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 901–950 of 2759 papers

TitleStatusHype
Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction RecognitionCode0
Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition—0
AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture SearchCode0
Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition—0
Active Generation Network of Human Skeleton for Action Recognition—0
MV2MAE: Multi-View Video Masked Autoencoders—0
Computer Vision for Primate Behavior Analysis in the Wild—0
Multi-modality action recognition based on dual feature shift in vehicle cabin monitoring—0
Multi-model learning by sequential reading of untrimmed videos for action recognition—0
Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition—0
GTAutoAct: An Automatic Datasets Generation Framework Based on Game Engine Redevelopment for Action Recognition—0
Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection—0
M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition—0
ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition—0
Exploring Missing Modality in Multimodal Egocentric Datasets—0
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution ShiftsCode0
Image-based human re-identification: Which covariates are actually (the most) important?—0
Understanding Video Transformers via Universal Concept Discovery—0
GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition—0
Robustness Evaluation of Machine Learning Models for Robot Arm Action Recognition in Noisy Environments—0
Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-M^2DF)Code0
TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding—0
Collaboratively Self-supervised Video Representation Learning for Action Recognition—0
HaltingVT: Adaptive Token Halting Transformer for Efficient Video RecognitionCode0
Efficient Selective Audio Masked Multimodal Bottleneck Transformer for Audio-Video Classification—0
Two-stream joint matching method based on contrastive learning for few-shot action recognition—0
Big Data and Deep Learning in Smart Cities: A Comprehensive Dataset for AI-Driven Traffic Accident Detection and Computer Vision Systems—0
Just Add ?! Pose Induced Video Transformers for Understanding Activities of Daily Living—0
Selective Interpretable and Motion Consistent Privacy Attribute Obfuscation for Action Recognition—0
Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton SequenceCode0
PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition—0
Modality-Collaborative Test-Time Adaptation for Action Recognition—0
MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning—0
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning—0
A Large-Scale Re-identification Analysis in Sporting Scenarios: the Betrayal of Reaching a Critical Point—0
STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose EstimationCode0
Classifying Soccer Ball-on-Goal Position Through Kicker Shooting Action—0
Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action RecognitionCode0
PoseViNet: Distracted Driver Action Recognition Framework Using Multi-View Pose Estimation and Vision Transformer—0
Online Action Recognition for Human Risk Prediction with Anticipated Haptic Alert via WearablesCode0
Towards a geometric understanding of Spatio Temporal Graph Convolution NetworksCode0
X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge TransferCode0
Early Action Recognition with Action Prototypes—0
DVANet: Disentangling View and Action Features for Multi-View Action RecognitionCode0
STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action RecognitionCode0
From Detection to Action Recognition: An Edge-Based Pipeline for Robot Human Perception—0
Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-TrainingCode0
RotaTR: Detection Transformer for Dense and Rotated Object—0
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures—0
Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition—0
Show:102550
← PrevPage 19 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