视频大模型 - arXivDaily 专题

2006.15327 2021-06-14 cs.CV cs.LG 57%

Compositional Video Synthesis with Action Graphs

Amir Bar, Roei Herzig, Xiaolong Wang, Anna Rohrbach, Gal Chechik, Trevor Darrell, Amir Globerson

专题命中动作与事件理解：video generation(abstract)；分类 cs.CV

Comments ICML 2021 Camera Ready

2104.09333 2021-04-20 cs.CV 57%

Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting

Anthony Cioppa, Adrien Deliège, Floriane Magera, Silvio Giancola, Olivier Barnich, Bernard Ghanem, Marc Van Droogenbroeck

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments Paper accepted at the CVsports workshop at CVPR2021

2104.08030 2021-04-19 cs.CV 57%

Temporally smooth online action detection using cycle-consistent future anticipation

Young Hwi Kim, Seonghyeon Nam, Seon Joo Kim

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments Accepted by Pattern Recognition

Journal ref Pattern Recognition, Volume 116, August 2021, 107954

2103.16564 2021-03-31 cs.CV cs.AI cs.CL cs.LG cs.SC 57%

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning

Zhenfang Chen, Jiayuan Mao, Jiajun Wu, Kwan-Yee Kenneth Wong, Joshua B. Tenenbaum, Chuang Gan

专题命中动作与事件理解：video reasoning(abstract)；分类 cs.CV

Comments ICLR 2021. Project page: http://dcl.csail.mit.edu/

2103.16024 2021-03-31 cs.CV 57%

Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation

Shuning Chang, Pichao Wang, Fan Wang, Hao Li, Jiashi Feng

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments 12 pagess, 4 figures

2103.11264 2021-03-30 cs.CV cs.AI cs.LG 57%

Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation

M. Saquib Sarfraz, Naila Murray, Vivek Sharma, Ali Diba, Luc Van Gool, Rainer Stiefelhagen

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments CVPR 2021

2103.13141 2021-03-25 cs.CV 57%

Temporal Context Aggregation Network for Temporal Action Proposal Refinement

Zhiwu Qing, Haisheng Su, Weihao Gan, Dongliang Wang, Wei Wu, Xiang Wang, Yu Qiao, Junjie Yan, Changxin Gao, Nong Sang

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments Accepted by CVPR2021

2103.13137 2021-03-25 cs.CV cs.AI 57%

Learning Salient Boundary Feature for Anchor-free Temporal Action Localization

Chuming Lin, Chengming Xu, Donghao Luo, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Yanwei Fu

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments Accepted by CVPR2021

2103.05270 2021-03-10 cs.CV 57%

PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization

Xin Qin, Hanbin Zhao, Guangchen Lin, Hao Zeng, Songcen Xu, Xi Li

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

2103.03465 2021-03-08 cs.CV 57%

Unsupervised Motion Representation Enhanced Network for Action Recognition

Xiaohang Yang, Lingtong Kong, Jie Yang

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments Accepted by ICASSP 2021

2012.10744 2020-12-22 cs.CV 57%

GlocalNet: Class-aware Long-term Human Motion Synthesis

Neeraj Battan, Yudhik Agrawal, Veeravalli Saisooryarao, Aman Goel, Avinash Sharma

专题命中动作与事件理解：video generation(abstract)；分类 cs.CV

Comments Appearing in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

Journal ref 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

2012.07508 2020-12-15 cs.CV cs.AI 57%

Temporal Relational Modeling with Self-Supervision for Action Segmentation

Dong Wang, Di Hu, Xingjian Li, Dejing Dou

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

Comments Accepted by the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)

2008.03014 2020-12-03 cs.CV 57%

A Multi-Task Learning Approach for Human Activity Segmentation and Ergonomics Risk Assessment

Behnoosh Parsa, Ashis G. Banerjee

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

Comments To appear at the 2021 Winter Conference on Applications of Computer Vision (WACV'21)

2011.10190 2020-11-23 cs.CV 57%

Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videos

Reza Ghoddoosian, Saif Sayed, Vassilis Athitsos

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

Comments Accepted to WACV 2021

1903.06531 2020-11-13 cs.CV 57%

High Frame Rate Video Reconstruction based on an Event Camera

Liyuan Pan, Richard Hartley, Cedric Scheerlinck, Miaomiao Liu, Xin Yu, Yuchao Dai

专题命中动作与事件理解：video generation(abstract)；分类 cs.CV

Comments TPAMI 2020. arXiv admin note: substantial text overlap with arXiv:1811.10180

2010.08055 2020-10-19 cs.CV 57%

Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset

Keshav Bhandari, Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments 5 pages, 5 figures, 1 table, 2020 IEEE International Conference on Image Processing (ICIP)

2008.11254 2020-08-27 cs.CV 57%

Temporal Action Localization with Variance-Aware Networks

Ting-Ting Xie, Christos Tzelepis, Ioannis Patras

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

Comments Journal paper; Under review

2007.01971 2020-08-18 cs.GR cs.CV cs.LG stat.ML 57%

Structure-Aware Human-Action Generation

Ping Yu, Yang Zhao, Chunyuan Li, Junsong Yuan, Changyou Chen

专题命中动作与事件理解：video generation(abstract)；分类 cs.CV

Comments accepted by ECCV 2020

2007.00822 2020-07-03 cs.CV 57%

Understanding Road Layout from Videos as a Whole

Buyu Liu, Bingbing Zhuang, Samuel Schulter, Pan Ji, Manmohan Chandraker

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

Comments CVPR 2020

2006.16132 2020-06-30 cs.CV cs.LG 57%

Human Activity Recognition based on Dynamic Spatio-Temporal Relations

Zhenyu Liu, Yaqiang Yao, Yan Liu, Yuening Zhu, Zhenchao Tao, Lei Wang, Yuhong Feng

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

1911.11462 2020-04-06 cs.CV 57%

G-TAD: Sub-Graph Localization for Temporal Action Detection

Mengmeng Xu, Chen Zhao, David S. Rojas, Ali Thabet, Bernard Ghanem

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments Accepted by CVPR2020. 8 pages, 9 figures, 2 pages appendix

1803.11264 2020-04-01 cs.CV 57%

DIY Human Action Data Set Generation

Mehran Khodabandeh, Hamid Reza Vaezi Joze, Ilya Zharkov, Vivek Pradeep

专题命中动作与事件理解：video generation(abstract)；分类 cs.CV

Journal ref The IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2018

2003.00847 2020-03-23 cs.CV 57%

Learning to Deblur and Generate High Frame Rate Video with an Event Camera

Chen Haoyu, Teng Minggui, Shi Boxin, Wang YIzhou, Huang Tiejun

专题命中动作与事件理解：video generation(abstract)；分类 cs.CV

2001.07793 2020-01-23 cs.CV cs.LG 57%

Weakly Supervised Temporal Action Localization Using Deep Metric Learning

Ashraful Islam, Richard J. Radke

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments accepted to WACV 2020

2001.05060 2020-01-16 cs.CV 57%

Recognizing Video Events with Varying Rhythms

Yikang Li, Tianshu Yu, Baoxin Li

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

1910.08250 2019-10-21 cs.CV 57%

AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection

Yiping Tang, Chuang Niu, Minghao Dong, Shenghan Ren, Jimin Liang

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

1910.01286 2019-10-04 cs.CV 57%

Learning Temporal Action Proposals With Fewer Labels

Jingwei Ji, Kaidi Cao, Juan Carlos Niebles

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

1908.10553 2019-10-04 cs.CV 57%

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

Jia-Wang Bian, Zhichao Li, Naiyan Wang, Huangying Zhan, Chunhua Shen, Ming-Ming Cheng, Ian Reid

专题命中动作与事件理解：long video(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2019. Code is available at https://github.com/JiawangBian/SC-SfMLearner-Release

1909.03877 2019-09-10 cs.CV 57%

Gaussian Temporal Awareness Networks for Action Localization

Fuchen Long, Ting Yao, Zhaofan Qiu, Xinmei Tian, Jiebo Luo, Tao Mei

专题命中动作与事件理解：video understanding(abstract)；分类 cs.CV

Comments CVPR 2019 Oral

1812.08861 2019-09-04 cs.GR cs.CV cs.LG stat.ML 57%

Animating Arbitrary Objects via Deep Motion Transfer

Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe

专题命中动作与事件理解：video generation(abstract)；分类 cs.CV

Comments CVPR-2019 (oral)

1. 动作与事件理解 473 篇

Compositional Video Synthesis with Action Graphs

Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting

Temporally smooth online action detection using cycle-consistent future anticipation

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning

Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation

Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation

Temporal Context Aggregation Network for Temporal Action Proposal Refinement

Learning Salient Boundary Feature for Anchor-free Temporal Action Localization

PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization

Unsupervised Motion Representation Enhanced Network for Action Recognition

GlocalNet: Class-aware Long-term Human Motion Synthesis

Temporal Relational Modeling with Self-Supervision for Action Segmentation

A Multi-Task Learning Approach for Human Activity Segmentation and Ergonomics Risk Assessment

Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videos

High Frame Rate Video Reconstruction based on an Event Camera

Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset

Temporal Action Localization with Variance-Aware Networks

Structure-Aware Human-Action Generation

Understanding Road Layout from Videos as a Whole

Human Activity Recognition based on Dynamic Spatio-Temporal Relations

G-TAD: Sub-Graph Localization for Temporal Action Detection

DIY Human Action Data Set Generation

Learning to Deblur and Generate High Frame Rate Video with an Event Camera

Weakly Supervised Temporal Action Localization Using Deep Metric Learning

Recognizing Video Events with Varying Rhythms

AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection

Learning Temporal Action Proposals With Fewer Labels

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

Gaussian Temporal Awareness Networks for Action Localization

Animating Arbitrary Objects via Deep Motion Transfer