Research map / Video / Action recognition
D2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
Wenjie Pei, Qizhong Tan, Guangming Lu, Jiandong Tian, Jun Yu
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 3D-conv spatio-temporal adapter instead of vanilla adapter (ablation) | ResNet-50 few-shot · SSv2-Full 1-shot | accuracy (%): 45.3 -> 52.2 | Improved |
| disentangle spatial and temporal pathways (DST-Adapter) rather than joint ST-Adapter (ablation) | ResNet-50 few-shot · SSv2-Full 1-shot | accuracy (%): 52.2 -> 53.7 | Improved |
| replace 3D convolution with anisotropic deformable attention (aDSTA) (ablation) | DST-Adapter · SSv2-Full 1-shot | accuracy (%): 53.7 -> 57.0 | Improved |
| replace 3D convolution with aDSTA (ablation) | DST-Adapter · Kinetics 1-shot | accuracy (%): 74.4 -> 75.8 | Improved |
| use both spatial and temporal aDSTA branches rather than spatial only (ablation) | D2ST-Adapter · SSv2-Full 1-shot | accuracy (%): 55.2 -> 57.0 | Improved |
| use anisotropic sampling densities rather than uniform (ablation) | D2ST-Adapter · SSv2-Full 1-shot | accuracy (%): 55.8 -> 57.0 | Improved |
| insert adapters in all 12 stages rather than only the last 6 (ablation) | D2ST-Adapter CLIP-ViT-B · SSv2-Small 1-shot | accuracy (%): 54.2 -> 55.0 | Improved |
| insert adapters in last 6 stages instead of first 6 (ablation) | D2ST-Adapter CLIP-ViT-B · SSv2-Small 1-shot | accuracy (%): 48.4 -> 54.2 | Improved |
| increase bottleneck ratio from 0.0625 to 0.25 (ablation) | D2ST-Adapter CLIP-ViT-B · SSv2-Small 1-shot | accuracy (%): 53.4 -> 55.0 | Improved |
| increase bottleneck ratio from 0.25 to 0.5 (ablation) | D2ST-Adapter CLIP-ViT-B · SSv2-Small 1-shot | accuracy (%): 55.0 -> 54.7 | No clear effect |
| increase sampling density from <1,4,4>&<4,2,2> to <2,4,4>&<8,2,2> (ablation) | D2ST-Adapter CLIP-ViT-B · SSv2-Full 1-shot | accuracy (%): 65.9 -> 66.7 | Improved |
| increase input frames from 4 to 16 (ablation) | D2ST-Adapter CLIP-ViT-B · SSv2-Full 1-shot | accuracy (%): 63.6 -> 69.9 | Improved |
Later papers that compared with this method
2 later accepted papers report D2ST-Adapter as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Task-Specific Distance Correlation Matching for Few-Shot Action Recognition (AAAI 2026 · better on 10 of 10 shared results)
- Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding (CVPR 2026 · better on 4 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ST-Adapter — ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning (NeurIPS 2022) · better on 4 of 4 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
- AIM: Adapting Image Models for Efficient Video Action Recognition (ICLR 2023 · similarity 0.90)
- ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning (NeurIPS 2022 · similarity 0.89)
- Not All Layers Are Equal in Image-to-Video Transfer (NeurIPS 2026 · similarity 0.89)
- Exploring Multimodal Adapters with Multi-Task Decoders for Video Action Recognition (TPAMI 2026 · similarity 0.88)
- ZeroI2V: Zero-Cost Adaptation of Pre-Trained Transformers from Image to Video (ECCV 2024 · similarity 0.88)
- Efficient Transfer Learning for Video-language Foundation Models (CVPR 2025 · 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.
