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 2701–2750 of 2759 papers

TitleStatusHype
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset—0
Feature and Region Selection for Visual Learning—0
A Hierarchical Context Model for Event Recognition in Surveillance Video—0
Human Action Recognition by Representing 3D Skeletons as Points in a Lie GroupCode0
Log-Euclidean Bag of Words for Human Action Recognition—0
Robust Estimation of 3D Human Poses from a Single Image—0
Two-Stream Convolutional Networks for Action Recognition in VideosCode0
Continuous Action Recognition Based on Sequence Alignment—0
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition—0
3D Pose from Motion for Cross-view Action Recognition via Non-linear Circulant Temporal EncodingCode0
Human Action Recognition Based on Context-Dependent Graph Kernels—0
Unsupervised Spectral Dual Assignment Clustering of Human Actions in Context—0
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition—0
Range-Sample Depth Feature for Action Recognition—0
Simplex-Based 3D Spatio-Temporal Feature Description for Action Recognition—0
Human Action Recognition Across Datasets by Foreground-weighted Histogram Decomposition—0
Multi-View Super Vector for Action Recognition—0
A Cause and Effect Analysis of Motion Trajectories for Modeling Actions—0
Efficient Nonlinear Markov Models for Human Motion—0
Depth and Skeleton Associated Action Recognition without Online Accessible RGB-D Cameras—0
Efficient Feature Extraction, Encoding and Classification for Action Recognition—0
Efficient Action Localization with Approximately Normalized Fisher Vectors—0
Towards Good Practices for Action Video Encoding—0
Feature sampling and partitioning for visual vocabulary generation on large action classification datasets—0
Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice—0
Cross-view Action Modeling, Learning and Recognition—0
From Synsets to Videos: Enriching ItalWordNet Multimodally—0
Shrinkage Optimized Directed Information using Pictorial Structures for Action Recognition—0
KPCA Spatio-temporal trajectory point cloud classifier for recognizing human actions in a CBVR system—0
Bregman Divergences for Infinite Dimensional Covariance Matrices—0
Group sparsity and geometry constrained dictionary learning for action recognition from depth maps.—0
Multiview Hessian regularized logistic regression for action recognition—0
A Hybrid Loss for Multiclass and Structured Prediction—0
Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds—0
Actions in the Eye: Dynamic Gaze Datasets and Learnt Saliency Models for Visual Recognition—0
EXMOVES: Classifier-based Features for Scalable Action Recognition—0
Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution—0
Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data—0
Seeing What You're Told: Sentence-Guided Activity Recognition In Video—0
Sparse Dictionary-based Attributes for Action Recognition and Summarization—0
An Approach to Pose-Based Action Recognition—0
Evaluation of Color STIPs for Human Action Recognition—0
3D R Transform on Spatio-temporal Interest Points for Action Recognition—0
Expanded Parts Model for Human Attribute and Action Recognition in Still Images—0
Multi-task Sparse Learning with Beta Process Prior for Action Recognition—0
Better Exploiting Motion for Better Action Recognition—0
Sampling Strategies for Real-Time Action Recognition—0
Detection of Manipulation Action Consequences (MAC)—0
Action Recognition by Hierarchical Sequence Summarization—0
Tracking Human Pose by Tracking Symmetric Parts—0
Show:102550
← PrevPage 55 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