Research map / Detection and segmentation / Open-set and few-shot detection
Progressively Parsing Interactional Objects for Fine Grained Action Detection
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 progressive LSTM object parsing instead of IAT tracking | Interactional object parsing · KSCGR | Err.: 12.3 -> 13.9 | Mixed |
| Use progressive LSTM object parsing instead of IAT tracking | Interactional object parsing · KSCGR | Prec.: 0.69 -> 0.66 | Mixed |
| Use object-centric motion feature pooling | Fine-grained action detection · KSCGR | Mean F-score: 0.76 -> 0.79 | Helped |
| Use the proposed parsing and action-detection framework instead of IAT-Action | Fine-grained action detection · KSCGR | Mean F-score: 0.79 -> 0.84 | Helped |
| Use the proposed parsing and action-detection framework instead of IAT-Action | Fine-grained action detection · MPII | AP: 54.3 -> 58.9 | Helped |
| Use the proposed parsing and action-detection framework instead of IAT-Action | Fine-grained action detection · MPII | Prec.: 28.6 -> 34.8 | Helped |
| Use the proposed parsing and action-detection framework instead of IAT-Action | Fine-grained action detection · MPII | Recall: 48.2 -> 51.7 | Helped |
| Progressively refine detections over more LSTM iterations (ablation) | Interactional object parsing · KSCGR | Average parsing error | Helped |
| Use LSTM across consecutive frames rather than on individual frames (ablation) | Interactional object parsing · KSCGR | Parsing performance | Helped |
| Use R-CNN or fast R-CNN instead of progressive parsing | Interactional object parsing · KSCGR | Parsing performance | Hurt |
Closest papers by meaning
- Attend and Interact: Higher-Order Object Interactions for Video Understanding (CVPR 2018 · similarity 0.89)
- Storyboard-guided Alignment for Fine-grained Video Action Recognition (NeurIPS 2025 · similarity 0.86)
- SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization (AAAI 2025 · similarity 0.85)
- ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition (NeurIPS 2024 · similarity 0.85)
- Dual DETRs for Multi-Label Temporal Action Detection (CVPR 2024 · similarity 0.85)
- FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment (CVPR 2024 · similarity 0.85)
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.