3D Deformable Convolution Temporal Reasoning network for action recognition |
| |
Affiliation: | School of Information Science and Technology, North China University of Technology, Beijing 100144, China |
| |
Abstract: | Modeling and reasoning of the interactions between multiple entities (actors and objects) are beneficial for the action recognition task. In this paper, we propose a 3D Deformable Convolution Temporal Reasoning (DCTR) network to model and reason about the latent relationship dependencies between different entities in videos. The proposed DCTR network consists of a spatial modeling module and a temporal reasoning module. The spatial modeling module uses 3D deformable convolution to capture relationship dependencies between different entities in the same frame, while the temporal reasoning module uses Conv-LSTM to reason about the changes of multiple entity relationship dependencies in the temporal dimension. Experiments on the Moments-in-Time dataset, UCF101 dataset and HMDB51 dataset demonstrate that the proposed method outperforms several state-of-the-art methods. |
| |
Keywords: | Action recognition 3D deformable convolutional network Reasoning |
本文献已被 ScienceDirect 等数据库收录! |
|