Research map / Video / Video-language understanding
MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
Jingchen Ni, Cangjin Yu, Zytang Jiang, Quan Zhang, Keyu Lv, Shannan Yan, Linyue Pan, Ke Zhang, Chun Yuan
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 bidirectional RWKV (ablation) | unidirectional RWKV-7 baseline · Lav-DF | mAP: 82.43 -> 85.99 | Improved |
| add bidirectional RWKV (ablation) | unidirectional RWKV-7 baseline · TVIL | mAP: 83.32 -> 83.08 | Mixed |
| add MG-MoE (ablation) | BiDir model · Lav-DF | mAP: 85.99 -> 86.94 | Improved |
| add MG-MoE (ablation) | BiDir model · TVIL | mAP: 83.08 -> 84.35 | Improved |
| add CGC (ablation) | BiDir+MG-MoE model · TVIL | mAP: 84.35 -> 85.91 | Improved |
| add CGC (ablation) | BiDir+MG-MoE model · Lav-DF | mAP: 86.94 -> 87.29 | Improved |
| add base CGC consistency loss (ablation) | BiDir+MG-MoE model · TVIL | mAP: 84.35 -> 84.77 | Improved |
| add boundary-aware weighting to CGC (ablation) | CGC loss · TVIL | mAP: 84.77 -> 85.04 | Improved |
| add progressive warmup schedule to CGC (ablation) | CGC loss · TVIL | mAP: 85.04 -> 85.91 | Improved |
| use scales [1,2,4] instead of single scale [1] (ablation) | MG-MoE · TVIL | mAP: 83.65 -> 85.91 | Improved |
| add scale 8 to [1,2,4] (ablation) | MG-MoE · TVIL | mAP: 85.91 -> 85.10 | Hurt |
| increase Top-K from 1 to 2 (ablation) | MG-MoE · TVIL | mAP: 84.43 -> 85.91 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ActionFormer — ActionFormer: Localizing Moments of Actions with Transformers (ECCV 2022) · better on 4 of 4 shared results
- TriDet — TriDet: Temporal Action Detection With Relative Boundary Modeling (CVPR 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.86)
- FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models (ICLR 2025 · similarity 0.86)
- SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints (AAAI 2025 · similarity 0.85)
- Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis (NeurIPS 2025 · similarity 0.85)
- Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization (AAAI 2025 · similarity 0.85)
- Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models (CVPR 2025 · 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.
