Awesome Video Understanding

Key papers

• A Survey On Visual Transformer (2020)
  Kai Han, Yunhe Wang, Hanting Chen, et al.
  26.80
• Learning Salient Boundary Feature For Anchor-free Temporal Action Localization (2021)
  Chuming Lin, Chengming Xu, Donghao Luo, et al.
  22.47
• Tubetk: Adopting Tubes To Track Multi-object In A One-step Training Model (2020)
  Bo Pang, Yizhuo Li, Yifan Zhang, et al.
  22.36
• How To Train Your Deep Multi-object Tracker (2019)
  Yihong Xu, Aljosa Osep, Yutong Ban, et al.
  22.35
• Deep Affinity Network For Multiple Object Tracking (2018)
  Shijie Sun, Naveed Akhtar, Huansheng Song, et al.
  22.06
• Tracking Without Bells And Whistles (2019)
  Philipp Bergmann, Tim Meinhardt, Laura Leal-Taixe
  22.04
• Collaborative Video Object Segmentation By Foreground-background Integration (2020)
  Zongxin Yang, Yunchao Wei, Yi Yang
  22.02
• Ranet: Ranking Attention Network For Fast Video Object Segmentation (2019)
  Ziqin Wang, Jun Xu, Li Liu, et al.
  21.97
• Background Suppression Network For Weakly-supervised Temporal Action Localization (2019)
  Pilhyeon Lee, Youngjung Uh, Hyeran Byun
  21.84
• Vadclip: Adapting Vision-language Models For Weakly Supervised Video Anomaly Detection (2023)
  Peng Wu, Xuerong Zhou, Guansong Pang, et al.
  20.92
• Video Object Segmentation Using Space-time Memory Networks (2019)
  Seoung Wug Oh, Joon-Young Lee, Ning Xu, et al.
  20.78
• Swiftnet: Real-time Video Object Segmentation (2021)
  Haochen Wang, Xiaolong Jiang, Haibing Ren, et al.
  20.57
• Relaxed Transformer Decoders For Direct Action Proposal Generation (2021)
  Jing Tan, Jiaqi Tang, Limin Wang, et al.
  20.49
• MOTS: Multi-object Tracking And Segmentation (2019)
  Paul Voigtlaender, Michael Krause, Aljosa Osep, et al.
  20.41
• Youtube-vos: Sequence-to-sequence Video Object Segmentation (2018)
  Ning Xu, Linjie Yang, Yuchen Fan, et al.
  20.04
• 3c-net: Category Count And Center Loss For Weakly-supervised Action Localization (2019)
  Sanath Narayan, Hisham Cholakkal, Fahad Shahbaz Khan, et al.
  19.77
• Quasi-dense Similarity Learning For Multiple Object Tracking (2020)
  Jiangmiao Pang, Linlu Qiu, Xia Li, et al.
  19.58
• Mhformer: Multi-hypothesis Transformer For 3D Human Pose Estimation (2021)
  Wenhao Li, Hong Liu, Hao Tang, et al.
  19.47
• Bottom-up Temporal Action Localization With Mutual Regularization (2020)
  Peisen Zhao, Lingxi Xie, Chen Ju, et al.
  19.32
• Single Shot Temporal Action Detection (2017)
  Tianwei Lin, Xu Zhao, Zheng Shou
  19.29
• Action Segmentation With Joint Self-supervised Temporal Domain Adaptation (2020)
  Min-Hung Chen, Baopu Li, Yingze Bao, et al.
  18.98
• Learning To Estimate Hidden Motions With Global Motion Aggregation (2021)
  Shihao Jiang, Dylan Campbell, Yao Lu, et al.
  18.71
• Cross-view Tracking For Multi-human 3D Pose Estimation At Over 100 FPS (2020)
  Long Chen, Haizhou Ai, Rui Chen, et al.
  18.65
• Dancetrack: Multi-object Tracking In Uniform Appearance And Diverse Motion (2021)
  Peize Sun, Jinkun Cao, Yi Jiang, et al.
  18.56
• M2TR: Multi-modal Multi-scale Transformers For Deepfake Detection (2021)
  Junke Wang, Zuxuan Wu, Wenhao Ouyang, et al.
  18.46
• Foreground Segmentation Using A Triplet Convolutional Neural Network For Multiscale Feature Encoding (2018)
  Long Ang Lim, Hacer Yalim Keles
  18.15
• Hourglass Tokenizer For Efficient Transformer-based 3D Human Pose Estimation (2023)
  Wenhao Li, Mengyuan Liu, Hong Liu, et al.
  17.81
• Spatial-temporal Relation Networks For Multi-object Tracking (2019)
  Jiarui Xu, Yue Cao, Zheng Zhang, et al.
  17.66
• Few-shot Video Classification Via Temporal Alignment (2019)
  Kaidi Cao, Jingwei Ji, Zhangjie Cao, et al.
  17.63
• Humans In 4D: Reconstructing And Tracking Humans With Transformers (2023)
  Shubham Goel, Georgios Pavlakos, Jathushan Rajasegaran, et al.
  17.58
• Blazingly Fast Video Object Segmentation With Pixel-wise Metric Learning (2018)
  Yuhua Chen, Jordi Pont-Tuset, Alberto Montes, et al.
  17.46
• Relation Distillation Networks For Video Object Detection (2019)
  Jiajun Deng, Yingwei Pan, Ting Yao, et al.
  17.32
• VRSTC: Occlusion-free Video Person Re-identification (2019)
  Ruibing Hou, Bingpeng Ma, Hong Chang, et al.
  17.14
• Learning To Track With Object Permanence (2021)
  Pavel Tokmakov, Jie Li, Wolfram Burgard, et al.
  17.11
• Temporal-relational Crosstransformers For Few-shot Action Recognition (2021)
  Toby Perrett, Alessandro Masullo, Tilo Burghardt, et al.
  17.06
• Spatial Temporal Transformer Network For Skeleton-based Action Recognition (2020)
  Chiara Plizzari, Marco Cannici, Matteo Matteucci
  17.06
• Sg-net: Spatial Granularity Network For One-stage Video Instance Segmentation (2021)
  Dongfang Liu, Yiming Cui, Wenbo Tan, et al.
  17.02
• Dmm-net: Differentiable Mask-matching Network For Video Object Segmentation (2019)
  Xiaohui Zeng, Renjie Liao, Li Gu, et al.
  17.02
• Context-aware RCNN: A Baseline For Action Detection In Videos (2020)
  Jianchao Wu, Zhanghui Kuang, Limin Wang, et al.
  16.93
• Modular Interactive Video Object Segmentation: Interaction-to-mask, Propagation And Difference-aware Fusion (2021)
  Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang
  16.86
• Arttrack: Articulated Multi-person Tracking In The Wild (2016)
  Eldar Insafutdinov, Mykhaylo Andriluka, Leonid Pishchulin, et al.
  16.82
• Scsampler: Sampling Salient Clips From Video For Efficient Action Recognition (2019)
  Bruno Korbar, Du Tran, Lorenzo Torresani
  16.77
• Multi-granularity Generator For Temporal Action Proposal (2018)
  Yuan Liu, Lin Ma, Yifeng Zhang, et al.
  16.67
• Video Re-localization (2018)
  Yang Feng, Lin Ma, Wei Liu, et al.
  16.62
• STA: Spatial-temporal Attention For Large-scale Video-based Person Re-identification (2018)
  Yang Fu, Xiaoyang Wang, Yunchao Wei, et al.
  16.61
• Leveraging Photometric Consistency Over Time For Sparsely Supervised Hand-object Reconstruction (2020)
  Yana Hasson, Bugra Tekin, Federica Bogo, et al.
  16.53
• Enhanced Spatio-temporal Interaction Learning For Video Deraining: A Faster And Better Framework (2021)
  Kaihao Zhang, Dongxu Li, Wenhan Luo, et al.
  16.51
• A Generative Appearance Model For End-to-end Video Object Segmentation (2018)
  Joakim Johnander, Martin Danelljan, Emil Brissman, et al.
  16.49
• Frozen CLIP Models Are Efficient Video Learners (2022)
  Ziyi Lin, Shijie Geng, Renrui Zhang, et al.
  16.47
• End-to-end Referring Video Object Segmentation With Multimodal Transformers (2021)
  Adam Botach, Evgenii Zheltonozhskii, Chaim Baskin
  16.45
• Video Panoptic Segmentation (2020)
  Dahun Kim, Sanghyun Woo, Joon-Young Lee, et al.
  16.19
• Fuseformer: Fusing Fine-grained Information In Transformers For Video Inpainting (2021)
  Rui Liu, Hanming Deng, Yangyi Huang, et al.
  16.19
• Efficient Regional Memory Network For Video Object Segmentation (2021)
  Haozhe Xie, Hongxun Yao, Shangchen Zhou, et al.
  16.19
• Kernelized Memory Network For Video Object Segmentation (2020)
  Hongje Seong, Junhyuk Hyun, Euntai Kim
  16.14
• Weakly-supervised Action Localization With Background Modeling (2019)
  Phuc Xuan Nguyen, Deva Ramanan, Charless C. Fowlkes
  16.10
• MAMBA: Multi-level Aggregation Via Memory Bank For Video Object Detection (2024)
  Guanxiong Sun, Yang Hua, Guosheng Hu, et al.
  16.09
• An Efficient And Layout-independent Automatic License Plate Recognition System Based On The YOLO Detector (2019)
  Rayson Laroca, Luiz A. Zanlorensi, Gabriel R. Gonçalves, et al.
  16.05
• Video Transformers: A Survey (2022)
  Javier Selva, Anders S. Johansen, Sergio Escalera, et al.
  15.98
• Occluded Video Instance Segmentation: A Benchmark (2021)
  Jiyang Qi, Yan Gao, Yao Hu, et al.
  15.95
• Sodformer: Streaming Object Detection With Transformer Using Events And Frames (2023)
  Dianze Li, Jianing Li, Yonghong Tian
  15.94