Papers › D²ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action...

D²ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition

3 Dec 2023arXiv:2312.01431archive 2025-07-28

Wenjie Pei, Qizhong Tan, Guangming Lu, Jiandong Tian

Adapting large pre-trained image models to few-shot action recognition has proven to be an effective and efficient strategy for learning robust feature extractors, which is essential for few-shot learning. Typical fine-tuning based adaptation paradigm is prone to overfitting in the few-shot learning scenarios and offers little modeling flexibility for learning temporal features in video data. In this work we present the Disentangled-and-Deformable Spatio-Temporal Adapter (D²ST-Adapter), which is a novel adapter tuning framework well-suited for few-shot action recognition due to lightweight design and low parameter-learning overhead. It is designed in a dual-pathway architecture to encode spatial and temporal features in a disentangled manner. In particular, we devise the anisotropic Deformable Spatio-Temporal Attention module as the core component of D²ST-Adapter, which can be tailored with anisotropic sampling densities along spatial and temporal domains to learn spatial and temporal features specifically in corresponding pathways, allowing our D²ST-Adapter to encode features in a global view in 3D spatio-temporal space while maintaining a lightweight design. Extensive experiments with instantiations of our method on both pre-trained ResNet and ViT demonstrate the superiority of our method over state-of-the-art methods for few-shot action recognition. Our method is particularly well-suited to challenging scenarios where temporal dynamics are critical for action recognition.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

qizhongtan/d2st-adapter officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionFew Shot Action RecognitionFew-Shot LearningFew-Shot action recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAdapterAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections