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 2501–2550 of 2759 papers

TitleStatusHype
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action RecognitionCode0
Ensemble Modeling for Multimodal Visual Action RecognitionCode0
Unsupervised Learning from Video with Deep Neural EmbeddingsCode0
Action Recognition based on Cross-Situational Action-object StatisticsCode0
Spatiotemporal Action Recognition in Restaurant VideosCode0
Towards a geometric understanding of Spatio Temporal Graph Convolution NetworksCode0
An Animation-based Augmentation Approach for Action Recognition from Discontinuous VideoCode0
Analysis of Hand Segmentation in the WildCode0
Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' ActionsCode0
Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM NetworksCode0
Unsupervised Learning of View-invariant Action RepresentationsCode0
Precondition and Effect Reasoning for Action RecognitionCode0
Learning Skeletal Graph Neural Networks for Hard 3D Pose EstimationCode0
Zero-Shot Action Recognition from Diverse Object-Scene CompositionsCode0
Unsupervised Motion Representation Learning with Capsule AutoencodersCode0
Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction RecognitionCode0
Learning long-term dependencies for action recognition with a biologically-inspired deep networkCode0
Unsupervised Representation Learning by Sorting SequencesCode0
End-to-End Semantic Video Transformer for Zero-Shot Action RecognitionCode0
Pre-training for Action Recognition with Automatically Generated Fractal DatasetsCode0
Beyond the Benchmark: Detecting Diverse Anomalies in VideosCode0
Beyond Short Snippets: Deep Networks for Video ClassificationCode0
Learning Human Action Recognition Representations Without Real HumansCode0
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural SearchingCode0
Bayesian Hierarchical Dynamic Model for Human Action RecognitionCode0
Balanced Representation Learning for Long-tailed Skeleton-based Action RecognitionCode0
Action Recognition Using Volumetric Motion RepresentationsCode0
Towards Improving Spatiotemporal Action Recognition in VideosCode0
Back to the Future: Cycle Encoding Prediction for Self-supervised Contrastive Video Representation LearningCode0
Enhancing Split Computing and Early Exit Applications through Predefined SparsityCode0
Learning Gating ConvNet for Two-Stream based Methods in Action RecognitionCode0
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action RecognitionCode0
Action Recognition using Visual AttentionCode0
Analysis and Extensions of Adversarial Training for Video ClassificationCode0
A Video-based End-to-end Pipeline for Non-nutritive Sucking Action Recognition and Segmentation in Young InfantsCode0
Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-TrainingCode0
Learning from Video and Text via Large-Scale Discriminative ClusteringCode0
Enhancing human action recognition with GAN-based data augmentationCode0
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action RecognitionCode0
ProMQA: Question Answering Dataset for Multimodal Procedural Activity UnderstandingCode0
Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action DetectionCode0
Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action RecognitionCode0
Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action RecognitionCode0
Video Transformer NetworkCode0
Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual ContextCode0
PSO-Convolutional Neural Networks with Heterogeneous Learning RateCode0
Learning deep representations for video-based intake gesture detectionCode0
Learning Actor Relation Graphs for Group Activity RecognitionCode0
End-to-end Video-level Representation Learning for Action RecognitionCode0
Large-scale weakly-supervised pre-training for video action recognitionCode0
Show:102550
← PrevPage 51 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
4DejaVidTop-1 Accuracy77.2—Unverified
5InternVideoTop-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
3VideoMAE V2-g3-fold Accuracy99.6—Unverified
4OmniVec3-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
8PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
9ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
10LGD-3D Two-stream3-fold Accuracy98.2—Unverified