Research map / Detection and segmentation / Open-set and few-shot detection
Interaction-aware Representation Modeling With Co-Occurrence Consistency for Egocentric Hand-Object Parsing
YUEJIAO SU, Yi Wang, Lei Yao, Yawen Cui, Lap-Pui Chau
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add CoCo loss (hand-first pixel-count co-occurrence constraint) (ablation) | InterFormer · EgoHOS in-domain test | interaction illusion rate (%): 2.19% -> 1.55% | Improved |
| add interaction prior predictor (IPP) branch (ablation) | InterFormer · EgoHOS in-domain test | mIoU | Improved |
| add DQG and DFS on top of the IPP branch (ablation) | InterFormer · EgoHOS in-domain test | mIoU | Improved |
| set CoCo pixel threshold tau to 100 versus other values from 50 to 300 (ablation) | CoCo loss · EgoHOS in-domain test | mIoU | Mixed |
| set dice and ce loss weights to 5 instead of 1 (ablation) | InterFormer · EgoHOS in-domain test | mIoU: 71.74 -> 73.22 | Improved |
| raise lambda_b and lambda_co to 5 (ablation) | InterFormer · EgoHOS in-domain test | mIoU: 71.74 -> 71.08 | Hurt |
| raise lambda_cls to 5 (ablation) | InterFormer · EgoHOS in-domain test | mIoU: 71.74 -> 71.30 | Hurt |
| raise lambda_co to 5 alone (ablation) | InterFormer · EgoHOS in-domain test | mIoU: 71.74 -> 71.88 | No clear effect |
| use InterFormer instead of the MLLM-based ANNEXE | EgoHOS parsing · EgoHOS in-domain test | FLOPs / mIoU: 610.500G -> 122.996G FLOPs; 71.38 -> 73.22 mIoU | Improved |
| use InterFormer instead of CaRe-Ego on mini-HOI4D left hand | EgoHOS parsing · mini-HOI4D (OOD) | left hand IoU: 70.39 -> 66.44 | Hurt |
Closest papers by meaning
- EgoMAN: Interaction-Structured Reasoning for Egocentric 3D Hand Trajectory Prediction (ECCV 2026 · similarity 0.90)
- Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning (ICLR 2025 · similarity 0.89)
- Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions? (ICLR 2025 · similarity 0.89)
- MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation (NeurIPS 2025 · similarity 0.88)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.88)
- How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions (CVPR 2025 · similarity 0.88)
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.
