **[Personalized and Invertible Face De-identification by Disentangled Identity Information Manipulation ↗](https://doi.org/10.1109/iccv48922.2021.00332)**Jingyi Cao, Bo Liu, Yunqian Wen et al.*87 citations*
511. **[Semantically Coherent Out-of-Distribution Detection ↗](https://doi.org/10.1109/iccv48922.2021.00819)**Jingkang Yang, Haoqi Wang, Litong Feng et al.*87 citations*
512. **[Black-box Detection of Backdoor Attacks with Limited Information and Data ↗](https://doi.org/10.1109/iccv48922.2021.01617)**Yinpeng Dong, Xiao Hui Yang, Zhijie Deng et al.*86 citations*
513. **[Bringing Events into Video Deblurring with Non-consecutively Blurry Frames ↗](https://doi.org/10.1109/iccv48922.2021.00449)**Wei Shang, Dongwei Ren, Dongqing Zou et al.*86 citations*
514. **[Collaborative Unsupervised Visual Representation Learning from Decentralized Data ↗](https://doi.org/10.1109/iccv48922.2021.00487)**Weiming Zhuang, Xin Gan, Yonggang Wen et al.*86 citations*
515. **[ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation ↗](https://doi.org/10.1109/iccv48922.2021.00710)**Zhenchao Jin, Bin Liu, Qi Chu et al.*86 citations*
516. **[A Latent Transformer for Disentangled Face Editing in Images and Videos ↗](https://doi.org/10.1109/iccv48922.2021.01353)**Xu Yao, Alasdair Newson, Yann Gousseau et al.*85 citations*
517. **[Attention is not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion ↗](https://doi.org/10.1109/iccv48922.2021.00804)**Tao Liang, Guosheng Lin, Lei Feng et al.*85 citations*
518. **[Equivariant Imaging: Learning Beyond the Range Space ↗](https://doi.org/10.1109/iccv48922.2021.00434)**Dongdong Chen, Julián Andrés Tachella, Mike E. Davies*85 citations*
519. **[Generating Smooth Pose Sequences for Diverse Human Motion Prediction ↗](https://doi.org/10.1109/iccv48922.2021.01306)**Wei Mao, Miaomiao Liu, Mathieu Salzmann*85 citations*
520. **[High-Resolution Optical Flow from 1D Attention and Correlation ↗](https://doi.org/10.1109/iccv48922.2021.01033)**Haofei Xu, Jiaolong Yang, Jianfei Cai et al.*85 citations*
521. **[Human Trajectory Prediction via Counterfactual Analysis ↗](https://doi.org/10.1109/iccv48922.2021.00968)**Guangyi Chen, Junlong Li, Jiwen Lu et al.*85 citations*
522. **[Physics-based Human Motion Estimation and Synthesis from Videos ↗](https://doi.org/10.1109/iccv48922.2021.01133)**Kevin Xie, Tingwu Wang, Umar Iqbal et al.*85 citations*
523. **[Road Anomaly Detection by Partial Image Reconstruction with Segmentation Coupling ↗](https://doi.org/10.1109/iccv48922.2021.01536)**Tomas Vojir, Tomas Sipka, Rahaf Aljundi et al.*85 citations*
524. **[Self-Supervised Vessel Segmentation via Adversarial Learning ↗](https://doi.org/10.1109/iccv48922.2021.00744)**Yuxin Ma, Hua Yang, Hanming Deng et al.*85 citations*
525. **[Context-aware Scene Graph Generation with Seq2Seq Transformers ↗](https://doi.org/10.1109/iccv48922.2021.01563)**Yichao Lu, Himanshu Rai, Jason S. Chang et al.*84 citations*
526. **[Exploring Relational Context for Multi-Task Dense Prediction ↗](https://doi.org/10.1109/iccv48922.2021.01557)**David Brüggemann, Menelaos Kanakis, Anton Obukhov et al.*84 citations*
527. **[Learning Unsupervised Metaformer for Anomaly Detection ↗](https://doi.org/10.1109/iccv48922.2021.00433)**Jhih-Ciang Wu, Ding-Jie Chen, Chiou‐Shann Fuh et al.*84 citations*
528. **[Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables ↗](https://doi.org/10.1109/iccv48922.2021.00247)**Tao Wang, Yong Li, Jingyang Peng et al.*84 citations*
529. **[BAPA-Net: Boundary Adaptation and Prototype Alignment for Cross-domain Semantic Segmentation ↗](https://doi.org/10.1109/iccv48922.2021.00868)**Yahao Liu, Jinhong Deng, Xinchen Gao et al.*83 citations*
530. **[Joint Visual and Audio Learning for Video Highlight Detection ↗](https://doi.org/10.1109/iccv48922.2021.00802)**Taivanbat Badamdorj, Mrigank Rochan, Yang Wang et al.*83 citations*
531. **[Meta Gradient Adversarial Attack ↗](https://doi.org/10.1109/iccv48922.2021.00765)**Zheng Yuan, Jie Zhang, Yunpei Jia et al.*83 citations*
532. **[MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments ↗](https://doi.org/10.1109/iccv48922.2021.01255)**Pan Ji, Runze Li, Bir Bhanu et al.*83 citations*
533. **[Orthogonal Projection Loss ↗](https://doi.org/10.1109/iccv48922.2021.01211)**Kanchana Ranasinghe, Muzammal Naseer, Munawar Hayat et al.*83 citations*
534. **[Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches ↗](https://doi.org/10.1109/iccv48922.2021.01278)**Benoît Guillard, Edoardo Remelli, Pierre Yvernay et al.*83 citations*
535. **[Understanding and Evaluating Racial Biases in Image Captioning ↗](https://doi.org/10.1109/iccv48922.2021.01456)**Dora Zhao, Angelina Wang, Olga Russakovsky*83 citations*
536. **[A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation ↗](https://doi.org/10.1109/iccv48922.2021.01276)**Jiteng Mu, Weichao Qiu, Adam Kortylewski et al.*82 citations*
537. **[Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation ↗](https://doi.org/10.1109/iccv48922.2021.00642)**Guile Wu, Shaogang Gong*82 citations*
538. **[Exploiting Explanations for Model Inversion Attacks ↗](https://doi.org/10.1109/iccv48922.2021.00072)**Xuejun Zhao, Wencan Zhang, Xiaokui Xiao et al.*82 citations*
539. **[Learning to Stylize Novel Views ↗](https://doi.org/10.1109/iccv48922.2021.01361)**Hsin–Ping Huang, Hung-Yu Tseng, Saurabh Saini et al.*82 citations*
540. **[Rethinking Noise Synthesis and Modeling in Raw Denoising ↗](https://doi.org/10.1109/iccv48922.2021.00455)**Yi Zhang, Hongwei Qin, Xiaogang Wang et al.*82 citations*
541. **[Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection ↗](https://doi.org/10.1109/iccv48922.2021.00907)**Farzaneh Rezaeianaran, Rakshith Shetty, Rahaf Aljundi et al.*82 citations*
542. **[Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency ↗](https://doi.org/10.1109/iccv48922.2021.00874)**Zhipeng Luo, Zhongang Cai, Changqing Zhou et al.*82 citations*
543. **[Multi-Task Self-Training for Learning General Representations ↗](https://doi.org/10.1109/iccv48922.2021.00873)**Golnaz Ghiasi, Barret Zoph, Ekin D. Cubuk et al.*81 citations*
544. **[ReCU: Reviving the Dead Weights in Binary Neural Networks ↗](https://doi.org/10.1109/iccv48922.2021.00515)**Zihan Xu, Mingbao Lin, Jianzhuang Liu et al.*81 citations*
545. **[RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering ↗](https://doi.org/10.1109/iccv48922.2021.00329)**Shun Iwase, Xingyu Liu, Rawal Khirodkar et al.*81 citations*
546. **[Towards Discriminative Representation Learning for Unsupervised Person Re-identification ↗](https://doi.org/10.1109/iccv48922.2021.00841)**Takashi Isobe, Dong Li, Lu Tian et al.*81 citations*
547. **[Image Harmonization with Transformer ↗](https://doi.org/10.1109/iccv48922.2021.01460)**Zonghui Guo, Dongsheng Guo, Haiyong Zheng et al.*80 citations*
548. **[Region Similarity Representation Learning ↗](https://doi.org/10.1109/iccv48922.2021.01037)**Tete Xiao, Colorado Reed, Xiaolong Wang et al.*80 citations*
549. **[Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark ↗](https://doi.org/10.1109/iccv48922.2021.01575)**Kun Wang, Zhenyu Zhang, Zhiqiang Yan et al.*80 citations*
550. **[Spatio-Temporal Representation Factorization for Video-based Person Re-Identification ↗](https://doi.org/10.1109/iccv48922.2021.00022)**Abhishek Aich, Meng Zheng, Srikrishna Karanam et al.*80 citations*
551. **[Student Customized Knowledge Distillation: Bridging the Gap Between Student and Teacher ↗](https://doi.org/10.1109/iccv48922.2021.00501)**Yichen Zhu, Yi Wang*80 citations*
552. **[Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate ↗](https://doi.org/10.1109/iccv48922.2021.01020)**Xiaofeng Liu, Zhenhua Guo, Site Li et al.*79 citations*
553. **[Domain Generalization via Gradient Surgery ↗](https://doi.org/10.1109/iccv48922.2021.00656)**Lucas Mansilla, Rodrigo Echeveste, Diego Humberto Milone et al.*79 citations*
554. **[Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data ↗](https://doi.org/10.1109/iccv48922.2021.00229)**Abdullah Abuolaim, Mauricio Delbracio, Damien Kelly et al.*79 citations*
555. **[Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection ↗](https://doi.org/10.1109/iccv48922.2021.01287)**Nianjin Ye, Chuan Wang, Haoqiang Fan et al.*79 citations*
556. **[Video Instance Segmentation with a Propose-Reduce Paradigm ↗](https://doi.org/10.1109/iccv48922.2021.00176)**Huaijia Lin, Ruizheng Wu, Shu Liu et al.*79 citations*
557. **[Voxel-based Network for Shape Completion by Leveraging Edge Generation ↗](https://doi.org/10.1109/iccv48922.2021.01294)**Xiaogang Wang, Marcelo H. Ang, Gim Hee Lee*79 citations*
558. **[C3-SemiSeg: Contrastive Semi-supervised Segmentation via Cross-set Learning and Dynamic Class-balancing ↗](https://doi.org/10.1109/iccv48922.2021.00695)**Yanning Zhou, Hang Xu, Wei Zhang et al.*78 citations*
559. **[Domain-Invariant Disentangled Network for Generalizable Object Detection ↗](https://doi.org/10.1109/iccv48922.2021.00865)**Chuang Lin, Zehuan Yuan, Sicheng Zhao et al.*78 citations*
560. **[Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields ↗](https://doi.org/10.1109/iccv48922.2021.00226)**Albert Reed, Hyojin Kim, Rushil Anirudh et al.*78 citations*
561. **[Learning with Noisy Labels via Sparse Regularization ↗](https://doi.org/10.1109/iccv48922.2021.00014)**Xiong Hui Zhou, Xianming Liu, Chenyang Wang et al.*78 citations*
562. **[MGSampler: An Explainable Sampling Strategy for Video Action Recognition ↗](https://doi.org/10.1109/iccv48922.2021.00154)**Yuan Zhi, Zhan Tong, Limin Wang et al.*78 citations*
563. **[Self-supervised Product Quantization for Deep Unsupervised Image Retrieval ↗](https://doi.org/10.1109/iccv48922.2021.01187)**Young Kyun Jang, Nam Ik Cho*78 citations*
564. **[The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation ↗](https://doi.org/10.1109/iccv48922.2021.00168)**Yuankai Qi, Zizheng Pan, Yicong Hong et al.*78 citations*
565. **[Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis ↗](https://doi.org/10.1109/iccv48922.2021.01300)**Jianhua Sun, Yuxuan Li, Hao-Shu Fang et al.*78 citations*
566. **[Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction ↗](https://doi.org/10.1109/iccv48922.2021.01149)**Xiao Tang, Tianyu Wang, Chi‐Wing Fu*78 citations*
567. **[Dual Path Learning for Domain Adaptation of Semantic Segmentation ↗](https://doi.org/10.1109/iccv48922.2021.00895)**Yiting Cheng, Fangyun Wei, Jianmin Bao et al.*77 citations*
568. **[Dynamic Cross Feature Fusion for Remote Sensing Pansharpening ↗](https://doi.org/10.1109/iccv48922.2021.01442)**Xiao Wu, Ting‐Zhu Huang, Liang-Jian Deng et al.*77 citations*
569. **[Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud ↗](https://doi.org/10.1109/iccv48922.2021.00370)**Mingtao Feng, Zhen Li, Qi Li et al.*77 citations*
570. **[Heterogeneous Relational Complement for Vehicle Re-identification ↗](https://doi.org/10.1109/iccv48922.2021.00027)**Jiajian Zhao, Yifan Zhao, Jia Li et al.*77 citations*
571. **[Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization ↗](https://doi.org/10.1109/iccv48922.2021.01339)**Pilhyeon Lee, Hyeran Byun*77 citations*
572. **[Mean Shift for Self-Supervised Learning ↗](https://doi.org/10.1109/iccv48922.2021.01016)**Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash*77 citations*
573. **[Pano-AVQA: Grounded Audio-Visual Question Answering on 360° Videos ↗](https://doi.org/10.1109/iccv48922.2021.00204)**Heeseung Yun, Youngjae Yu, Wonsuk Yang et al.*77 citations*
574. **[SSH: A Self-Supervised Framework for Image Harmonization ↗](https://doi.org/10.1109/iccv48922.2021.00479)**Yifan Jiang, He Zhang, Jianming Zhang et al.*77 citations*
575. **[Self-supervised 3D Skeleton Action Representation Learning with Motion Consistency and Continuity ↗](https://doi.org/10.1109/iccv48922.2021.01308)**Yukun Su, Guosheng Lin, Qingyao Wu*77 citations*
576. **[Vision-Language Navigation with Random Environmental Mixup ↗](https://doi.org/10.1109/iccv48922.2021.00167)**Chong Liu, Fengda Zhu, Xiaojun Chang et al.*77 citations*
577. **[Visual Graph Memory with Unsupervised Representation for Visual Navigation ↗](https://doi.org/10.1109/iccv48922.2021.01559)**Obin Kwon, Nuri Kim, Yunho Choi et al.*77 citations*
578. **[Where are you heading? Dynamic Trajectory Prediction with Expert Goal Examples ↗](https://doi.org/10.1109/iccv48922.2021.00753)**He Zhao, Richard P. Wildes*77 citations*
579. **[Adaptive Surface Normal Constraint for Depth Estimation ↗](https://doi.org/10.1109/iccv48922.2021.01261)**Xiaoxiao Long, Cheng Chung Lin, Lingjie Liu et al.*76 citations*
580. **[Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation ↗](https://doi.org/10.1109/iccv48922.2021.00381)**Yunfei Liu, Ruicong Liu, Haofei Wang et al.*76 citations*
581. **[Local Temperature Scaling for Probability Calibration ↗](https://doi.org/10.1109/iccv48922.2021.00681)**Zhipeng Ding, Xu Han, Peirong Liu et al.*76 citations*
582. **[Neural Image Compression via Attentional Multi-scale Back Projection and Frequency Decomposition ↗](https://doi.org/10.1109/iccv48922.2021.01441)**Ge Gao, Pei You, Rong Pan et al.*76 citations*
583. **[Predicting with Confidence on Unseen Distributions ↗](https://doi.org/10.1109/iccv48922.2021.00117)**Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi et al.*76 citations*
584. **[Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation ↗](https://doi.org/10.1109/iccv48922.2021.01250)**Lina Liu, Xibin Song, Mengmeng Wang et al.*76 citations*
585. **[Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection ↗](https://doi.org/10.1109/iccv48922.2021.00413)**Ni Zhang, Junwei Han, Nian Liu et al.*76 citations*
586. **[TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition ↗](https://doi.org/10.1109/iccv48922.2021.00133)**Wenyuan Xue, Baosheng Yu, Wen Wang et al.*76 citations*
587. **[Variational Feature Disentangling for Fine-Grained Few-Shot Classification ↗](https://doi.org/10.1109/iccv48922.2021.00869)**Jingyi Xu, Hieu Le, Mingzhen Huang et al.*76 citations*
588. **[Aligning Latent and Image Spaces to Connect the Unconnectable ↗](https://doi.org/10.1109/iccv48922.2021.01388)**Ivan Skorokhodov, Grigorii Sotnikov, Mohamed Elhoseiny*75 citations*
589. **[Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation ↗](https://doi.org/10.1109/iccv48922.2021.00878)**Luyu Yang, Yan Wang, Mingfei Gao et al.*75 citations*
590. **[Deep Metric Learning for Open World Semantic Segmentation ↗](https://doi.org/10.1109/iccv48922.2021.01505)**Jun Cen, Yun Peng, Junhao Cai et al.*75 citations*
591. **[Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds ↗](https://doi.org/10.1109/iccv48922.2021.00634)**Longkun Zou, Hui Tang, Ke Chen et al.*75 citations*
592. **[Rehearsal revealed: The limits and merits of revisiting samples in continual learning ↗](https://doi.org/10.1109/iccv48922.2021.00925)**Eli Verwimp, Matthias De Lange, Tinne Tuytelaars*75 citations*
593. **[SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks ↗](https://doi.org/10.1109/iccv48922.2021.00644)**Jiapeng Tang, Jiabao Lei, Dan Xu et al.*75 citations*
594. **[Self-Supervised 3D Hand Pose Estimation from monocular RGB via Contrastive Learning ↗](https://doi.org/10.1109/iccv48922.2021.01104)**Adrian Spurr, Aneesh Dahiya, Xi Wang et al.*75 citations*
595. **[Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder ↗](https://doi.org/10.1109/iccv48922.2021.00929)**Hanwen Liang, Qiong Zhang, Peng Dai et al.*74 citations*
596. **[Contrastive Multimodal Fusion with TupleInfoNCE ↗](https://doi.org/10.1109/iccv48922.2021.00079)**Yunze Liu, Qingnan Fan, Shanghang Zhang et al.*74 citations*
597. **[LoFGAN: Fusing Local Representations for Few-shot Image Generation ↗](https://doi.org/10.1109/iccv48922.2021.00835)**Zheng Gu, Wenbin Li, Jing Huo et al.*74 citations*
598. **[Motion Guided Region Message Passing for Video Captioning ↗](https://doi.org/10.1109/iccv48922.2021.00157)**Shaoxiang Chen, Yu–Gang Jiang*74 citations*
599. **[Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation ↗](https://doi.org/10.1109/iccv48922.2021.00689)**Hui Zhang, Henghui Ding*74 citations*
600. **[Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking ↗](https://doi.org/10.1109/iccv48922.2021.00973)**Gaoang Wang, Renshu Gu, Zuozhu Liu et al.*74 citations*

[← prev](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/5/) [1](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/) … [5](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/5/) **6** [7](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/7/) … [10](https://md.research.elamur.ai/free/en/venues/ieee-cvf-international-conference-on-computer-vision-iccv/2021/papers/page/10/) … [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/7/)

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