Extreme Low Resolution Activity Recognition with Confident Spatial-Temporal Attention Transfer
arXiv:1909.03580
Abstract
Activity recognition on extreme low-resolution videos, e.g., a resolution of 12*16 pixels, plays a vital role in far-view surveillance and privacy-preserving multimedia analysis. Low-resolution videos only contain limited information. Given the fact that one same activity may be represented by videos in both high resolution (HR) and extreme low resolution (eLR), it is worth studying to utilize the relevant HR data to improve the eLR activity recognition. In this work, we propose a novel Confident Spatial-Temporal Attention Transfer (CSTAT) for eLR activity recognition. CSTAT can acquire information from HR data by reducing the attention differences with a transfer-learning strategy. Besides, the credibility of the supervisory signal is also taken into consideration for a more confident transferring process. Experimental results on two well-known datasets, i.e., UCF101 and HMDB51, demonstrate that, the proposed method can effectively improve the accuracy of eLR activity recognition and achieve an accuracy of 59.23% on 12*16 videos in HMDB51, a state-of-the-art performance.
arXiv comment12 pages, 9 fugures. 2nd-round review of TIP
References in corpus (8)
- Distilling the Knowledge in a Neural Network
- Two-Stream Convolutional Networks for Action Recognition in Videos
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
- Do Deep Nets Really Need to be Deep?
- Deep Model Compression: Distilling Knowledge from Noisy Teachers
- Deep Ordinal Hashing with Spatial Attention
- Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning