视频大模型 - arXivDaily 专题

2106.03152 2021-06-16 cs.CV 57%

Technical Report: Temporal Aggregate Representations

Fadime Sener, Dibyadip Chatterjee, Angela Yao

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2106.05058 2021-06-10 cs.CV 57%

Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition

Ziyuan Huang, Zhiwu Qing, Xiang Wang, Yutong Feng, Shiwei Zhang, Jianwen Jiang, Zhurong Xia, Mingqian Tang, Nong Sang, Marcelo H. Ang

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments CVPRW 2021, EPIC-KITCHENS-100 Competition Report

2106.03772 2021-06-08 cs.CV 57%

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking

Yiding Yang, Zhou Ren, Haoxiang Li, Chunluan Zhou, Xinchao Wang, Gang Hua

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments Accepted by CVPR 2021

2106.00451 2021-06-02 cs.CV cs.AI cs.CL 57%

Highlight Timestamp Detection Model for Comedy Videos via Multimodal Sentiment Analysis

Fan Huang

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2105.04489 2021-05-11 cs.CV cs.CL cs.LG cs.SD eess.AS 57%

Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions

Mathew Monfort, SouYoung Jin, Alexander Liu, David Harwath, Rogerio Feris, James Glass, Aude Oliva

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments To appear at CVPR 2021

2104.13400 2021-04-29 cs.CV cs.LG 57%

FrameExit: Conditional Early Exiting for Efficient Video Recognition

Amir Ghodrati, Babak Ehteshami Bejnordi, Amirhossein Habibian

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments CVPR 2021 | Oral paper

2104.10492 2021-04-22 cs.CV 57%

Skimming and Scanning for Untrimmed Video Action Recognition

Yunyan Hong, Ailing Zeng, Min Li, Cewu Lu, Li Jiang, Qiang Xu

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2104.05970 2021-04-14 cs.CV 57%

Crossover Learning for Fast Online Video Instance Segmentation

Shusheng Yang, Yuxin Fang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu

专题命中视频理解：video understanding(abstract)；分类 cs.CV

1907.11272 2021-03-16 cs.CV 57%

A Novel Approach for Robust Multi Human Action Recognition and Summarization based on 3D Convolutional Neural Networks

Noor Almaadeed, Omar Elharrouss, Somaya Al-Maadeed, Ahmed Bouridane, Azeddine Beghdadi

专题命中视频理解：long video(abstract)；分类 cs.CV

2011.09280 2021-01-18 cs.CV cs.LG 57%

Continuous Emotion Recognition with Spatiotemporal Convolutional Neural Networks

Thomas Teixeira, Eric Granger, Alessandro Lameiras Koerich

专题命中视频理解：long video(abstract)；分类 cs.CV

Comments 33 pages

2101.05061 2021-01-14 cs.CV cs.RO 57%

Understanding Action Sequences based on Video Captioning for Learning-from-Observation

Iori Yanokura, Naoki Wake, Kazuhiro Sasabuchi, Katsushi Ikeuchi, Masayuki Inaba

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2011.13046 2020-11-30 cs.CV 57%

Can Temporal Information Help with Contrastive Self-Supervised Learning?

Yutong Bai, Haoqi Fan, Ishan Misra, Ganesh Venkatesh, Yongyi Lu, Yuyin Zhou, Qihang Yu, Vikas Chandra, Alan Yuille

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2011.09046 2020-11-25 cs.CV cs.CL 57%

A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus

Bowen Zhang, Hexiang Hu, Joonseok Lee, Ming Zhao, Sheide Chammas, Vihan Jain, Eugene Ie, Fei Sha

专题命中视频理解：long video(abstract)；分类 cs.CV

2010.14810 2020-10-29 cs.CV cs.LG 57%

Cycle-Contrast for Self-Supervised Video Representation Learning

Quan Kong, Wenpeng Wei, Ziwei Deng, Tomoaki Yoshinaga, Tomokazu Murakami

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments 12 pages

2004.14338 2020-10-19 cs.CL cs.CV 57%

Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube

Jack Hessel, Zhenhai Zhu, Bo Pang, Radu Soricut

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments 11 pages including supplementary materials

Journal ref Published in EMNLP 2020

2010.03019 2020-10-15 cs.CV cs.LG 57%

Global Self-Attention Networks for Image Recognition

Zhuoran Shen, Irwan Bello, Raviteja Vemulapalli, Xuhui Jia, Ching-Hui Chen

专题命中视频理解：video understanding(abstract)；分类 cs.CV

1912.06430 2020-08-25 cs.CV 57%

End-to-End Learning of Visual Representations from Uncurated Instructional Videos

Antoine Miech, Jean-Baptiste Alayrac, Lucas Smaira, Ivan Laptev, Josef Sivic, Andrew Zisserman

专题命中视频理解：text-to-video(abstract)；分类 cs.CV

Comments CVPR'2020 Oral

2008.01057 2020-08-04 cs.CV 57%

Residual Frames with Efficient Pseudo-3D CNN for Human Action Recognition

Jiawei Chen, Jenson Hsiao, Chiu Man Ho

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2008.00936 2020-08-04 cs.CV 57%

Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detection

Duygu Sarikaya, Jason J. Corso, Khurshid A. Guru

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Journal ref IEEE Transactions on Medical Imaging 36 (2017) 1542-1549

1912.00998 2020-06-11 cs.CV 57%

A Multigrid Method for Efficiently Training Video Models

Chao-Yuan Wu, Ross Girshick, Kaiming He, Christoph Feichtenhofer, Philipp Krähenbühl

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments CVPR 2020

1905.13209 2020-05-28 cs.CV cs.LG cs.NE 57%

AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures

Michael S. Ryoo, AJ Piergiovanni, Mingxing Tan, Anelia Angelova

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Journal ref ICLR 2020

1901.09260 2020-05-22 cs.CV cs.RO 57%

4D Generic Video Object Proposals

Aljosa Osep, Paul Voigtlaender, Mark Weber, Jonathon Luiten, Bastian Leibe

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments ICRA 2020

1911.08206 2020-04-23 cs.CV 57%

Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain

Barak Battash, Haim Barad, Hanlin Tang, Amit Bleiweiss

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments CVPR 2020: Joint Workshop on Efficient Deep Learning in Computer Vision

2003.09087 2020-03-23 cs.CV 57%

Fully Automated Hand Hygiene Monitoring\\in Operating Room using 3D Convolutional Neural Network

Minjee Kim, Joonmyeong Choi, Namkug Kim

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2003.05614 2020-03-13 cs.CV 57%

Beyond the Camera: Neural Networks in World Coordinates

Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid, Karteek Alahari

专题命中视频理解：video understanding(abstract)；分类 cs.CV

1910.01442 2020-03-10 cs.CV cs.AI cs.CL cs.LG 57%

CLEVRER: CoLlision Events for Video REpresentation and Reasoning

Kexin Yi, Chuang Gan, Yunzhu Li, Pushmeet Kohli, Jiajun Wu, Antonio Torralba, Joshua B. Tenenbaum

专题命中视频理解：video reasoning(abstract)；分类 cs.CV

Comments The first two authors contributed equally to this work. Accepted as Oral Spotlight as ICLR 2020. Project page: http://clevrer.csail.mit.edu/

2002.03152 2020-02-11 cs.CV 57%

CTM: Collaborative Temporal Modeling for Action Recognition

Qian Liu, Tao Wang, Jie Liu, Yang Guan, Qi Bu, Longfei Yang

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2001.06680 2020-01-22 cs.CV 57%

Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video

Jie Wu, Guanbin Li, Si Liu, Liang Lin

专题命中视频理解：video understanding(abstract)；分类 cs.CV

Comments To appear in AAAI2020

1911.11961 2019-11-28 cs.CV 57%

AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization

Xiao-Yu Zhang, Changsheng Li, Haichao Shi, Xiaobin Zhu, Peng Li, Jing Dong

专题命中视频理解：video understanding(abstract)；分类 cs.CV

1911.08548 2019-11-21 cs.CV 57%

Cross-Class Relevance Learning for Temporal Concept Localization

Junwei Ma, Satya Krishna Gorti, Maksims Volkovs, Ilya Stanevich, Guangwei Yu

专题命中视频理解：video understanding(abstract)；分类 cs.CV

1. 视频理解 1375 篇

Technical Report: Temporal Aggregate Representations

Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking

Highlight Timestamp Detection Model for Comedy Videos via Multimodal Sentiment Analysis

Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions

FrameExit: Conditional Early Exiting for Efficient Video Recognition

Skimming and Scanning for Untrimmed Video Action Recognition

Crossover Learning for Fast Online Video Instance Segmentation

A Novel Approach for Robust Multi Human Action Recognition and Summarization based on 3D Convolutional Neural Networks

Continuous Emotion Recognition with Spatiotemporal Convolutional Neural Networks

Understanding Action Sequences based on Video Captioning for Learning-from-Observation

Can Temporal Information Help with Contrastive Self-Supervised Learning?

A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus

Cycle-Contrast for Self-Supervised Video Representation Learning

Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube

Global Self-Attention Networks for Image Recognition

End-to-End Learning of Visual Representations from Uncurated Instructional Videos

Residual Frames with Efficient Pseudo-3D CNN for Human Action Recognition

Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detection

A Multigrid Method for Efficiently Training Video Models

AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures

4D Generic Video Object Proposals

Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain

Fully Automated Hand Hygiene Monitoring\\in Operating Room using 3D Convolutional Neural Network

Beyond the Camera: Neural Networks in World Coordinates

CLEVRER: CoLlision Events for Video REpresentation and Reasoning

CTM: Collaborative Temporal Modeling for Action Recognition

Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video

AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization

Cross-Class Relevance Learning for Temporal Concept Localization