Spatio-Temporal Action Localization

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.

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

14 shown of 14 papers with code (37 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.

• 1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
  16 Jun 2020 3 repositories listed
  This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020.
• Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
  14 Jun 2020 3 repositories listed Syntology ran 1 of 27 samples · 26 unverified
  We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.
• InternVideo: General Video Foundation Models via Generative and Discriminative Learning
  6 Dec 2022 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  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…
• Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision
  9 Dec 2021 2 repositories listed
  Modern self-supervised learning algorithms typically enforce persistency of instance representations across views.
• Action Tubelet Detector for Spatio-Temporal Action Localization
  4 May 2017 2 repositories listed
  We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i.
• Scaling Open-Vocabulary Action Detection
  4 Apr 2025 1 repository listed
  In this work, we focus on scaling open-vocabulary action detection.
• VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
  29 Mar 2023 1 repository listed Syntology ran 2 of 6 samples · 4 unverified
  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.
• Unmasked Teacher: Towards Training-Efficient Video Foundation Models
  28 Mar 2023 1 repository listed Syntology ran 3 of 8 samples · 5 unverified
  Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain.
• E^2TAD: An Energy-Efficient Tracking-based Action Detector
  9 Apr 2022 1 repository listed
  Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays.
• KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization
  5 Nov 2021 1 repository listed
  Despite the simplicity of our approach, our lightweight end-to-end architecture achieves state-of-the-art frame-mAP of 74.
• ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos
  25 May 2021 1 repository listed Syntology ran 1 of 4 samples · 3 unverified · 4 pointer-only (licence)
  Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines.
• Video action detection by learning graph-based spatio-temporal interactions
  9 Dec 2019 1 repository listed
  Action Detection is a complex task that aims to detect and classify human actions in video clips.
• Actor-Centric Relation Network
  28 Jul 2018 1 repository listed
  A visualization of the learned relation features confirms that our approach is able to attend to the relevant relations for each action.
• Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
  3 Apr 2017 1 repository listed
  In 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.

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. Read from the graph 2026-09-24.