paper-with-me

Papers

Compressed Video Action Recognition

2017-12-02 · CVPR 2018 6 · Chao-yuan Wu, Manzil Zaheer, Hexiang Hu, R. Manmatha, Alexander J. Smola, Philipp Krähenbühl

Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and interesting signal is often drowned in too much irrelevant data. Motivated by that the superfluous information can be reduced by up to two orders of magnitude by video compression (using H.264, HEVC, etc.), we propose to train a deep network directly on the compressed video. This representation has a higher information density, and we found the training to be easier. In addition, the signals in a compressed video provide free, albeit noisy, motion information. We propose novel techniques to use them effectively. Our approach is about 4.6 times faster than Res3D and 2.7 times faster than ResNet-152. On the task of action recognition, our approach outperforms all the other methods on the UCF-101, HMDB-51, and Charades dataset.

📄 PDF Abstract BibTeX arXiv:1712.00636

Code (1)

chaoyuaw/pytorch-coviar pytorch

Tasks

Action ClassificationAction RecognitionTemporal Action LocalizationVideo Compression

Similar Papers 제목 키워드 기반

Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain

2020-12-26 · Samuel Felipe dos Santos, Jurandy Almeida

Human action recognition has become one of the most active field of research in computer vision due to its wide range of applications, like surveillance, medical, industrial environments, smart homes, among others. Recen…

Action RecognitionTemporal Action Localization

Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition

2019-12-10 · Shiyuan Huang, Xudong Lin, Svebor Karaman, Shih-Fu Chang

Two-stream networks have achieved great success in video recognition. A two-stream network combines a spatial stream of RGB frames and a temporal stream of Optical Flow to make predictions. However, the temporal redundan…

Action RecognitionOptical Flow EstimationTemporal Action LocalizationVideo Recognition+1

Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain

2022-09-29 · Ali Abdari, Pouria Amirjan, Azadeh Mansouri

With the widespread use of installed cameras, video-based monitoring approaches have seized considerable attention for different purposes like assisted living. Temporal redundancy and the sheer size of raw videos are the…

Action RecognitionVideo Understanding

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

2019-11-19 · Barak Battash, Haim Barad, Hanlin Tang, Amit Bleiweiss

Video understanding usually requires expensive computation that prohibits its deployment, yet videos contain significant spatiotemporal redundancy that can be exploited. In particular, operating directly on the motion ve…

Action RecognitionVideo RecognitionVideo Understanding

MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition

2021-08-20 · Jiawei Chen, Chiu Man Ho

This paper presents a pure transformer-based approach, dubbed the Multi-Modal Video Transformer (MM-ViT), for video action recognition. Different from other schemes which solely utilize the decoded RGB frames, MM-ViT ope…

Action RecognitionOptical Flow EstimationTemporal Action Localization