Adaptive Focus for Efficient Video Recognition

By Yulin Wang, Zhaoxi Chen, Haojun Jiang, Shiji Song, Yizeng Han, Gao Huang. 2021

118 citations recorded by the source corpus.

In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which shifts smoothly across frames. Therefore, we model the patch localization problem as a sequential decision task, and propose a reinforcement learning based approach for efficient spatially adaptive video recognition (AdaFocus). In specific, a light-weighted ConvNet is first adopted to quickly process the full video sequence, whose features are used by a recurrent policy network to localize the most task-relevant regions. Then the selected patches are inferred by a high-capacity network for the final prediction. During offline inference, once the informative patch sequence has been generated, the bulk of computation can be done in parallel, and is efficient on modern GPU devices. In addition, we demonstrate that the proposed method can be easily extended by further considering the temporal redundancy, e.g., dynamically skipping less valuable frames. Extensive experiments on five benchmark datasets, i.e., ActivityNet, FCVID, MiniKinetics, Something-Something V1&V2, demonstrate that our method is significantly more efficient than the competitive baselines. Code is available at https://github.com/blackfeather-wang/AdaFocus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Shiji Song
2. Yulin Wang
3. Gao Huang
4. Le Yang
5. Yizeng Han
6. Honghui Wang
7. Quoc V. Le
8. Alan L. Yuille

In Computer Vision and Pattern Recognition

1. Shiji Song
2. Yulin Wang
3. Gao Huang
4. Yizeng Han
5. Le Yang
6. Honghui Wang
7. Luc Van Gool
8. Alan L. Yuille

In Efficiency & Compression

1. Shiji Song
2. Gao Huang
3. Yulin Wang
4. Le Yang
5. Yizeng Han
6. Honghui Wang

Citations in the corpus

• Dynamic Neural Networks: A Survey (2021, background): “Adjusting multiple factors of deep models simultaneously has attracted researches in both static [193], [194] and dynamic networks [195], [196], [197], [198].”
• Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition (2021, unknown): “Besides, the spatial adaptive paradigm [15, 4, 47, 42, 46] has been proposed for efficient image and video recognition.”
• Not All Images are Worth 16x16 Words: Dynamic Vision Transformers with Adaptive Sequence Length (2021, unknown): “Besides, the spatial adaptive paradigm [14, 4, 44, 39, 43] has been proposed for efficient image and video recognition.”