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 1351–1400 of 2759 papers

TitleStatusHype
RegionViT: Regional-to-Local Attention for Vision TransformersCode1
ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency—0
CT-Net: Channel Tensorization Network for Video ClassificationCode1
Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment—0
TSI: Temporal Saliency Integration for Video Action Recognition—0
A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDP—0
Inertial Sensor Data To Image Encoding For Human Action Recognition—0
The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy OptimizationCode0
The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition—0
SSAN: Separable Self-Attention Network for Video Representation Learning—0
Anticipating human actions by correlating past with the future with Jaccard similarity measures—0
GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition—0
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation LearningCode1
Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model—0
Sharing Pain: Using Pain Domain Transfer for Video Recognition of Low Grade Orthopedic Pain in HorsesCode1
Egocentric Activity Recognition and Localization on a 3D Map—0
Multimodal Fusion via Teacher-Student Network for Indoor Action RecognitionCode1
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily LivingCode1
MutualNet: Adaptive ConvNet via Mutual Learning from Different Model ConfigurationsCode1
REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition—0
Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency—0
Home Action Genome: Cooperative Compositional Action UnderstandingCode1
Unsupervised Visual Representation Learning by Tracking Patches in VideoCode1
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action RecognitionCode1
Motion-Augmented Self-Training for Video Recognition at Smaller Scale—0
An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs—0
Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities—0
CoCon: Cooperative-Contrastive LearningCode1
Action in Mind: A Neural Network Approach to Action Recognition and Segmentation—0
3D Human Action Representation Learning via Cross-View Consistency PursuitCode1
Revisiting Skeleton-based Action RecognitionCode1
Three-stream network for enriched Action Recognition—0
Modeling long-term interactions to enhance action recognition—0
3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces—0
VidTr: Video Transformer Without Convolutions—0
H2O: Two Hands Manipulating Objects for First Person Interaction Recognition—0
Multiscale Vision TransformersCode1
Hierarchical growing grid networks for skeleton based action recognitionCode0
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and TextCode1
ImageNet-21K Pretraining for the MassesCode1
Skimming and Scanning for Untrimmed Video Action Recognition—0
MGSampler: An Explainable Sampling Strategy for Video Action RecognitionCode1
Temporal Query Networks for Fine-grained Video Understanding—0
Higher Order Recurrent Space-Time Transformer for Video Action PredictionCode1
Online Recognition of Actions Involving ObjectsCode0
First and Second Order Dynamics in a Hierarchical SOM system for Action RecognitionCode0
Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition—0
Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation—0
Action-Conditioned 3D Human Motion Synthesis with Transformer VAECode1
Few-Shot Action Recognition with Compromised Metric via Optimal Transport—0
Show:102550
← PrevPage 28 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