Browse State-of-the-Art › Zero-Shot Action Recognition
Zero-Shot Action Recognition
40 papers with code · 7 benchmarks · 6 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
7 leaderboard tables shown for this task, 7 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 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): ActivityNet (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
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.
Papers archive 2025-07-28
archive papers tagged: 83 · with a code link: 40 · where Syntology ran a sample: 18 (15 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (18 of 83 tagged: 15 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 83 of 83, 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.
-
3 Oct 2023 6 repositories listed Syntology official (archive's flag): 5 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 14 harvested samples) · 3 pointer-only (licence)We thus propose VIDAL-10M with Video, Infrared, Depth, Audio and their corresponding Language, naming as VIDAL-10M.
-
31 Dec 2022 5 repositories listedIn this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video Attribute Association mechanism, which leverages the…
-
4 Jul 2022 5 repositories listedIn this study, we focus on transferring knowledge for video classification tasks.
-
27 Mar 2023 4 repositories listed Syntology community repositories only · 1 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; 0 where Syntology's instrument failed) · 3 unverified (of 4 harvested samples)Our approach incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters…
-
15 Nov 2016 4 repositories listedIn this paper we argue that the key to make deep ZSL models succeed is to choose the right embedding space.
-
15 Apr 2024 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)To be specific, we introduce Temporal Contextualization (TC), a layer-wise temporal information infusion mechanism for videos, which 1) extracts core information from each frame, 2) connects relevant information across…
-
4 Aug 2022 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result (of 3 harvested samples) · 3 pointer-only (licence)Extensive experiments demonstrate that our approach is effective and can be generalized to different video recognition scenarios.
-
24 Mar 2022 2 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval.
-
13 Jan 2022 2 repositories listed Syntology official (archive's flag): 2 ran · 13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified (of 24 harvested samples) · 6 pointer-only (licence)As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e. g., action recognition with linear evaluation.
-
17 Sep 2021 2 repositories listed Syntology official (archive's flag): 6 ran · 6 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; 5 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples) · 4 pointer-only (licence)Moreover, to handle the deficiency of label texts and make use of tremendous web data, we propose a new paradigm based on this multimodal learning framework for action recognition, which we dub "pre-train, prompt and…
-
30 Mar 2015 2 repositories listedAttributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce.
-
30 Sep 2014 2 repositories listedImage classification has advanced significantly in recent years with the availability of large-scale image sets.
-
13 Dec 2024 1 repository listedZero-shot action recognition (ZSAR) requires collaborative multi-modal spatiotemporal understanding.
-
27 Nov 2024 1 repository listedSpecifically, we obtain relative gains of 3.
-
16 Nov 2024 1 repository listedIn zero-shot skeleton-based action recognition, aligning skeleton features with the text features of action labels is essential for accurately predicting unseen actions.
-
19 Jun 2024 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) · 0 unverified (of 3 harvested samples)While remarkable progress has been made on supervised skeleton-based action recognition, the challenge of zero-shot recognition remains relatively unexplored.
-
13 Dec 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 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; 9 where Syntology's instrument failed) · 4 unverified (of 13 harvested samples) · 4 pointer-only (licence)Recent advancements in large-scale pre-training of visual-language models on paired image-text data have demonstrated impressive generalization capabilities for zero-shot tasks.
-
30 Nov 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 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; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)Due to the resource-intensive nature of training vision-language models on expansive video data, a majority of studies have centered on adapting pre-trained image-language models to the video domain.
-
29 Sep 2023 1 repository listedThe textual narratives forge connections between seen and unseen classes, overcoming the bottleneck of labeled data that has long impeded advancements in this exciting domain.
-
14 Aug 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)We propose a model called OTI for ZSVR by employing orthogonal temporal interpolation and the matching loss based on VLMs.
-
20 Jul 2023 1 repository listedExisting action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors.
-
13 Jul 2023 1 repository listedSpecifically, we utilize a multi-scale approach to generate video-related descriptions.
-
6 Apr 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 5 samples that ran constructed an object rather than computing a result (of 9 harvested samples)Through this prompting scheme, we can achieve state-of-the-art zero-shot performance on Kinetics-600, HMDB51 and UCF101 while remaining competitive in the supervised setting.
-
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.
-
24 Sep 2022 1 repository listedThis work introduces a new ZSAR method based on the relationships of actions-objects and actions-descriptive sentences.
-
17 May 2022 1 repository listedOur goal in this paper is the adaptation of image-text models for long video retrieval.
-
26 Apr 2022 1 repository listedDominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations…
-
29 Mar 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 5 pointer-only (licence)Further, we synthesize features of unseen classes by proposing a class generator that interpolates and extrapolates the features of seen classes.
-
28 Mar 2022 1 repository listedHowever, due to the complexity of actions, it remains challenging to transfer knowledge learned from source to target action domains.
-
10 Mar 2022 1 repository listedWhile video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction.
-
18 Dec 2021 1 repository listed
-
26 Oct 2021 1 repository listed
-
5 Aug 2021 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 15 harvested samples)
-
27 Jul 2021 1 repository listed
-
3 Mar 2020 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 12 harvested samples)
-
16 Jan 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
17 Jul 2019 1 repository listed
-
18 Apr 2019 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
16 Oct 2018 1 repository listed
-
6 Jul 2015 1 repository listed
-
The Role of Video Generation in Enhancing Data-Limited Action Understanding26 May 2025 0 repositories listed
-
Can masking background and object reduce static bias for zero-shot action recognition?22 Jan 2025 0 repositories listed
-
Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition1 Jan 2025 0 repositories listed
-
Zero-Shot Action Recognition in Surveillance Videos28 Oct 2024 0 repositories listed
-
Continual Learning Improves Zero-Shot Action Recognition14 Oct 2024 0 repositories listed
-
Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment22 Sep 2024 0 repositories listed
-
Text-Enhanced Zero-Shot Action Recognition: A training-free approach29 Aug 2024 0 repositories listed
-
An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition2 Jun 2024 0 repositories listed
-
A Cross-Dataset Study for Text-based 3D Human Motion Retrieval27 May 2024 0 repositories listed
-
The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks14 May 2024 0 repositories listed
-
11 Apr 2024 0 repositories listed
-
ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition22 Jan 2024 0 repositories listed
-
10 May 2023 0 repositories listed
-
6 Apr 2023 0 repositories listed
-
5 Apr 2023 0 repositories listed
-
Improving Zero-Shot Action Recognition using Human Instruction with Text Description21 Jan 2023 0 repositories listed
-
9 Dec 2022 0 repositories listed
-
REST: REtrieve & Self-Train for generative action recognition29 Sep 2022 0 repositories listed
-
15 Jul 2022 0 repositories listed
-
Learning Using Privileged Information for Zero-Shot Action Recognition17 Jun 2022 0 repositories listed
-
3 May 2022 0 repositories listed
-
Universal Prototype Transport for Zero-Shot Action Recognition and Localization8 Mar 2022 0 repositories listed
-
Reformulating Zero-shot Action Recognition for Multi-label Actions1 Dec 2021 0 repositories listed
-
Transductive Universal Transport for Zero-Shot Action Recognition29 Sep 2021 0 repositories listed
-
GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition25 May 2021 0 repositories listed
-
18 Jan 2021 0 repositories listed
-
28 Aug 2020 0 repositories listed
-
Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space26 Nov 2019 0 repositories listed
-
Zero-Shot Action Recognition in Videos: A Survey13 Sep 2019 0 repositories listed
-
Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework4 Aug 2019 0 repositories listed
-
21 Jul 2019 0 repositories listed
-
Action2Vec: A Crossmodal Embedding Approach to Action Learning2 Jan 2019 0 repositories listed
-
22 Mar 2018 0 repositories listed
-
A Generative Approach to Zero-Shot and Few-Shot Action Recognition27 Jan 2018 0 repositories listed
-
Natural Language Descriptions for Human Activities in Video Streams1 Sep 2017 0 repositories listed
-
1 Jul 2017 0 repositories listed
-
28 Jun 2017 0 repositories listed
-
26 Nov 2016 0 repositories listed
-
Learning a Pose Lexicon for Semantic Action Recognition1 Apr 2016 0 repositories listed
-
Transductive Zero-Shot Action Recognition by Word-Vector Embedding13 Nov 2015 0 repositories listed
-
23 Oct 2015 0 repositories listed
-
5 Feb 2015 0 repositories listed
-
1 Dec 2013 0 repositories listed
Syntology lines on 18 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