Video Classification

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

12 leaderboard tables shown for this task, 12 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 12 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

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

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 206 papers with code (455 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.

• Non-local Neural Networks
  21 Nov 2017 32 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.
• Group Normalization
  22 Mar 2018 22 repositories listed Syntology ran 5 of 15 samples · 10 unverified · 4 pointer-only (licence)
  FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
• Is Space-Time Attention All You Need for Video Understanding?
  9 Feb 2021 16 repositories listed Syntology ran 35 of 43 samples · 8 unverified · 14 pointer-only (licence)
  We present a convolution-free approach to video classification built exclusively on self-attention over space and time.
• Video Swin Transformer
  24 Jun 2021 15 repositories listed Syntology ran 7 of 32 samples · 25 unverified
  The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks.
• 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.
• Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
  19 Nov 2015 11 repositories listed
  One of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject differences, as well as to inherent noise associated with…
• ViViT: A Video Vision Transformer
  29 Mar 2021 10 repositories listed Syntology ran 14 of 21 samples · 7 unverified · 1 pointer-only (licence)
  We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification.
• Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
  10 Apr 2020 10 repositories listed Syntology ran 2 of 22 samples · 20 unverified
  Therefore, in the present paper, we conduct exploration study in order to improve spatiotemporal 3D CNNs as follows: (i) Recently proposed large-scale video datasets help improve spatiotemporal 3D CNNs in terms of video…
• MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
  2 Dec 2021 9 repositories listed
  In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection.
• UniFormer: Unifying Convolution and Self-attention for Visual Recognition
  24 Jan 2022 8 repositories listed
  Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both…
• X3D: Expanding Architectures for Efficient Video Recognition
  9 Apr 2020 8 repositories listed Syntology ran 2 of 15 samples · 13 unverified
  This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth.
• Video Classification with Channel-Separated Convolutional Networks
  4 Apr 2019 7 repositories listed Syntology ran 1 of 4 samples · 3 unverified
  It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video classification networks; 2) what factors matter the most in 3D group convolutional networks; and 3) what are good…
• 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.
• ECO: Efficient Convolutional Network for Online Video Understanding
  24 Apr 2018 6 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  In this paper, we introduce a network architecture that takes long-term content into account and enables fast per-video processing at the same time.
• Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
  4 Jul 2022 5 repositories listed
  In this study, we focus on transferring knowledge for video classification tasks.
• 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.
• Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
  27 Nov 2017 5 repositories listed
  In this paper, however, we show that temporal information, especially longer-term patterns, may not be necessary to achieve competitive results on common video classification datasets.
• Learnable pooling with Context Gating for video classification
  21 Jun 2017 5 repositories listed
  In particular, we evaluate our method on the large-scale multi-modal Youtube-8M v2 dataset and outperform all other methods in the Youtube 8M Large-Scale Video Understanding challenge.
• Reversible Vision Transformers
  9 Feb 2023 4 repositories listed Syntology ran 12 of 29 samples · 17 unverified · 26 pointer-only (licence)
  Reversible Vision Transformers achieve a reduced memory footprint of up to 15.
• Billion-scale semi-supervised learning for image classification
  2 May 2019 4 repositories listed
  This paper presents a study of semi-supervised learning with large convolutional networks.
• 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.
• Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
  12 Jul 2023 3 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
  The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged.
• Token Shift Transformer for Video Classification
  5 Aug 2021 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  It is worth noticing that our TokShift transformer is a pure convolutional-free video transformer pilot with computational efficiency for video understanding.
• Revisiting ResNets: Improved Training and Scaling Strategies
  13 Mar 2021 3 repositories listed
  Using improved training and scaling strategies, we design a family of ResNet architectures, ResNet-RS, which are 1.
• VideoMix: Rethinking Data Augmentation for Video Classification
  7 Dec 2020 3 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  Recent data augmentation strategies have been reported to address the overfitting problems in static image classifiers.
• Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
  20 Jun 2020 3 repositories listed
  This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales.
• Non-Local Neural Networks With Grouped Bilinear Attentional Transforms
  1 Jun 2020 3 repositories listed
  The core of our method is learnable and data-adaptive bilinear attentional transform (BA-Transform), whose merits are three-folds: first, BA-Transform is versatile to model a wide spectrum of local or global attentional…
• On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
  16 Mar 2020 3 repositories listed
  In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant.
• A Multigrid Method for Efficiently Training Video Models
  2 Dec 2019 3 repositories listed Syntology ran 2 of 10 samples · 8 unverified · 3 pointer-only (licence)
  We empirically demonstrate a general and robust grid schedule that yields a significant out-of-the-box training speedup without a loss in accuracy for different models (I3D, non-local, SlowFast), datasets (Kinetics,…

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.