Research map / Detection and segmentation / CNN features
QPIC: Query-Based Pairwise Human-Object Interaction Detection With Image-Wide Contextual Information
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use QPIC with ResNet-101 instead of DRG | HICO-DET default full · HICO-DET default full | mAP: 5.37 mAP | Helped |
| use QPIC with ResNet-50 instead of FCMNet | V-COCO scenario 1 · V-COCO scenario 1 | mAP: 5.7 mAP | Helped |
| replace simple heads with point-matching heads (ablation) | QPIC on HICO-DET · HICO-DET | mAP: 29.07 -> 29.04 | No clear effect |
| replace pairwise heads with two-stage-like heads (ablation) | QPIC on HICO-DET · HICO-DET | mAP: 29.07 -> 26.18 | Hurt |
| replace PPDM point-matching heads with simple heads (ablation) | PPDM on HICO-DET · HICO-DET | mAP: 21.73 -> 17.45 | Hurt |
| add transformer encoder without decoder (ablation) | QPIC on HICO-DET · HICO-DET | mAP: 18.89 -> 20.07 | Helped |
| add transformer encoder with decoder present (ablation) | QPIC on HICO-DET · HICO-DET | mAP: 26.75 -> 29.27 | Helped |
| add transformer decoder without encoder (ablation) | QPIC on HICO-DET · HICO-DET | mAP: 18.89 -> 26.75; 7.86 mAP | Helped |
| add transformer decoder with encoder present (ablation) | QPIC on HICO-DET · HICO-DET | mAP: 20.07 -> 29.27; 9.20 mAP | Helped |
| add transformer decoder without encoder (ablation) | QPIC on COCO · COCO | mAP: 34.6 -> 38.7 | Helped |
| add transformer decoder with encoder present (ablation) | QPIC on COCO · COCO | mAP: 35.1 -> 43.5 | Helped |
Closest papers by meaning
- QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection (AAAI 2026 · similarity 0.92)
- Learning Human-Object Interaction Detection Using Interaction Points (CVPR 2020 · similarity 0.92)
- LINK: Learning Instance-level Knowledge from Vision-Language Models for Human-Object Interaction Detection (ICLR 2026 · similarity 0.92)
- Learning Human-Object Interaction as Groups (NeurIPS 2025 · similarity 0.90)
- Exploring Pose-Aware Human-Object Interaction via Hybrid Learning (CVPR 2024 · similarity 0.90)
- Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness (CVPR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.