Actor-agnostic Multi-label Action Recognition with Multi-modal Query

20 Jul 2023  ·  Anindya Mondal, Sauradip Nag, Joaquin M Prada, Xiatian Zhu, Anjan Dutta ·

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 will be released at

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Recognition Animal Kingdom MSQNet mAP 73.1 # 1
Zero-Shot Action Recognition Charades MSQNet mAP 35.59 # 1
Action Recognition Charades MSQNet MAP 47.57 # 1
Zero-Shot Action Recognition HMDB51 MSQNet Accuracy 69.43 # 1
Action Recognition HMDB51 MSQNet Accuracy 93.25 # 1
Action Recognition Hockey MSQNet Accuracy 3.05 # 1
Action Recognition THUMOS14 MSQNet Accuracy 83.16 # 1
Zero-Shot Action Recognition THUMOS' 14 MSQNet Accuracy 75.33 # 1