paper-with-me

홈 › Papers

Temporal Bilinear Networks for Video Action Recognition

2018-11-25 · Yanghao Li, Sijie Song, Yuqi Li, Jiaying Liu

Temporal modeling in videos is a fundamental yet challenging problem in computer vision. In this paper, we propose a novel Temporal Bilinear (TB) model to capture the temporal pairwise feature interactions between adjacent frames. Compared with some existing temporal methods which are limited in linear transformations, our TB model considers explicit quadratic bilinear transformations in the temporal domain for motion evolution and sequential relation modeling. We further leverage the factorized bilinear model in linear complexity and a bottleneck network design to build our TB blocks, which also constrains the parameters and computation cost. We consider two schemes in terms of the incorporation of TB blocks and the original 2D spatial convolutions, namely wide and deep Temporal Bilinear Networks (TBN). Finally, we perform experiments on several widely adopted datasets including Kinetics, UCF101 and HMDB51. The effectiveness of our TBNs is validated by comprehensive ablation analyses and comparisons with various state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:1811.09974

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionTemporal Action Localization

Similar Papers 제목 키워드 기반

Spatiotemporal Pyramid Network for Video Action Recognition

2019-03-04 · CVPR 2017 7 · Yunbo Wang, Mingsheng Long, Jian-Min Wang, Philip S. Yu

Two-stream convolutional networks have shown strong performance in video action recognition tasks. The key idea is to learn spatiotemporal features by fusing convolutional networks spatially and temporally. However, it r…

Action RecognitionTemporal Action Localization

Approximated Bilinear Modules for Temporal Modeling

2020-07-25 · ICCV 2019 10 · Xinqi Zhu, Chang Xu, Langwen Hui, Cewu Lu 외

We consider two less-emphasized temporal properties of video: 1. Temporal cues are fine-grained; 2. Temporal modeling needs reasoning. To tackle both problems at once, we exploit approximated bilinear modules (ABMs) for …

Action RecognitionVideo Classification

Deep Bilinear Learning for RGB-D Action Recognition

2018-09-01 · ECCV 2018 9 · Jian-Fang Hu, Wei-Shi Zheng, Jia-Hui Pan, Jian-Huang Lai 외

In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition. In order to learn time-varying information and multi-modal features jointly, we propose a novel deep bilinear learni…

Action RecognitionTemporal Action Localization

Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition

2017-04-24 · Congqi Cao, Yifan Zhang, Chunjie Zhang, Hanqing Lu

Three dimensional convolutional neural networks (3D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which is suitable to be applied to video-base…

Action RecognitionTemporal Action Localization

Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition

2020-05-06 · Yuecong Xu, Jianfei Yang, Kezhi Mao, Jianxiong Yin 외

Temporal feature extraction is an important issue in video-based action recognition. Optical flow is a popular method to extract temporal feature, which produces excellent performance thanks to its capacity of capturing …

Action RecognitionOptical Flow Estimation