Action Recognition In Videos

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

17 leaderboard tables shown for this task, 17 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 17 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

17 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 71 papers with code (124 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.

• Learning Spatiotemporal Features with 3D Convolutional Networks
  2 Dec 2014 29 repositories listed
  We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset.
• 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.
• SlowFast Networks for Video Recognition
  10 Dec 2018 15 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  We present SlowFast networks for video recognition.
• 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.
• YouTube-8M: A Large-Scale Video Classification Benchmark
  27 Sep 2016 7 repositories listed Syntology ran 1 of 9 samples · 8 unverified
  Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using TensorFlow.
• 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.
• 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…
• You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
  15 Nov 2019 5 repositories listed Syntology ran 3 of 12 samples · 9 unverified · 2 pointer-only (licence)
  YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation.
• 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.
• Temporal Relational Reasoning in Videos
  22 Nov 2017 5 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species.
• 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.
• Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
  1 Jun 2023 4 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance.
• Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos
  11 Apr 2024 3 repositories listed
  These spatial features then undergo intermediate temporal modeling facilitated by the Mamba block before progressing to the encoder section, which comprises vanilla upsampling Shift S-GCN blocks.
• Gating Revisited: Deep Multi-layer RNNs That Can Be Trained
  25 Nov 2019 3 repositories listed
  We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.
• What Makes Training Multi-Modal Classification Networks Hard?
  29 May 2019 3 repositories listed Syntology ran 1 of 11 samples · 10 unverified
  Consider end-to-end training of a multi-modal vs.
• R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
  22 Mar 2017 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  We address the problem of activity detection in continuous, untrimmed video streams.
• Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer
  17 Feb 2023 2 repositories listed
  To extend our approach to video, we integrate ConvNets with state-of-the-art temporal methods such as Transformer and Recurrent Neural Networks.
• Florence: A New Foundation Model for Computer Vision
  22 Nov 2021 2 repositories listed
  Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications.
• ActionCLIP: A New Paradigm for Video Action Recognition
  17 Sep 2021 2 repositories listed Syntology ran 5 of 9 samples · 4 unverified
  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…
• Busy-Quiet Video Disentangling for Video Classification
  29 Mar 2021 2 repositories listed
  We design a trainable Motion Band-Pass Module (MBPM) for separating busy information from quiet information in raw video data.
• Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
  6 Aug 2020 2 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  With the proposed Inter-Intra Contrastive (IIC) framework, we can train spatio-temporal convolutional networks to learn video representations.
• IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos
  13 Jul 2020 2 repositories listed
  Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input.
• Learning Video Representations from Correspondence Proposals
  20 May 2019 2 repositories listed
  In particular, it can effectively learn representations for videos by mixing appearance and long-range motion with an RGB-only input.
• Resource Efficient 3D Convolutional Neural Networks
  4 Apr 2019 2 repositories listed
  Recently, convolutional neural networks with 3D kernels (3D CNNs) have been very popular in computer vision community as a result of their superior ability of extracting spatio-temporal features within video frames…
• 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning
  26 Feb 2018 2 repositories listed Syntology ran 0 of 25 samples · 25 unverified
  Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature.
• Convolutional Two-Stream Network Fusion for Video Action Recognition
  22 Apr 2016 2 repositories listed
  Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information.
• Action Recognition using Visual Attention
  12 Nov 2015 2 repositories listed
  We propose a soft attention based model for the task of action recognition in videos.
• Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition
  19 Mar 2025 1 repository listed
  In this paper, we propose BHaRNet (Body-Hand action Recognition Network), a novel framework that augments a typical body-expert model with a hand-expert model.
• EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition
  10 Aug 2024 1 repository listed
  In this work, we present an efficient pose-driven attention-guided multimodal network (EPAM-Net) for action recognition in videos.

Syntology lines on 14 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.