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 801–850 of 2759 papers

TitleStatusHype
DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition—0
Advancing Compressed Video Action Recognition through Progressive Knowledge DistillationCode0
Mask and Compress: Efficient Skeleton-based Action Recognition in Continual LearningCode0
Expressive Keypoints for Skeleton-based Action Recognition via Skeleton TransformationCode0
Using joint angles based on the international biomechanical standards for human action recognition and related tasks—0
Dark Transformer: A Video Transformer for Action Recognition in the Dark—0
SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition—0
Exploring the Impact of Hand Pose and Shadow on Hand-washing Action Recognition—0
CM2-Net: Continual Cross-Modal Mapping Network for Driver Action Recognition—0
Brain-inspired Computational Modeling of Action Recognition with Recurrent Spiking Neural Networks Equipped with Reinforcement Delay Learning—0
Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild—0
ALGO: Object-Grounded Visual Commonsense Reasoning for Open-World Egocentric Action Recognition—0
SMART: Scene-motion-aware human action recognition framework for mental disorder groupCode0
Enhancing human action recognition with GAN-based data augmentationCode0
FILS: Self-Supervised Video Feature Prediction In Semantic Language Space—0
Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and BeyondCode0
DL-KDD: Dual-Light Knowledge Distillation for Action Recognition in the Dark—0
Contrastive Language Video Time Pre-training—0
ELSA: Evaluating Localization of Social Activities in Urban Streets using Open-Vocabulary Detection—0
Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models—0
RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model—0
An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition—0
HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model—0
Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action DetectionCode0
Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation LearningCode0
From Forest to Zoo: Great Ape Behavior Recognition with ChimpBehaveCode0
Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition—0
Matrix Manifold Neural Networks++—0
Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservation—0
Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions—0
A Cross-Dataset Study for Text-based 3D Human Motion Retrieval—0
Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion PerceptionCode0
Enhanced Spatiotemporal Prediction Using Physical-guided And Frequency-enhanced Recurrent Neural Networks—0
MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models—0
From CNNs to Transformers in Multimodal Human Action Recognition: A Survey—0
Counterfactual Gradients-based Quantification of Prediction Trust in Neural NetworksCode0
Identity-free Artificial Emotional Intelligence via Micro-Gesture Understanding—0
The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks—0
Coarse or Fine? Recognising Action End States without LabelsCode0
PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition—0
A Survey on Backbones for Deep Video Action Recognition—0
JOSENet: A Joint Stream Embedding Network for Violence Detection in Surveillance VideosCode0
MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition—0
Multi-view Action Recognition via Directed Gromov-Wasserstein Discrepancy—0
Cross-Block Fine-Grained Semantic Cascade for Skeleton-Based Sports Action Recognition—0
Enhancing Action Recognition from Low-Quality Skeleton Data via Part-Level Knowledge Distillation—0
Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognition—0
An Improved Graph Pooling Network for Skeleton-Based Action Recognition—0
Combating Missing Modalities in Egocentric Videos at Test Time—0
Driver Activity Classification Using Generalizable Representations from Vision-Language Models—0
Show:102550
← PrevPage 17 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