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 351–400 of 2759 papers

TitleStatusHype
Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in VideosCode1
An Animation-based Augmentation Approach for Action Recognition from Discontinuous VideoCode0
O-TALC: Steps Towards Combating Oversegmentation within Online Action Segmentation—0
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in VideosCode0
TIM: A Time Interval Machine for Audio-Visual Action RecognitionCode2
X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model—0
Koala: Key frame-conditioned long video-LLM—0
PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos—0
Learning Correlation Structures for Vision Transformers—0
Multi-Scale Spatial-Temporal Self-Attention Graph Convolutional Networks for Skeleton-based Action Recognition—0
Disentangled Pre-training for Human-Object Interaction DetectionCode1
Leveraging YOLO-World and GPT-4V LMMs for Zero-Shot Person Detection and Action Recognition in Drone Imagery—0
Language Model Guided Interpretable Video Action ReasoningCode0
PREGO: online mistake detection in PRocedural EGOcentric videosCode1
LLMs are Good Action Recognizers—0
A Unified Framework for Human-centric Point Cloud Video Understanding—0
Hypergraph-based Multi-View Action Recognition using Event Cameras—0
OmniVid: A Generative Framework for Universal Video UnderstandingCode2
DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action RecognitionCode2
Understanding Long Videos with Multimodal Language ModelsCode2
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with ObjectsCode3
Emotion Recognition from the perspective of Activity Recognition—0
Enhancing Video Transformers for Action Understanding with VLM-aided Training—0
InternVideo2: Scaling Foundation Models for Multimodal Video UnderstandingCode7
GCN-DevLSTM: Path Development for Skeleton-Based Action RecognitionCode1
vid-TLDR: Training Free Token merging for Light-weight Video TransformerCode2
Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality AssessmentCode2
Benchmarking Badminton Action Recognition with a New Fine-Grained Dataset—0
ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and MoreCode1
Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition—0
Multi-View Video-Based Learning: Leveraging Weak Labels for Frame-Level Perception—0
A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognition—0
A Lie Group Approach to Riemannian Batch NormalizationCode1
CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner—0
Skeleton-Based Human Action Recognition with Noisy LabelsCode0
On the Utility of 3D Hand Poses for Action RecognitionCode1
Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Lines—0
SkateFormer: Skeletal-Temporal Transformer for Human Action RecognitionCode2
EventRPG: Event Data Augmentation with Relevance Propagation GuidanceCode1
Real-Time Multimodal Cognitive Assistant for Emergency Medical ServicesCode1
Deep Learning Approaches for Human Action Recognition in Video Data—0
Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal ModelingCode1
Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition—0
Density-Guided Label Smoothing for Temporal Localization of Driving Actions—0
Coherent Temporal Synthesis for Incremental Action Segmentation—0
Benchmarking Micro-action Recognition: Dataset, Methods, and ApplicationsCode1
Temporal Relations of Informative Frames in Action RecognitionCode0
Video Relationship Detection Using Mixture of ExpertsCode0
Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action RecognitionCode1
A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation—0
Show:102550
← PrevPage 8 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