Holistic Interaction Transformer Network for Action Detection
This work addresses action detection for computer vision applications, offering a novel method that improves accuracy on specific benchmarks, though it is incremental in its approach.
The paper tackles action detection by proposing a multi-modal Holistic Interaction Transformer Network (HIT) that integrates hand and pose information with RGB data, achieving significant performance improvements on datasets like J-HMDB, UCF101-24, and MultiSports.
Actions are about how we interact with the environment, including other people, objects, and ourselves. In this paper, we propose a novel multi-modal Holistic Interaction Transformer Network (HIT) that leverages the largely ignored, but critical hand and pose information essential to most human actions. The proposed "HIT" network is a comprehensive bi-modal framework that comprises an RGB stream and a pose stream. Each of them separately models person, object, and hand interactions. Within each sub-network, an Intra-Modality Aggregation module (IMA) is introduced that selectively merges individual interaction units. The resulting features from each modality are then glued using an Attentive Fusion Mechanism (AFM). Finally, we extract cues from the temporal context to better classify the occurring actions using cached memory. Our method significantly outperforms previous approaches on the J-HMDB, UCF101-24, and MultiSports datasets. We also achieve competitive results on AVA. The code will be available at https://github.com/joslefaure/HIT.