Research map / Video / Action recognition
Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries
Hao Wang, Cheng Deng, Fan Ma, Yi Yang
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 |
|---|---|---|---|
| replace traditional dynamic convolution with groupwise kernel prediction and progressive interaction (ablation) | CMDyConv baseline · A2D Sentences | mAP 0.5:0.95: 28.5 -> 29.3 | Improved |
| add context modulation (stacked 3 times) (ablation) | CMDyConv baseline · A2D Sentences | mAP 0.5:0.95: 29.3 -> 30.2 | Improved |
| add deformable offsets to context modulated dynamic convolution (ablation) | CMDyConv · A2D Sentences | mAP 0.5:0.95: 30.2 -> 33.3 | Improved |
| add ConvLSTM temporal evolution encoder (ablation) | DCMDyConv · A2D Sentences | mAP 0.5:0.95: 33.3 -> 33.3 | No clear effect |
| add ConvLSTM temporal encoder (ablation) | DCMDyConv · A2D Sentences | P@0.9: 3.8 -> 4.5 | Improved |
| add ConvLSTM temporal encoder (ablation) | DCMDyConv · A2D Sentences | Overall IoU: 62.6 -> 62.3 | Hurt |
| progressive interaction instead of direct interaction (ablation) | CMDyConv · A2D Sentences | Mean IoU: 52.5 -> 53.1 | Mixed |
| CMDyConv full model vs Gavrilyuk et al. on A2D | CMDyConv · A2D Sentences | mAP 0.5:0.95: 26.9 -> 33.3 | Improved |
| transfer to J-HMDB without fine-tuning, P@0.9 | CMDyConv · J-HMDB Sentences | P@0.9: 0.0 -> 0.0 | No clear effect |
Closest papers by meaning
- Actor and Action Video Segmentation From a Sentence (CVPR 2018 · similarity 0.91)
- Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation (CVPR 2021 · similarity 0.91)
- Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query (ICCV 2019 · similarity 0.91)
- End-to-End Joint Semantic Segmentation of Actors and Actions in Video (ECCV 2018 · similarity 0.89)
- Visual-Textual Capsule Routing for Text-Based Video Segmentation (CVPR 2020 · similarity 0.88)
- FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation (CVPR 2024 · similarity 0.87)
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.
