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 451–500 of 2759 papers

TitleStatusHype
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
Generative Model-based Feature Knowledge Distillation for Action RecognitionCode1
EZ-CLIP: Efficient Zeroshot Video Action RecognitionCode1
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
Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven ReasoningCode1
Early Action Recognition with Action Prototypes—0
Navigating Open Set Scenarios for Skeleton-based Action RecognitionCode1
DVANet: Disentangling View and Action Features for Multi-View Action RecognitionCode0
From Detection to Action Recognition: An Edge-Based Pipeline for Robot Human Perception—0
STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action RecognitionCode0
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures—0
Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-TrainingCode0
RotaTR: Detection Transformer for Dense and Rotated Object—0
Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition—0
Hulk: A Universal Knowledge Translator for Human-Centric TasksCode2
D^2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action RecognitionCode1
Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CPM^2C)Code0
DEVIAS: Learning Disentangled Video Representations of Action and SceneCode1
Action Recognition in Video Recordings from Gynecologic Laparoscopy—0
CAST: Cross-Attention in Space and Time for Video Action RecognitionCode1
Just Add π! Pose Induced Video Transformers for Understanding Activities of Daily LivingCode1
LEAP: LLM-Generation of Egocentric Action Programs—0
Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic ScenesCode1
Object-based (yet Class-agnostic) Video Domain Adaptation—0
PALM: Predicting Actions through Language Models—0
GeoDeformer: Geometric Deformable Transformer for Action Recognition—0
Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling—0
F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning—0
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition—0
REACT: Recognize Every Action Everywhere All At Once—0
Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition—0
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer LearningCode1
UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning—0
VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViGCode1
Multi-modal Instance Refinement for Cross-domain Action Recognition—0
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the ArtCode1
GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain GapCode0
Modality Mixer Exploiting Complementary Information for Multi-modal Action Recognition—0
VLM-Eval: A General Evaluation on Video Large Language Models—0
MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation—0
SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition System—0
Learning Human Action Recognition Representations Without Real HumansCode0
Semantic-aware Video Representation for Few-shot Action Recognition—0
Asymmetric Masked Distillation for Pre-Training Small Foundation ModelsCode0
FPGA-QHAR: Throughput-Optimized for Quantized Human Action Recognition on The EdgeCode0
Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition—0
Show:102550
← PrevPage 10 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