Browse State-of-the-Art › Few Shot Action Recognition
Few Shot Action Recognition
31 papers with code · 5 benchmarks · 6 datasets archive 2025-07-28
Few-shot (FS) action recognition is a challenging com- puter vision problem, where the task is to classify an unlabelled query video into one of the action categories in the support set having limited samples per action class.
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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Kinetics-100 (8 rows) | Name Tuning | Few-Shot Classification of Interactive Activities of Daily Living... | code | — | Compare |
| HMDB51 (7 rows) | STRM | Spatio-temporal Relation Modeling for Few-shot Action Recognition | code | — | Compare |
| UCF101 (7 rows) | STRM | Spatio-temporal Relation Modeling for Few-shot Action Recognition | code | — | Compare |
| Something-Something-100 (5 rows) | HyRSM | Hybrid Relation Guided Set Matching for Few-shot Action Recognition | code | — | Compare |
| MOMA-LRG (4 rows) | Name Tuning | Few-Shot Classification of Interactive Activities of Daily Living... | code | — | Compare |
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
Papers archive 2025-07-28
archive papers tagged: 76 · with a code link: 31 · where Syntology ran a sample: 10 (8 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (10 of 76 tagged: 8 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 76 of 76, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
15 Jan 2021 2 repositories listed Syntology official (archive's flag): 1 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 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.
-
15 Dec 2019 2 repositories listedNext, 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…
-
9 May 2025 1 repository listedLarge-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…
-
8 Apr 2025 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 8 harvested samples) · 8 pointer-only (licence)Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances.
-
28 Nov 2024 1 repository listedTo 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…
-
23 Jul 2024 1 repository listedHigh frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density.
-
3 Jun 2024 1 repository listedUnderstanding Activities of Daily Living (ADLs) is a crucial step for different applications including assistive robots, smart homes, and healthcare.
-
3 Dec 2023 1 repository listedIn 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…
-
7 Sep 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 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…
-
18 Aug 2023 1 repository listedClass prototype construction and matching are core aspects of few-shot action recognition.
-
5 Jul 2023 1 repository listedThe 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.
-
3 Apr 2023 1 repository listedTo 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.
-
15 Mar 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 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.
-
6 Mar 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 3 pointer-only (licence)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…
-
9 Jan 2023 1 repository listedTo be specific, HyRSM++ consists of two key components, a hybrid relation module and a temporal set matching metric.
-
28 Dec 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)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.
-
28 Nov 2022 1 repository listedVideo-language models (VLMs), large models pre-trained on numerous but noisy video-text pairs from the internet, have revolutionized activity recognition through their remarkable generalization and open-vocabulary…
-
30 Oct 2022 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 7 harvested samples) · 7 pointer-only (licence)Dynamic Time Warping (DTW) is used for matching pairs of sequences and celebrated in applications such as forecasting the evolution of time series, clustering time series or even matching sequence pairs in few-shot…
-
20 Jul 2022 1 repository listedIn this paper, we propose a novel video frame sampler for few-shot action recognition to address this issue, where task-specific spatial-temporal frame sampling is achieved via a temporal selector (TS) and a spatial…
-
28 Apr 2022 1 repository listedTo overcome the two limitations, we propose a novel Hybrid Relation guided Set Matching (HyRSM) approach that incorporates two key components: hybrid relation module and set matching metric.
-
15 Jan 2022 1 repository listedThe goal of multi-level feature design is to extract feature representations at different layer-wise levels of CNN, realizing several levels of visual abstraction to achieve robust few-shot learning.
-
9 Dec 2021 1 repository listedExperiments are performed on four few-shot action recognition benchmarks: Kinetics, SSv2, HMDB51 and UCF101.
-
2 Nov 2021 1 repository listedRecognizing human actions is fundamentally a spatio-temporal reasoning problem, and should be, at least to some extent, invariant to the appearance of the human and the objects involved.
-
13 Oct 2021 1 repository listed Syntology 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)In this work, we present Object-Region Video Transformers (ORViT), an object-centric approach that extends video transformer layers with a block that directly incorporates object representations.
-
29 Sep 2021 1 repository listedExplainable distances for sequence data depend on temporal alignment to tackle sequences with different lengths and local variances.
-
27 Jul 2021 1 repository listedWe benchmark several recent approaches on the proposed True Zero-Shot(TruZe) Split for UCF101 and HMDB51, with zero-shot and generalized zero-shot evaluation.
-
10 Jul 2021 1 repository listedThe first stage locates the action by learning a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature (e. g. background).
-
11 May 2021 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 16 harvested samples)However, there remains a lack of studies that extend action composition and leverage multiple viewpoints and multiple modalities of data for representation learning.
-
20 Jan 2021 1 repository listedExtensive experiments on four standard few-shot action benchmarks show that our method clearly outperforms previous state-of-the-art methods, with the improvement particularly significant (10+%) on the most challenging…
-
20 Oct 2020 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples)Humans can easily recognize actions with only a few examples given, while the existing video recognition models still heavily rely on the large-scale labeled data inputs.
-
12 Jan 2020 1 repository listed
-
Active Multimodal Distillation for Few-shot Action Recognition16 Jun 2025 0 repositories listed
-
Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition11 Mar 2025 0 repositories listed
-
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence10 Dec 2024 0 repositories listed
-
Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition18 Nov 2024 0 repositories listed
-
Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition22 Aug 2024 0 repositories listed
-
Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition1 Aug 2024 0 repositories listed
-
Trajectory-aligned Space-time Tokens for Few-shot Action Recognition25 Jul 2024 0 repositories listed
-
A Comprehensive Review of Few-shot Action Recognition20 Jul 2024 0 repositories listed
-
DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition8 Jul 2024 0 repositories listed
-
Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models3 Jun 2024 0 repositories listed
-
MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition3 May 2024 0 repositories listed
-
Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition18 Apr 2024 0 repositories listed
-
Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition20 Feb 2024 0 repositories listed
-
Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment7 Feb 2024 0 repositories listed
-
Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-M²DF)16 Jan 2024 0 repositories listed
-
Two-stream joint matching method based on contrastive learning for few-shot action recognition8 Jan 2024 0 repositories listed
-
Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CPM²C)2 Dec 2023 0 repositories listed
-
Semantic-aware Video Representation for Few-shot Action Recognition10 Nov 2023 0 repositories listed
-
Few-shot Action Recognition with Captioning Foundation Models16 Oct 2023 0 repositories listed
-
On the Importance of Spatial Relations for Few-shot Action Recognition14 Aug 2023 0 repositories listed
-
MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition3 Aug 2023 0 repositories listed
-
Few-shot Action Recognition via Intra- and Inter-Video Information Maximization10 May 2023 0 repositories listed
-
Rethinking matching-based few-shot action recognition28 Mar 2023 0 repositories listed
-
Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition19 Jan 2023 0 repositories listed
-
Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition1 Jan 2023 0 repositories listed
-
SMAM: Self and Mutual Adaptive Matching for Skeleton-Based Few-Shot Action Recognition27 Dec 2022 0 repositories listed
-
Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition9 Dec 2022 0 repositories listed
-
Knowledge Prompting for Few-shot Action Recognition22 Nov 2022 0 repositories listed
-
Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition30 Oct 2022 0 repositories listed
-
Hierarchical Compositional Representations for Few-shot Action Recognition19 Aug 2022 0 repositories listed
-
Compound Prototype Matching for Few-shot Action Recognition12 Jul 2022 0 repositories listed
-
9 Jun 2022 0 repositories listed
-
Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition1 Jan 2022 0 repositories listed
-
3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve23 Dec 2021 0 repositories listed
-
Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation30 Sep 2021 0 repositories listed
-
Learning Graphs for Knowledge Transfer With Limited Labels19 Jun 2021 0 repositories listed
-
Few-Shot Action Recognition with Compromised Metric via Optimal Transport8 Apr 2021 0 repositories listed
-
CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition18 Mar 2021 0 repositories listed
-
Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization13 Oct 2020 0 repositories listed
-
28 Aug 2020 0 repositories listed
-
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs1 Jun 2020 0 repositories listed
-
TAEN: Temporal Aware Embedding Network for Few-Shot Action Recognition21 Apr 2020 0 repositories listed
-
21 Jul 2019 0 repositories listed
-
27 Jun 2019 0 repositories listed
-
A Generative Approach to Zero-Shot and Few-Shot Action Recognition27 Jan 2018 0 repositories listed
Syntology lines on 10 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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