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 301–350 of 2759 papers

TitleStatusHype
Spatio-temporal Relation Modeling for Few-shot Action RecognitionCode1
Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action RecognitionCode1
Prompting Visual-Language Models for Efficient Video UnderstandingCode1
TCGL: Temporal Contrastive Graph for Self-supervised Video Representation LearningCode1
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action RecognitionCode1
E^2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action RecognitionCode1
Self-supervised Video TransformerCode1
BEVT: BERT Pretraining of Video TransformersCode1
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
MAU: A Motion-Aware Unit for Video Prediction and BeyondCode1
Anonymization for Skeleton Action RecognitionCode1
Learning from Temporal Gradient for Semi-supervised Action RecognitionCode1
Florence: A New Foundation Model for Computer VisionCode1
M2A: Motion Aware Attention for Accurate Video Action RecognitionCode1
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly DetectionCode1
Real-time 3D human action recognition based on Hyperpoint sequenceCode1
Revisiting spatio-temporal layouts for compositional action recognitionCode1
Relational Self-Attention: What's Missing in Attention for Video UnderstandingCode1
With a Little Help from my Temporal Context: Multimodal Egocentric Action RecognitionCode1
Logsig-RNN: a novel network for robust and efficient skeleton-based action recognitionCode1
LSTC: Boosting Atomic Action Detection with Long-Short-Term ContextCode1
Counterfactual Debiasing Inference for Compositional Action RecognitionCode1
Object-Region Video TransformersCode1
Sign Language Recognition via Skeleton-Aware Multi-Model EnsembleCode1
Motion-aware Contrastive Video Representation Learning via Foreground-background MergingCode1
Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence ClassificationCode1
UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation LearningCode1
Fusion-GCN: Multimodal Action Recognition using Graph Convolutional NetworksCode1
ActionCLIP: A New Paradigm for Video Action RecognitionCode1
Improving Phenotype Prediction using Long-Range Spatio-Temporal Dynamics of Functional ConnectivityCode1
Video Pose Distillation for Few-Shot, Fine-Grained Sports Action RecognitionCode1
Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion PerceptionCode1
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionCode1
AutoVideo: An Automated Video Action Recognition SystemCode1
One-Shot Object Affordance Detection in the WildCode1
Skeleton-Contrastive 3D Action Representation LearningCode1
Unifying Nonlocal Blocks for Neural NetworksCode1
Elaborative Rehearsal for Zero-shot Action RecognitionCode1
Video Based Fall Detection Using Human PosesCode1
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action RecognitionCode1
TinyAction Challenge: Recognizing Real-world Low-resolution Activities in VideosCode1
EAN: Event Adaptive Network for Enhanced Action RecognitionCode1
Evidential Deep Learning for Open Set Action RecognitionCode1
UNIK: A Unified Framework for Real-world Skeleton-based Action RecognitionCode1
Data Efficient Video Transformer for Violence DetectionCode1
STAR: Sparse Transformer-based Action RecognitionCode1
TA2N: Two-Stage Action Alignment Network for Few-shot Action RecognitionCode1
Federated Learning for Multi-Center Imaging Diagnostics: A Study in Cardiovascular DiseaseCode1
Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action RecognitionCode1
Constructing Stronger and Faster Baselines for Skeleton-based Action RecognitionCode1
Show:102550
← PrevPage 7 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