Multi-Modal Three-Stream Network for Action Recognition
This work addresses the challenge of high variation and complexity in video data for action recognition, though it is incremental by building on existing two-stream networks.
The paper tackled human action recognition in video by proposing a multi-modal framework that fuses pose features with existing two-stream networks, achieving state-of-the-art performance on datasets like JHMDB, sub-JHMDB, and Penn Action.
Human action recognition in video is an active yet challenging research topic due to high variation and complexity of data. In this paper, a novel video based action recognition framework utilizing complementary cues is proposed to handle this complex problem. Inspired by the successful two stream networks for action classification, additional pose features are studied and fused to enhance understanding of human action in a more abstract and semantic way. Towards practices, not only ground truth poses but also noisy estimated poses are incorporated in the framework with our proposed pre-processing module. The whole framework and each cue are evaluated on varied benchmarking datasets as JHMDB, sub-JHMDB and Penn Action. Our results outperform state-of-the-art performance on these datasets and show the strength of complementary cues.