Research map / Detection and segmentation / Weakly supervised detection and segmentation
Cascaded Interactional Targeting Network for Egocentric Video Analysis
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 EM-like training to augment pixel-level hand segmentation training with hand bounding-box data | Hand segmentation on GTEA · GTEA | F-score: 0.883 -> 0.912; 0.933 -> 0.954; 0.943 -> 0.962 | Helped |
| Combine passive and active object features with global and local motion pooling | ADL action recognition · ADL | mAP (%): 43.8 -> 55.2; 42.5 -> 55.2 | Helped |
| Add active object histogram to passive object histogram (ablation) | Object-centric action representation · ADL | mAP (%): 35.2 -> 43.8 | Helped |
| Add local motion pooling on active foreground regions (ablation) | Motion action representation · ADL | mAP (%): 36.7 -> 42.5 | Helped |
| Use pixel-level hand maps instead of hand bounding boxes (ablation) | ADL action recognition · ADL | mAP (%): 48.1 -> 55.2; 38.5 -> 43.8; 39.8 -> 42.5 | Helped |
| Use proposed hand segmentation instead of Superpixel + CRF (ablation) | ADL action recognition · ADL | mAP (%): 49.8 -> 55.2; 39.3 -> 43.8; 40.1 -> 42.5 | Helped |
| Use proposed hand segmentation instead of Global scene (ablation) | ADL action recognition · ADL | mAP (%): 44.3 -> 55.2; 33.7 -> 43.8; 38.2 -> 42.5 | Helped |
Closest papers by meaning
- Analysis of Hand Segmentation in the Wild (CVPR 2018 · similarity 0.89)
- Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning (ICLR 2025 · similarity 0.88)
- Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics (AAAI 2025 · similarity 0.85)
- How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions (CVPR 2025 · similarity 0.84)
- Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions? (ICLR 2025 · similarity 0.84)
- Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data (NeurIPS 2024 · similarity 0.84)
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.