Abstract | ||
---|---|---|
The approaches based on spatio-temporal features for video action recognition have emerged such as two-stream based methods and 3D convolution based methods. However, current methods suffer from the problems caused by partial observation, or restricted to single information modeling, and so on. Segment-level recognition results obtained from dense sampling can not represent the entire video and, therefore lead to partial observation. And a single model is hard to capture the complementary information on spacial, temporal and spatio-temporal information from video at the same time. Therefore, the challenge is to build the video-level representation and capture multiple information. In this paper, a video-level multi-model fusion action recognition method is proposed to solve these problems. Firstly, an efficient video-level 3D convolution model is proposed to get the global information in the video which assembling segment-level 3D convolution models. Secondly, a multi-model fusion architecture is proposed for video action recognition to capture multiple information. The spatial, temporal and spatio-temporal information are aggregate with SVM classifier. Experimental results show that this method achieves the state-of-the-art performance on the datasets of UCF-101(97.6%) without pre-training on Kinetics.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3357384.3357935 | Proceedings of the 28th ACM International Conference on Information and Knowledge Management |
Keywords | Field | DocType |
3d convolution, action recognition, multi-model fusion, video-leval recognition | Information retrieval,Computer science,Action recognition,Fusion,Artificial intelligence,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-4503-6976-3 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaomin Wang | 1 | 0 | 0.34 |
Junsan Zhang | 2 | 1 | 1.73 |
Leiquan Wang | 3 | 48 | 7.63 |
Philip S. Yu | 4 | 30670 | 3474.16 |
Jie Zhu | 5 | 0 | 0.34 |
Haisheng Li | 6 | 10 | 10.14 |