SOTAVerified

Action Recognition

Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.

In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.

Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1651–1700 of 2759 papers

TitleStatusHype
Improving Skeleton-based Action Recognitionwith Robust Spatial and Temporal Features—0
LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task ActivitiesCode1
AR-Net: Adaptive Frame Resolution for Efficient Action RecognitionCode1
Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition—0
Hierarchical Action Classification with Network Pruning—0
Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionCode1
Learning Video Representations from Textual Web Supervision—0
On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures—0
Representation Learning with Video Deep InfoMax—0
Approximated Bilinear Modules for Temporal ModelingCode1
Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos—0
Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition—0
Deep-VFX: Deep Action Recognition Driven VFX for Short Video—0
Directional Temporal Modeling for Action Recognition—0
Video Representation Learning by Recognizing Temporal Transformations—0
Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos—0
MotionSqueeze: Neural Motion Feature Learning for Video UnderstandingCode1
Context-Aware RCNN: A Baseline for Action Detection in VideosCode1
Hierarchical Contrastive Motion Learning for Video Action Recognition—0
Region-based Non-local Operation for Video ClassificationCode1
Challenge report:VIPriors Action Recognition Challenge—0
Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation—0
Temporal Distinct Representation Learning for Action Recognition—0
TinyVIRAT: Low-resolution Video Action RecognitionCode1
Unsupervised 3D Human Pose Representation with Viewpoint and Pose DisentanglementCode1
Universal-to-Specific Framework for Complex Action Recognition—0
IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in VideosCode1
Multitask Non-Autoregressive Model for Human Motion Prediction—0
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition—0
Representation Learning via Adversarially-Contrastive Optimal Transport—0
Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action TripletsCode1
AViD Dataset: Anonymized Videos from Diverse CountriesCode1
Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision—0
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action RecognitionCode1
VPN: Learning Video-Pose Embedding for Activities of Daily LivingCode1
Complex Human Action Recognition in Live Videos Using Hybrid FR-DL Method—0
Learning from Failure: Training Debiased Classifier from Biased ClassifierCode1
Quo Vadis, Skeleton Action Recognition ?Code1
Egocentric Action Recognition by Video Attention and Temporal Context—0
Path Signatures on Lie GroupsCode0
Attention-Oriented Action Recognition for Real-Time Human-Robot Interaction—0
Low-light Environment Neural SurveillanceCode0
JUMPS: Joints Upsampling Method for Pose Sequences—0
Group Ensemble: Learning an Ensemble of ConvNets in a single ConvNetCode0
The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and PoseCode1
Automatic Operating Room Surgical Activity Recognition for Robot-Assisted Surgery—0
Video Representation Learning with Visual Tempo ConsistencyCode1
Dynamic Sampling Networks for Efficient Action Recognition in Videos—0
Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action RecognitionCode0
Unsupervised Learning of Video Representations via Dense Trajectory ClusteringCode1
Show:102550
← PrevPage 34 of 56Next →
All datasetsSomething-Something V2UCF101HMDB-51Something-Something V1AVA v2.2EPIC-KITCHENS-100NTU RGB+DNTU RGB+D 120Diving-48ActivityNetAVA v2.1H2O (2 Hands and Objects)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MViTv2-B (IN-21K + Kinetics400 pretrain)Top-5 Accuracy93.4—Unverified
2RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips)Top-5 Accuracy91.1—Unverified
3MVD (Kinetics400 pretrain, ViT-H, 16 frame)Top-1 Accuracy77.3—Unverified
4InternVideoTop-1 Accuracy77.2—Unverified
5DejaVidTop-1 Accuracy77.2—Unverified
6InternVideo2-1BTop-1 Accuracy77.1—Unverified
7VideoMAE V2-gTop-1 Accuracy77—Unverified
8MVD (Kinetics400 pretrain, ViT-L, 16 frame)Top-1 Accuracy76.7—Unverified
9Hiera-L (no extra data)Top-1 Accuracy76.5—Unverified
10TubeViT-LTop-1 Accuracy76.1—Unverified
#ModelMetricClaimedVerifiedStatus
1FTP-UniFormerV2-L/143-fold Accuracy99.7—Unverified
2OmniVec23-fold Accuracy99.6—Unverified
3OmniVec3-fold Accuracy99.6—Unverified
4VideoMAE V2-g3-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
8OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
9PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
10Text4Vis3-fold Accuracy98.2—Unverified