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 1951–2000 of 2759 papers

TitleStatusHype
Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks—0
Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation—0
Context-Gated ConvolutionCode0
Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models—0
Interaction Relational Network for Mutual Action RecognitionCode0
Cross-modal knowledge distillation for action recognition—0
Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision SensingCode0
Compressed Video Action Recognition with Refined Motion Vector—0
Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction—0
Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition—0
Order-Preserving Wasserstein Discriminant Analysis—0
Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles—0
AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos—0
View-LSTM: Novel-View Video Synthesis Through View Decomposition—0
Generative Multi-View Human Action Recognition—0
MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding—0
Spatio-Temporal FAST 3D Convolutions for Human Action Recognition—0
Grouped Spatial-Temporal Aggregation for Efficient Action RecognitionCode0
Discriminability Distillation in Group Representation Learning—0
Learning deep representations for video-based intake gesture detectionCode0
Learning Coupled Spatial-temporal Attention for Skeleton-based Action Recognition—0
Making the Invisible Visible: Action Recognition Through Walls and Occlusions—0
Target-Specific Action Classification for Automated Assessment of Human Motor Behavior from Video—0
Class Feature Pyramids for Video ExplanationCode0
Multiple Human Tracking using Multi-Cues including Primitive Action FeaturesCode0
Global Temporal Representation based CNNs for Infrared Action Recognition—0
Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition—0
ProtoGAN: Towards Few Shot Learning for Action Recognition—0
Deep Point-wise Prediction for Action Temporal ProposalCode0
Multitask Learning to Improve Egocentric Action Recognition—0
X-ToM: Explaining with Theory-of-Mind for Gaining Justified Human Trust—0
Adversarial Attack on Skeleton-based Human Action Recognition—0
Metric-Based Few-Shot Learning for Video Action Recognition—0
Zero-Shot Action Recognition in Videos: A Survey—0
MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition—0
Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference JointsCode0
Comparative Analysis of CNN-based Spatiotemporal Reasoning in VideosCode0
Video Representation Learning by Dense Predictive CodingCode0
Multi-Modal Three-Stream Network for Action Recognition—0
Discriminative Video Representation Learning Using Support Vector Classifiers—0
Tensor Analysis with n-Mode Generalized Difference SubspaceCode0
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks—0
Riemannian batch normalization for SPD neural networks—0
DWnet: Deep-Wide Network for 3D Action Recognition—0
Temporal Reasoning Graph for Activity Recognition—0
Mobile Video Action Recognition—0
Cooperative Cross-Stream Network for Discriminative Action Representation—0
Graph Based Skeleton Modeling for Human Activity Analysis—0
Non-local Recurrent Neural Memory for Supervised Sequence Modeling—0
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action RecognitionCode0
Show:102550
← PrevPage 40 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