Temporal Action Localization

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

14 leaderboard tables shown for this task, 14 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. 10 shown of 14 until expanded.

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

42 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 42 until expanded.

Subtasks archive 2025-07-28

8 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 493 papers with code (1,477 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.

• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
  23 Jan 2018 24 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Dynamics of human body skeletons convey significant information for human action recognition.
• A Closer Look at Spatiotemporal Convolutions for Action Recognition
  30 Nov 2017 24 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 4 pointer-only (licence)
  In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition.
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
  30 Oct 2017 24 repositories listed Syntology ran 4 of 7 samples · 3 unverified · 3 pointer-only (licence)
  Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.
• Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
  2 Aug 2016 22 repositories listed Syntology ran 2 of 24 samples · 22 unverified · 3 pointer-only (licence)
  The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.
• BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
  8 Jun 2018 17 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion…
• BMN: Boundary-Matching Network for Temporal Action Proposal Generation
  23 Jul 2019 15 repositories listed Syntology ran 3 of 11 samples · 8 unverified
  To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending…
• Unsupervised Learning of Video Representations using LSTMs
  16 Feb 2015 12 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 2 pointer-only (licence)
  We further evaluate the representations by finetuning them for a supervised learning problem - human action recognition on the UCF-101 and HMDB-51 datasets.
• Temporal Segment Networks for Action Recognition in Videos
  8 May 2017 11 repositories listed
  Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
• Graph-Based Global Reasoning Networks
  30 Nov 2018 9 repositories listed Syntology ran 8 of 15 samples · 7 unverified · 4 pointer-only (licence)
  In this work, we propose a new approach for reasoning globally in which a set of features are globally aggregated over the coordinate space and then projected to an interaction space where relational reasoning can be…
• AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
  23 May 2017 9 repositories listed
  The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.
• StNet: Local and Global Spatial-Temporal Modeling for Action Recognition
  5 Nov 2018 8 repositories listed
  In this paper, in contrast to the existing CNN+RNN or pure 3D convolution based approaches, we explore a novel spatial temporal network (StNet) architecture for both local and global spatial-temporal modeling in videos.
• G-TAD: Sub-Graph Localization for Temporal Action Detection
  26 Nov 2019 7 repositories listed Syntology ran 3 of 18 samples · 15 unverified
  In this work, we propose a graph convolutional network (GCN) model to adaptively incorporate multi-level semantic context into video features and cast temporal action detection as a sub-graph localization problem.
• Multivariate LSTM-FCNs for Time Series Classification
  14 Jan 2018 7 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Over the past decade, multivariate time series classification has received great attention.
• Two-Stream Convolutional Networks for Action Recognition in Videos
  9 Jun 2014 7 repositories listed Syntology ran 1 of 7 samples · 6 unverified · 2 pointer-only (licence)
  Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art.
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
  3 Dec 2012 7 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large number of classes, large number of clips and also unconstrained nature of such clips.
• EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
  14 Nov 2022 6 repositories listed Syntology ran 1 of 3 samples · 2 unverified
  We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data.
• Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation
  17 Apr 2018 6 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 3 pointer-only (licence)
  Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets.
• Delving Deeper into Convolutional Networks for Learning Video Representations
  19 Nov 2015 6 repositories listed
  We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).
• ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization
  21 Dec 2021 5 repositories listed
  Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available.
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
  22 Apr 2021 5 repositories listed Syntology ran 5 of 8 samples · 3 unverified · 8 pointer-only (licence)
  We train VATT end-to-end from scratch using multimodal contrastive losses and evaluate its performance by the downstream tasks of video action recognition, audio event classification, image classification, and…
• What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
  8 Apr 2019 5 repositories listed
  Can performance on the task of action quality assessment (AQA) be improved by exploiting a description of the action and its quality?
• Representation Flow for Action Recognition
  2 Oct 2018 5 repositories listed
  Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel within a convolutional neural network for action recognition.
• Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks
  23 May 2017 5 repositories listed
  Shot boundary detection (SBD) is an important component of many video analysis tasks, such as action recognition, video indexing, summarization and editing.
• Towards Good Practices for Very Deep Two-Stream ConvNets
  8 Jul 2015 5 repositories listed
  However, for action recognition in videos, the improvement of deep convolutional networks is not so evident.
• Describing Videos by Exploiting Temporal Structure
  27 Feb 2015 5 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions.
• Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
  1 Jul 2021 4 repositories listed
  Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer.
• Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
  20 May 2018 4 repositories listed
  In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing…
• Moments in Time Dataset: one million videos for event understanding
  9 Jan 2018 4 repositories listed
  We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds.
• Im2Flow: Motion Hallucination from Static Images for Action Recognition
  12 Dec 2017 4 repositories listed
  Second, we show the power of hallucinated flow for recognition, successfully transferring the learned motion into a standard two-stream network for activity recognition.
• TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
  30 Mar 2017 4 repositories listed
  We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.

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. Read from the graph 2026-09-24.