Browse State-of-the-Art › Self-Supervised Action Recognition
Self-Supervised Action Recognition
35 papers with code · 6 benchmarks · 5 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
6 leaderboard tables shown for this task, 6 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. 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
5 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: 51 · with a code link: 35 · where Syntology ran a sample: 12 (9 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 (12 of 51 tagged: 9 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 51 of 51, 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.
-
23 Mar 2022 9 repositories listed Syntology official (archive's flag): 9 ran · 10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 13 harvested samples) · 12 pointer-only (licence)Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets.
-
13 Jun 2019 8 repositories listed Syntology official (archive's flag): 1 ran · 4 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; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 2 pointer-only (licence)We analyze key properties of the approach that make it work, finding that the contrastive loss outperforms a popular alternative based on cross-view prediction, and that the more views we learn from, the better the…
-
8 Dec 2022 4 repositories listedFor the choice of teacher models, we observe that students taught by video teachers perform better on temporally-heavy video tasks, while image teachers transfer stronger spatial representations for spatially-heavy…
-
9 Aug 2020 4 repositories listedOur representations are learned using a contrastive loss, where two augmented clips from the same short video are pulled together in the embedding space, while clips from different videos are pushed away.
-
15 Jul 2023 2 repositories listedInspired by SkeletonBYOL, this paper further presents a Cross-Model and Cross-Stream (CMCS) framework.
-
21 Dec 2022 2 repositories listedA good data representation should contain relations between the instances, or semantic similarity and dissimilarity, that contrastive learning harms by considering all negatives as noise.
-
19 Nov 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) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result (of 6 harvested samples) · 6 pointer-only (licence)Masked Video Autoencoder (MVA) approaches have demonstrated their potential by significantly outperforming previous video representation learning methods.
-
12 Oct 2022 2 repositories listedThe latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.
-
29 Apr 2021 2 repositories listedWe present a large-scale study on unsupervised spatiotemporal representation learning from videos.
-
6 Aug 2020 2 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 4 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; 4 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)With the proposed Inter-Intra Contrastive (IIC) framework, we can train spatio-temporal convolutional networks to learn video representations.
-
1 May 2023 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) · 6 unverified (of 12 harvested samples) · 12 pointer-only (licence)This paper proposes an attention-based contrastive learning framework for skeleton representation learning, called SkeAttnCLR, which integrates local similarity and global features for skeleton-based action…
-
29 Mar 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 6 harvested samples)Finally, we successfully train a video ViT model with a billion parameters, which achieves a new state-of-the-art performance on the datasets of Kinetics (90.
-
17 Feb 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 2 pointer-only (licence)Specifically, we construct a negative-sample-free triplet steam structure that is composed of an anchor stream without any masking, a spatial masking stream with Central Spatial Masking (CSM), and a temporal masking…
-
25 Nov 2022 1 repository listedFirst, masked data reconstruction is performed to learn modality-specific representations from audio and visual streams.
-
25 Jun 2022 1 repository listedOne of the key reasons for this is that sampling pairs of similar video clips, a required step for many self-supervised contrastive learning methods, is currently done conservatively to avoid false positives.
-
7 Dec 2021 1 repository listedIn this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR)…
-
9 Nov 2021 1 repository listedWe present CrissCross, a self-supervised framework for learning audio-visual representations.
-
19 Jun 2021 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 4 unverified (of 4 harvested samples)We introduce a framework for learning from unlabeled video what is predictable in the future.
-
18 Jun 2021 1 repository listedInstance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning.
-
30 Mar 2021 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) · 1 unverified (of 8 harvested samples)Most successful self-supervised learning methods are trained to align the representations of two independent views from the data.
-
20 Jan 2021 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct across the temporal dimension.
-
29 Oct 2020 1 repository listedIt is convenient to treat PCL as a standard training strategy and apply it to many other works in self-supervised video feature learning.
-
27 Oct 2020 1 repository listedWe study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition.
-
19 Oct 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)The objective of this paper is visual-only self-supervised video representation learning.
-
29 Jun 2020 1 repository listedIn particular, we explore how best to combine the modalities, such that fine-grained representations of the visual and audio modalities can be maintained, whilst also integrating text into a common embedding.
-
1 Jun 2020 1 repository listedThe generative perception model acts as a feature decoder to focus on comprehending high temporal resolution and short-term representation by introducing a motion-attention mechanism.
-
27 Apr 2020 1 repository listedOur method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa.
-
13 Apr 2020 1 repository listedWe demonstrate how those learned features can boost the performance of self-supervised action recognition, and can be used for video retrieval.
-
21 Mar 2020 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding space, rather than indirectly learning it through ranking or predictive proxy tasks.
-
5 Mar 2020 1 repository listedWe propose a self-supervised visual learning method by predicting the variable playback speeds of a video.
-
2 Jan 2020 1 repository listed Syntology 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) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
28 Nov 2019 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
10 Sep 2019 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples)
-
7 Apr 2019 1 repository listed
-
3 Aug 2017 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) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Feature Hallucination for Self-supervised Action Recognition25 Jun 2025 0 repositories listed
-
9 Jun 2023 0 repositories listed
-
Self-supervised Contrastive Learning for Audio-Visual Action Recognition28 Apr 2022 0 repositories listed
-
Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training27 Apr 2022 0 repositories listed
-
19 Aug 2021 0 repositories listed
-
Self-Supervised Learning via multi-Transformation Classification for Action Recognition20 Feb 2021 0 repositories listed
-
26 Feb 2020 0 repositories listed
-
28 Oct 2019 0 repositories listed
-
1 Jun 2019 0 repositories listed
-
28 Nov 2018 0 repositories listed
-
24 Nov 2018 0 repositories listed
-
30 Jun 2018 0 repositories listed
-
1 Jun 2018 0 repositories listed
-
21 Nov 2016 0 repositories listed
-
8 Sep 2016 0 repositories listed
-
28 Mar 2016 0 repositories listed
Syntology lines on 16 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