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 2201–2250 of 2759 papers

TitleStatusHype
O-TALC: Steps Towards Combating Oversegmentation within Online Action Segmentation—0
OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition—0
PA3D: Pose-Action 3D Machine for Video Recognition—0
Pairwise Linear Regression Classification for Image Set Retrieval—0
Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition—0
Parallel Separable 3D Convolution for Video and Volumetric Data Understanding—0
Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition—0
Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework—0
Path-adaptive Spatio-Temporal State Space Model for Event-based Recognition with Arbitrary Duration—0
Attention Distillation for Learning Video Representations—0
PBADet: A One-Stage Anchor-Free Approach for Part-Body Association—0
PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition—0
P-CNN: Pose-based CNN Features for Action Recognition—0
Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints—0
Peer-to-Peer Federated Continual Learning for Naturalistic Driving Action Recognition—0
PERF-Net: Pose Empowered RGB-Flow Net—0
Per-Sample Kernel Adaptation for Visual Recognition and Grouping—0
Persistent Homology of Attractors For Action Recognition—0
PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition—0
PGCN-TCA: Pseudo Graph Convolutional Network With Temporal and Channel-Wise Attention for Skeleton-Based Action Recognition—0
Phase Space Reconstruction Network for Lane Intrusion Action Recognition—0
Physical Adversarial Attacks for Surveillance: A Survey—0
PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos—0
Pillar Networks++: Distributed non-parametric deep and wide networks—0
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding—0
PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities—0
PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition—0
Point3D: tracking actions as moving points with 3D CNNs—0
Poisson Kernel Avoiding Self-Smoothing in Graph Convolutional Networks—0
PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition—0
PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition—0
Pooling the Convolutional Layers in Deep ConvNets for Action Recognition—0
PoseAction: Action Recognition for Patients in the Ward using Deep Learning Approaches—0
Pose-based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation—0
Pose-Based Two-Stream Relational Networks for Action Recognition in Videos—0
Pose-conditioned Spatio-Temporal Attention for Human Action Recognition—0
Pose Encoding for Robust Skeleton-Based Action Recognition—0
PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos—0
Pose for Action - Action for Pose—0
Pose from Action: Unsupervised Learning of Pose Features based on Motion—0
Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition—0
Pose-guided multi-task video transformer for driver action recognition—0
Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition—0
PoseViNet: Distracted Driver Action Recognition Framework Using Multi-View Pose Estimation and Vision Transformer—0
Position and Orientation-Aware One-Shot Learning for Medical Action Recognition from Signal Data—0
PoTion: Pose MoTion Representation for Action Recognition—0
Predictive Coding Networks Meet Action Recognition—0
Predictive Learning: Using Future Representation Learning Variantial Autoencoder for Human Action Prediction—0
PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition—0
Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition—0
Show:102550
← PrevPage 45 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