Few Shot Action Recognition

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 31 papers with code (76 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Temporal-Relational CrossTransformers for Few-Shot Action Recognition
  15 Jan 2021 2 repositories listed Syntology ran 2 of 5 samples · 3 unverified · 1 pointer-only (licence)
  We propose a novel approach to few-shot action recognition, finding temporally-corresponding frame tuples between the query and videos in the support set.
• Temporal-Relational CrossTransformers for Few-Shot Action Recognition
  15 Jan 2021 2 repositories listed Syntology ran 2 of 5 samples · 3 unverified · 1 pointer-only (licence)
  We propose a novel approach to few-shot action recognition, finding temporally-corresponding frame tuples between the query and videos in the support set.
• Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
  15 Dec 2019 2 repositories listed
  Next, by decomposing and learning the temporal changes in visual relationships that result in an action, we demonstrate the utility of a hierarchical event decomposition by enabling few-shot action recognition,…
• Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
  15 Dec 2019 2 repositories listed
  Next, by decomposing and learning the temporal changes in visual relationships that result in an action, we demonstrate the utility of a hierarchical event decomposition by enabling few-shot action recognition,…
• Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition
  9 May 2025 1 repository listed
  Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image models, such as CLIP, in the domain of…
• Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition
  9 May 2025 1 repository listed
  Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image models, such as CLIP, in the domain of…
• Temporal Alignment-Free Video Matching for Few-shot Action Recognition
  8 Apr 2025 1 repository listed Syntology ran 4 of 8 samples · 4 unverified · 8 pointer-only (licence)
  Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances.
• Temporal Alignment-Free Video Matching for Few-shot Action Recognition
  8 Apr 2025 1 repository listed Syntology ran 4 of 8 samples · 4 unverified · 8 pointer-only (licence)
  Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances.
• TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
  28 Nov 2024 1 repository listed
  To effectively and efficiently explore the potential of pre-trained models in transferring to target domain, our TAMT proposes a Hierarchical Temporal Tuning Network (HTTN), whose core involves local temporal-aware…
• TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
  28 Nov 2024 1 repository listed
  To effectively and efficiently explore the potential of pre-trained models in transferring to target domain, our TAMT proposes a Hierarchical Temporal Tuning Network (HTTN), whose core involves local temporal-aware…
• SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition
  23 Jul 2024 1 repository listed
  High frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density.
• SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition
  23 Jul 2024 1 repository listed
  High frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density.
• Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)
  3 Jun 2024 1 repository listed
  Understanding Activities of Daily Living (ADLs) is a crucial step for different applications including assistive robots, smart homes, and healthcare.
• D²ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
  3 Dec 2023 1 repository listed
  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…
• D²ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
  3 Dec 2023 1 repository listed
  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…
• CDFSL-V: Cross-Domain Few-Shot Learning for Videos
  7 Sep 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  To address this issue, in this work, we propose a novel cross-domain few-shot video action recognition method that leverages self-supervised learning and curriculum learning to balance the information from the source…
• CDFSL-V: Cross-Domain Few-Shot Learning for Videos
  7 Sep 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  To address this issue, in this work, we propose a novel cross-domain few-shot video action recognition method that leverages self-supervised learning and curriculum learning to balance the information from the source…
• Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching
  18 Aug 2023 1 repository listed
  Class prototype construction and matching are core aspects of few-shot action recognition.
• Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching
  18 Aug 2023 1 repository listed
  Class prototype construction and matching are core aspects of few-shot action recognition.
• Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition
  5 Jul 2023 1 repository listed
  The second module (MLT) focuses on the Multiple-level feature of the support prototype and query sample to mine more information for the alignment, which operates on different level features.
• Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition
  5 Jul 2023 1 repository listed
  The second module (MLT) focuses on the Multiple-level feature of the support prototype and query sample to mine more information for the alignment, which operates on different level features.
• MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition
  3 Apr 2023 1 repository listed
  To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder.
• MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition
  3 Apr 2023 1 repository listed
  To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder.
• MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
  15 Mar 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  We adapt a VL model for zero-shot and few-shot action recognition using a collection of unlabeled videos and an unpaired action dictionary.
• MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
  15 Mar 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  We adapt a VL model for zero-shot and few-shot action recognition using a collection of unlabeled videos and an unpaired action dictionary.
• CLIP-guided Prototype Modulating for Few-shot Action Recognition
  6 Mar 2023 1 repository listed Syntology ran 5 of 5 samples · 0 unverified
  Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action…
• CLIP-guided Prototype Modulating for Few-shot Action Recognition
  6 Mar 2023 1 repository listed Syntology ran 5 of 5 samples · 0 unverified
  Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action…
• HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition
  9 Jan 2023 1 repository listed
  To be specific, HyRSM++ consists of two key components, a hybrid relation module and a temporal set matching metric.
• HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition
  9 Jan 2023 1 repository listed
  To be specific, HyRSM++ consists of two key components, a hybrid relation module and a temporal set matching metric.
• TempCLR: Temporal Alignment Representation with Contrastive Learning
  28 Dec 2022 1 repository listed Syntology ran 3 of 5 samples · 2 unverified
  For long videos, given a paragraph of description where the sentences describe different segments of the video, by matching all sentence-clip pairs, the paragraph and the full video are aligned implicitly.

Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.