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 1001–1050 of 2759 papers

TitleStatusHype
Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification—0
Fusing Hand and Body Skeletons for Human Action Recognition in Assembly—0
Fusing multiple features for depth-based action recognition—0
C3T: Cross-modal Transfer Through Time for Sensor-based Human Activity Recognition—0
Adversarial Bone Length Attack on Action Recognition—0
FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification—0
BabyNet: A Lightweight Network for Infant Reaching Action Recognition in Unconstrained Environments to Support Future Pediatric Rehabilitation Applications—0
A3D: Adaptive 3D Networks for Video Action Recognition—0
ActAR: Actor-Driven Pose Embeddings for Video Action Recognition—0
Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition—0
Comparative Evaluation of Action Recognition Methods via Riemannian Manifolds, Fisher Vectors and GMMs: Ideal and Challenging Conditions—0
Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision—0
GCF-Net: Gated Clip Fusion Network for Video Action Recognition—0
DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition—0
Hierarchical Graph Convolutional Skeleton Transformer for Action Recognition—0
Optimized Skeleton-based Action Recognition via Sparsified Graph Regression—0
Driver Activity Classification Using Generalizable Representations from Vision-Language Models—0
Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data—0
Actionness-Assisted Recognition of Actions—0
Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models—0
Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling—0
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition—0
How Object Information Improves Skeleton-based Human Action Recognition in Assembly Tasks—0
Human Action Recognition and Assessment via Deep Neural Network Self-Organization—0
Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles—0
AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning—0
Down-Sampling coupled to Elastic Kernel Machines for Efficient Recognition of Isolated Gestures—0
Dominant Codewords Selection with Topic Model for Action Recognition—0
Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers—0
Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition—0
AVT: Audio-Video Transformer for Multimodal Action Recognition—0
Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition—0
Domain Generalization: A Survey—0
Adversarial Attack on Skeleton-based Human Action Recognition—0
Action Machine: Rethinking Action Recognition in Trimmed Videos—0
Action Localization through Continual Predictive Learning—0
Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web—0
DOAD: Decoupled One Stage Action Detection Network—0
DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition—0
DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition—0
A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition—0
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition—0
3D Action Recognition From Novel Viewpoints—0
Histogram of Oriented Principal Components for Cross-View Action Recognition—0
Hollywood 3D: Recognizing Actions in 3D Natural Scenes—0
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding—0
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition—0
DL-KDD: Dual-Light Knowledge Distillation for Action Recognition in the Dark—0
Advances in Human Action Recognition: A Survey—0
DIY Human Action Data Set Generation—0
Show:102550
← PrevPage 21 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