Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics
About
Human-Object Interaction (HOI) detection is an essential task to understand human-centric images from a fine-grained perspective. Although end-to-end HOI detection models thrive, their paradigm of parallel human/object detection and verb class prediction loses two-stage methods' merit: object-guided hierarchy. The object in one HOI triplet gives direct clues to the verb to be predicted. In this paper, we aim to boost end-to-end models with object-guided statistical priors. Specifically, We propose to utilize a Verb Semantic Model (VSM) and use semantic aggregation to profit from this object-guided hierarchy. Similarity KL (SKL) loss is proposed to optimize VSM to align with the HOI dataset's priors. To overcome the static semantic embedding problem, we propose to generate cross-modality-aware visual and semantic features by Cross-Modal Calibration (CMC). The above modules combined composes Object-guided Cross-modal Calibration Network (OCN). Experiments conducted on two popular HOI detection benchmarks demonstrate the significance of incorporating the statistical prior knowledge and produce state-of-the-art performances. More detailed analysis indicates proposed modules serve as a stronger verb predictor and a more superior method of utilizing prior knowledge. The codes are available at \url{https://github.com/JacobYuan7/OCN-HOI-Benchmark}.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Human-Object Interaction Detection | HICO-DET (test) | mAP (full)31.43 | 493 | |
| Human-Object Interaction Detection | V-COCO (test) | AP (Role, Scenario 1)65.3 | 270 | |
| Human-Object Interaction Detection | HICO-DET | mAP (Full)31.43 | 233 | |
| HOI Detection | V-COCO | AP Role 164.2 | 40 | |
| HOI Detection | HICO-DET | mAP (Rare)25.56 | 34 | |
| HOI Detection | V-COCO v1 (test) | AP Role (Scenario 1)64.2 | 25 | |
| HOI Detection | HICO-DET v1 (test) | mAP (Rare)25.56 | 24 | |
| Human-Object Interaction Detection | V-COCO standard (test) | AP (Role 1)64.2 | 18 |