Actor-agnostic Multi-label Action Recognition with Multi-modal Query
arXiv:2307.10763 · doi:10.1109/ICCVW60793.2023.00086
Abstract
Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estimation (e.g., humans vs. animals), leading to cumbersome model design complexity and high maintenance costs. Moreover, they often focus on learning the visual modality alone and single-label classification whilst neglecting other available information sources (e.g., class name text) and the concurrent occurrence of multiple actions. To overcome these limitations, we propose a new approach called 'actor-agnostic multi-modal multi-label action recognition,' which offers a unified solution for various types of actors, including humans and animals. We further formulate a novel Multi-modal Semantic Query Network (MSQNet) model in a transformer-based object detection framework (e.g., DETR), characterized by leveraging visual and textual modalities to represent the action classes better. The elimination of actor-specific model designs is a key advantage, as it removes the need for actor pose estimation altogether. Extensive experiments on five publicly available benchmarks show that our MSQNet consistently outperforms the prior arts of actor-specific alternatives on human and animal single- and multi-label action recognition tasks by up to 50%. Code is made available at https://github.com/mondalanindya/MSQNet.
Published at the 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Paris, France
References in corpus (5)
- The Kinetics Human Action Video Dataset
- ActionCLIP: A New Paradigm for Video Action Recognition
- Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
- A CLIP-Hitchhiker's Guide to Long Video Retrieval
- Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models