Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition

• URL: http://arxiv.org/abs/2602.18043v1
• Date: Fri, 20 Feb 2026 07:52:57 GMT
• Title: Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition
• Authors: Hongyu Qu, Xiangbo Shu, Rui Yan, Hailiang Gao, Wenguan Wang, Jinhui Tang,
• Abstract summary: Few-Shot Action Recognition (FSAR) is a challenging task that requires recognizing novel action categories with a few labeled videos.<n>Recent works typically apply semantically coarse category names as auxiliary contexts to guide the learning of discriminative visual features.<n>We propose DiST, an innovative De-incorporation framework for FSAR that makes use of decoupled Spatial knowledge.
• Score: 92.22104713961431
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Few-Shot Action Recognition (FSAR) is a challenging task that requires recognizing novel action categories with a few labeled videos. Recent works typically apply semantically coarse category names as auxiliary contexts to guide the learning of discriminative visual features. However, such context provided by the action names is too limited to provide sufficient background knowledge for capturing novel spatial and temporal concepts in actions. In this paper, we propose DiST, an innovative Decomposition-incorporation framework for FSAR that makes use of decoupled Spatial and Temporal knowledge provided by large language models to learn expressive multi-granularity prototypes. In the decomposition stage, we decouple vanilla action names into diverse spatio-temporal attribute descriptions (action-related knowledge). Such commonsense knowledge complements semantic contexts from spatial and temporal perspectives. In the incorporation stage, we propose Spatial/Temporal Knowledge Compensators (SKC/TKC) to discover discriminative object-level and frame-level prototypes, respectively. In SKC, object-level prototypes adaptively aggregate important patch tokens under the guidance of spatial knowledge. Moreover, in TKC, frame-level prototypes utilize temporal attributes to assist in inter-frame temporal relation modeling. These learned prototypes thus provide transparency in capturing fine-grained spatial details and diverse temporal patterns. Experimental results show DiST achieves state-of-the-art results on five standard FSAR datasets.

Related papers

• StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning [79.44594332189018]
  Class-Incremental Learning (CIL) seeks to develop models that continuously learn new action categories over time without previously acquired knowledge.<n>Existing approaches either rely on forgetting, raising concerns over memory and privacy, or adapt static image-based methods that neglect temporal modeling.<n>We propose a unified and exemplar-free VCIL framework that explicitly disentangles and preserves information.
  arXiv  Detail & Related papers  (2025-05-20T06:46:51Z)
• InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models [24.170351966913557]
  We propose the InPK model, which infuses class-specific prior knowledge into the learnable tokens.<n>We also introduce a learnable text-to-vision projection layer to accommodate the text adjustments.<n>In experiments, InPK significantly outperforms state-of-the-art methods in multiple zero/few-shot image classification tasks.
  arXiv  Detail & Related papers  (2025-02-27T05:33:18Z)
• CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning [62.69917996026769]
  A class-incremental learning task requires learning and preserving both spatial appearance and temporal action involvement.<n>We propose a framework that equips separate adapters to learn new class patterns, accommodating the incremental information requirements unique to each class.<n>A causal compensation mechanism is proposed to reduce the conflicts during increment and memorization for between different types of information.
  arXiv  Detail & Related papers  (2025-01-13T11:34:55Z)
• Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning [23.671999163027284]
  This paper proposes a novel framework for multi-label image recognition without any training data. It uses knowledge of pre-trained Large Language Model to learn prompts to adapt pretrained Vision-Language Model like CLIP to multilabel classification. Our framework presents a new way to explore the synergies between multiple pre-trained models for novel category recognition.
  arXiv  Detail & Related papers  (2024-03-02T13:43:32Z)
• Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning [59.26623999209235]
  We present DiST, which disentangles the learning of spatial and temporal aspects of videos. The disentangled learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps.
  arXiv  Detail & Related papers  (2023-09-14T17:58:33Z)
• On the Importance of Spatial Relations for Few-shot Action Recognition [109.2312001355221]
  In this paper, we investigate the importance of spatial relations and propose a more accurate few-shot action recognition method. A novel Spatial Alignment Cross Transformer (SA-CT) learns to re-adjust the spatial relations and incorporates the temporal information. Experiments reveal that, even without using any temporal information, the performance of SA-CT is comparable to temporal based methods on 3/4 benchmarks.
  arXiv  Detail & Related papers  (2023-08-14T12:58:02Z)
• Spatio-temporal Relation Modeling for Few-shot Action Recognition [100.3999454780478]
  We propose a few-shot action recognition framework, STRM, which enhances class-specific featureriminability while simultaneously learning higher-order temporal representations. Our approach achieves an absolute gain of 3.5% in classification accuracy, as compared to the best existing method in the literature.
  arXiv  Detail & Related papers  (2021-12-09T18:59:14Z)
• Spatio-Temporal Analysis of Facial Actions using Lifecycle-Aware Capsule Networks [12.552355581481994]
  AULA-Caps learns between contiguous frames by focusing on relevant temporal-temporal segments in the sequence. The learnt feature capsules are routed together such that the model learns to selectively focus on spatial ortemporal information depending upon the AU lifecycle. The proposed model is evaluated on the commonly used BP4D and GFT benchmark datasets.
  arXiv  Detail & Related papers  (2020-11-17T18:36:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.