Browse State-of-the-Art › Spatio-Temporal Action Localization
Spatio-Temporal Action Localization
14 papers with code · 1 benchmark · 6 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 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 |
|---|---|---|---|---|---|
| AVA-Kinetics (7 rows) | VideoMAE V2-g | VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking | code | 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 | 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: 37 · with a code link: 14 · where Syntology ran a sample: 5 (4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 37 tagged: 4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 37 of 37, 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.
-
16 Jun 2020 3 repositories listedThis technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020.
-
14 Jun 2020 3 repositories listed Syntology official (archive's flag): 12 ran · 17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified (of 27 harvested samples) · 4 pointer-only (licence)We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.
-
6 Dec 2022 2 repositories 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) · 0 unverified (of 3 harvested samples)Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary…
-
9 Dec 2021 2 repositories listedModern self-supervised learning algorithms typically enforce persistency of instance representations across views.
-
4 May 2017 2 repositories listedWe propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i. e., sequences of bounding boxes with associated scores.
-
4 Apr 2025 1 repository listedIn this work, we focus on scaling open-vocabulary action detection.
-
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.
-
28 Mar 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 3 pointer-only (licence)Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain.
-
9 Apr 2022 1 repository listedVideo action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays.
-
5 Nov 2021 1 repository listedDespite the simplicity of our approach, our lightweight end-to-end architecture achieves state-of-the-art frame-mAP of 74.
-
25 May 2021 1 repository 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: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines.
-
9 Dec 2019 1 repository listedAction Detection is a complex task that aims to detect and classify human actions in video clips.
-
28 Jul 2018 1 repository listedA visualization of the learned relation features confirms that our approach is able to attend to the relevant relations for each action.
-
3 Apr 2017 1 repository listedIn this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images.
-
Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues1 Feb 2025 0 repositories listedThis paper introduces ViNet-S, a 36MB model based on the ViNet architecture with a U-Net design, featuring a lightweight decoder that significantly reduces model size and parameters without compromising performance.
-
Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives21 Sep 2023 0 repositories listedAction scene understanding in soccer is a challenging task due to the complex and dynamic nature of the game, as well as the interactions between players.
-
24 Apr 2023 0 repositories listedThe most performant spatio-temporal action localisation models use external person proposals and complex external memory banks.
-
27 Mar 2023 0 repositories listedThis paper simultaneously addresses three limitations associated with conventional skeleton-based action recognition; skeleton detection and tracking errors, poor variety of the targeted actions, as well as person-wise…
-
MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization6 Apr 2022 0 repositories listedIn this paper, we introduce a novel large-scale video dataset dubbed MM-SEAL for multi-person multi-grained spatio-temporal action localization among human daily life.
-
15 Jun 2021 0 repositories listedThis paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021.
-
Relevance Detection in Cataract Surgery Videos by Spatio-Temporal Action Localization29 Apr 2021 0 repositories listedIn cataract surgery, the operation is performed with the help of a microscope.
-
Real-time Spatio-temporal Action Localization via Learning Motion Representation30 Nov 2020 0 repositories listedAbstract.
-
Unsupervised Domain Adaptation for Spatio-Temporal Action Localization19 Oct 2020 0 repositories listedSpatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features.
-
CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization19 Aug 2020 0 repositories listedMost current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by…
-
Three Branches: Detecting Actions With Richer Features13 Aug 2019 0 repositories listedWe present our three branch solutions for International Challenge on Activity Recognition at CVPR2019.
-
Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization25 Jul 2019 0 repositories listedThis technical report present an overview of our system proposed for the spatio-temporal action localization(SAL) task in ActivityNet Challenge 2019.
-
Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 201914 Jun 2019 0 repositories listedThis notebook paper presents an overview and comparative analysis of our systems designed for the following three tasks in ActivityNet Challenge 2019: trimmed action recognition, dense-captioning events in videos, and…
-
Improving Action Localization by Progressive Cross-stream Cooperation28 May 2019 0 repositories listedSpatio-temporal action localization consists of three levels of tasks: spatial localization, action classification, and temporal segmentation.
-
Spatio-Temporal Action Localization in a Weakly Supervised Setting6 May 2019 0 repositories listedEnabling computational systems with the ability to localize actions in video-based content has manifold applications.
-
Spatio-Temporal Instance Learning: Action Tubes from Class Supervision8 Jul 2018 0 repositories listedThe goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels.
-
YH Technologies at ActivityNet Challenge 201829 Jun 2018 0 repositories listed
-
Modeling Spatio-Temporal Human Track Structure for Action Localization28 Jun 2018 0 repositories listed
-
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection10 Jul 2016 0 repositories listed
-
What If We Do Not Have Multiple Videos of the Same Action? -- Video Action Localization Using Web Images1 Jun 2016 0 repositories listed
-
Learning to track for spatio-temporal action localization5 Jun 2015 0 repositories listed
-
Action is in the Eye of the Beholder: Eye-gaze Driven Model for Spatio-Temporal Action Localization1 Dec 2013 0 repositories listed
-
Max-Margin Structured Output Regression for Spatio-Temporal Action Localization1 Dec 2012 0 repositories listed
Syntology lines on 5 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