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 2451–2500 of 2759 papers

TitleStatusHype
SMART: Scene-motion-aware human action recognition framework for mental disorder groupCode0
The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain AdaptationCode0
Out-of-Distribution Detection for Generalized Zero-Shot Action RecognitionCode0
Learn to cycle: Time-consistent feature discovery for action recognitionCode0
Action Recognition with Dynamic Image NetworksCode0
Unsupervised Domain Adaptation for Video Transformers in Action RecognitionCode0
ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked AutoencodersCode0
Learning with privileged information via adversarial discriminative modality distillationCode0
SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action RecognitionCode0
Exploring Modulated Detection Transformer as a Tool for Action Recognition in VideosCode0
Learning Visual Actions Using Multiple Verb-Only LabelsCode0
Learning Video Representations from Correspondence ProposalsCode0
Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding ManifoldCode0
Learning To Score Olympic EventsCode0
Part-based Graph Convolutional Network for Action RecognitionCode0
Action Recognition Based on Optimal Joint Selection and Discriminative Depth DescriptorCode0
Explaining NonLinear Classification Decisions with Deep Taylor DecompositionCode0
Path Signatures on Lie GroupsCode0
Collaborative Spatiotemporal Feature Learning for Video Action RecognitionCode0
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction NetworksCode0
Collaborative Spatio-temporal Feature Learning for Video Action RecognitionCode0
Sound Bridge: Associating Egocentric and Exocentric Videos via Audio CuesCode0
Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative MeasuresCode0
Excitation Backprop for RNNsCode0
Coarse or Fine? Recognising Action End States without LabelsCode0
Every Moment Counts: Dense Detailed Labeling of Actions in Complex VideosCode0
Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event StreamsCode0
A New Split for Evaluating True Zero-Shot Action RecognitionCode0
CNN based Multistage Gated Average Fusion (MGAF) for Human Action Recognition Using Depth and Inertial SensorsCode0
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints InvarianceCode0
PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical InstructionCode0
Sparse Covariance Neural NetworksCode0
Class Feature Pyramids for Video ExplanationCode0
3D CNNs on Distance Matrices for Human Action RecognitionCode0
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and DetectionCode0
Learning to Estimate Pose by Watching VideosCode0
Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action RecognitionCode0
PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action RecognitionCode0
Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action RecognitionCode0
Learning Spatio-Temporal Representation with Local and Global DiffusionCode0
Boosting Few-shot Action Recognition with Graph-guided Hybrid MatchingCode0
Learning Spatio-Temporal Features with 3D Residual Networks for Action RecognitionCode0
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTMCode0
Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action RecognitionCode0
Event-based Vision for Early Prediction of Manipulation ActionsCode0
EVA: Exploring the Limits of Masked Visual Representation Learning at ScaleCode0
Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action RecognitionCode0
Pose And Joint-Aware Action RecognitionCode0
Boosting Adversarial Transferability across Model Genus by Deformation-Constrained WarpingCode0
Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action RecognitionCode0
Show:102550
← PrevPage 50 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