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 1–50 of 2759 papers

TitleStatusHype
A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains—0
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature AlignmentCode1
EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception—0
Feature Hallucination for Self-supervised Action Recognition—0
CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition—0
Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition—0
Adapting Vision-Language Models for Evaluating World Models—0
Active Multimodal Distillation for Few-shot Action Recognition—0
Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation—0
An Effective End-to-End Solution for Multimodal Action Recognition—0
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person ScenariosCode0
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding—0
EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language modelsCode1
A Review on Coarse to Fine-Grained Animal Action Recognition—0
3D Skeleton-Based Action Recognition: A Review—0
EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity UnderstandingCode1
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action RecognitionCode0
The Role of Video Generation in Enhancing Data-Limited Action Understanding—0
PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical InstructionCode0
Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action RecognitionCode0
Leveraging Foundation Models for Multimodal Graph-Based Action Recognition—0
Egocentric Action-aware Inertial Localization in Point CloudsCode0
Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?Code0
Mission Balance: Generating Under-represented Class Samples using Video Diffusion ModelsCode0
Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection—0
A Short Overview of Multi-Modal Wi-Fi Sensing—0
Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action RecognitionCode0
DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person RecognitionCode0
Direct Motion Models for Assessing Generated Videos—0
Talk is Not Always Cheap: Promoting Wireless Sensing Models with Text PromptsCode0
Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization—0
Are you SURE? Enhancing Multimodal Pretraining with Missing Modalities through Uncertainty Estimation—0
PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition—0
SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature AggregationCode1
H-MoRe: Learning Human-centric Motion Representation for Action AnalysisCode0
Knowledge Distillation for Multimodal Egocentric Action Recognition Robust to Missing Modalities—0
Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach—0
Temporal Alignment-Free Video Matching for Few-shot Action RecognitionCode1
MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor FusionCode0
MultiTSF: Transformer-based Sensor Fusion for Human-Centric Multi-view and Multi-modal Action Recognition—0
LSC-ADL: An Activity of Daily Living (ADL)-Annotated Lifelog Dataset Generated via Semi-Automatic Clustering—0
Is Temporal Prompting All We Need For Limited Labeled Action Recognition?—0
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition—0
OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition—0
Action Recognition in Real-World Ambient Assisted Living EnvironmentCode0
ForcePose: A Deep Learning Approach for Force Calculation Based on Action Recognition Using MediaPipe Pose Estimation Combined with Object Detection—0
Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language RecognitionCode1
fine-CLIP: Enhancing Zero-Shot Fine-Grained Surgical Action Recognition with Vision-Language Models—0
Surg-3M: A Dataset and Foundation Model for Perception in Surgical SettingsCode2
LLaVAction: evaluating and training multi-modal large language models for action recognitionCode2
Show:102550
← PrevPage 1 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