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.

翻译：摘要：现有动作识别方法通常因演员内在的拓扑结构和外观差异而具有演员特异性。这需要针对不同演员（例如人类与动物）进行特定的姿态估计，导致模型设计复杂、维护成本高昂。此外，这些方法通常仅专注于学习视觉模态和单标签分类，忽略了其他可用信息源（如类别名称文本）以及多个动作的并发发生。为克服这些局限，我们提出一种名为“演员无关多模态多标签动作识别”的新方法，为包括人类和动物在内的各类演员提供统一解决方案。我们进一步在基于Transformer的目标检测框架（如DETR）中构建了一种新型多模态语义查询网络（MSQNet）模型，其特点在于利用视觉和文本模态更好地表示动作类别。消除演员特定模型设计是关键优势，因为它完全无需进行演员姿态估计。在五个公开基准数据集上的大量实验表明，我们的MSQNet在人类和动物的单标签及多标签动作识别任务上，始终比先前的演员特异性方法性能提升高达50%。代码已开源至 https://github.com/mondalanindya/MSQNet。