Relational Context Learning for Human-Object Interaction Detection
This work addresses a bottleneck in HOI detection for computer vision applications, offering an incremental improvement over existing transformer-based methods.
The paper tackled the problem of insufficient context exchange in disentangled transformer architectures for human-object interaction (HOI) detection, proposing the multiplex relation network (MUREN) that uses unary, pairwise, and ternary relations to improve relational reasoning, achieving state-of-the-art performance on HICO-DET and V-COCO benchmarks.
Recent state-of-the-art methods for HOI detection typically build on transformer architectures with two decoder branches, one for human-object pair detection and the other for interaction classification. Such disentangled transformers, however, may suffer from insufficient context exchange between the branches and lead to a lack of context information for relational reasoning, which is critical in discovering HOI instances. In this work, we propose the multiplex relation network (MUREN) that performs rich context exchange between three decoder branches using unary, pairwise, and ternary relations of human, object, and interaction tokens. The proposed method learns comprehensive relational contexts for discovering HOI instances, achieving state-of-the-art performance on two standard benchmarks for HOI detection, HICO-DET and V-COCO.