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 201–250 of 2759 papers

TitleStatusHype
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action RecognitionCode1
Concatenated Masked Autoencoders as Spatial-Temporal LearnerCode1
A Body Part Embedding Model With Datasets for Measuring 2D Human Motion SimilarityCode1
Conquering the cnn over-parameterization dilemma: A volterra filtering approach for action recognitionCode1
Audio-Visual Instance Discrimination with Cross-Modal AgreementCode1
Constructing Stronger and Faster Baselines for Skeleton-based Action RecognitionCode1
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action RecognitionCode1
ConvNet Architecture Search for Spatiotemporal Feature LearningCode1
Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action RecognitionCode1
A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action RecognitionCode1
Enlarging Instance-specific and Class-specific Information for Open-set Action RecognitionCode1
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical AggregationCode1
Epic-Sounds: A Large-scale Dataset of Actions That SoundCode1
Human-centric Scene Understanding for 3D Large-scale ScenariosCode1
Cross-Architecture Self-supervised Video Representation LearningCode1
A Lie Group Approach to Riemannian Batch NormalizationCode1
HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action RecognitionCode1
ImageNet-21K Pretraining for the MassesCode1
A Closer Look at Spatiotemporal Convolutions for Action RecognitionCode1
Improved Residual Networks for Image and Video RecognitionCode1
CT-Net: Channel Tensorization Network for Video ClassificationCode1
A Local-to-Global Approach to Multi-modal Movie Scene SegmentationCode1
DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action RecognitionCode1
Attention-Based Context Aware Reasoning for Situation RecognitionCode1
A Multigrid Method for Efficiently Training Video ModelsCode1
Data Efficient Video Transformer for Violence DetectionCode1
Deep Analysis of CNN-based Spatio-temporal Representations for Action RecognitionCode1
An Action Is Worth Multiple Words: Handling Ambiguity in Action RecognitionCode1
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action RecognitionCode1
Decoupling GCN with DropGraph Module for Skeleton-Based Action RecognitionCode1
Augmented Neural Fine-Tuning for Efficient Backdoor PurificationCode1
Interferometric Graph Transform: a Deep Unsupervised Graph RepresentationCode1
End-to-End Learning of Visual Representations from Uncurated Instructional VideosCode1
Deep Multimodal Feature Encoding for Video OrderingCode1
ViViT: A Video Vision TransformerCode1
Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action RecognitionCode1
Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal ModelingCode1
Iterate & Cluster: Iterative Semi-Supervised Action RecognitionCode1
A Comprehensive Study of Deep Video Action RecognitionCode1
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action RecognitionCode1
End-to-End Streaming Video Temporal Action Segmentation with Reinforce LearningCode1
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action RecognitionCode1
3D Human Action Representation Learning via Cross-View Consistency PursuitCode1
DirecFormer: A Directed Attention in Transformer Approach to Robust Action RecognitionCode1
Disentangled Non-Local Neural NetworksCode1
Disentangled Pre-training for Human-Object Interaction DetectionCode1
Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video ClassificationCode1
An Evaluation of Action Recognition Models on EPIC-KitchensCode1
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation LearningCode1
Mitigating and Evaluating Static Bias of Action Representations in the Background and the ForegroundCode1
Show:102550
← PrevPage 5 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
2OmniVec3-fold Accuracy99.6—Unverified
3VideoMAE V2-g3-fold Accuracy99.6—Unverified
4OmniVec23-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
8PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
9OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
10Text4Vis3-fold Accuracy98.2—Unverified