Parallel Reasoning Network for Human-Object Interaction Detection
This work addresses a specific bottleneck in HOI detection for computer vision applications, representing an incremental improvement over existing methods.
The paper tackled the problem of Human-Object Interaction (HOI) detection by addressing the limitation of using a single shared predictor, which fails to differentiate between instance-level and relation-level predictions. The proposed Parallel Reasoning Network (PR-Net) achieved competitive results on HICO-DET and V-COCO benchmarks.
Human-Object Interaction (HOI) detection aims to learn how human interacts with surrounding objects. Previous HOI detection frameworks simultaneously detect human, objects and their corresponding interactions by using a predictor. Using only one shared predictor cannot differentiate the attentive field of instance-level prediction and relation-level prediction. To solve this problem, we propose a new transformer-based method named Parallel Reasoning Network(PR-Net), which constructs two independent predictors for instance-level localization and relation-level understanding. The former predictor concentrates on instance-level localization by perceiving instances' extremity regions. The latter broadens the scope of relation region to reach a better relation-level semantic understanding. Extensive experiments and analysis on HICO-DET benchmark exhibit that our PR-Net effectively alleviated this problem. Our PR-Net has achieved competitive results on HICO-DET and V-COCO benchmarks.