PBADet: A One-Stage Anchor-Free Approach for Part-Body Association
This addresses the need for scalable and accurate part-body association in applications like human-machine interfaces, offering a more streamlined solution compared to traditional multi-stage methods.
The paper tackles the problem of detecting human parts and associating them with individuals by introducing PBADet, a one-stage anchor-free approach that uses a part-to-body center offset, achieving state-of-the-art performance with improved efficiency.
The detection of human parts (e.g., hands, face) and their correct association with individuals is an essential task, e.g., for ubiquitous human-machine interfaces and action recognition. Traditional methods often employ multi-stage processes, rely on cumbersome anchor-based systems, or do not scale well to larger part sets. This paper presents PBADet, a novel one-stage, anchor-free approach for part-body association detection. Building upon the anchor-free object representation across multi-scale feature maps, we introduce a singular part-to-body center offset that effectively encapsulates the relationship between parts and their parent bodies. Our design is inherently versatile and capable of managing multiple parts-to-body associations without compromising on detection accuracy or robustness. Comprehensive experiments on various datasets underscore the efficacy of our approach, which not only outperforms existing state-of-the-art techniques but also offers a more streamlined and efficient solution to the part-body association challenge.