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 2351–2400 of 2759 papers

TitleStatusHype
Summarization of User-Generated Sports Video by Using Deep Action Recognition Features—0
Human Action Forecasting by Learning Task Grammars—0
Multi-Label Zero-Shot Human Action Recognition via Joint Latent Ranking Embedding—0
Viewpoint Invariant Action Recognition using RGB-D Videos—0
Learning Gating ConvNet for Two-Stream based Methods in Action RecognitionCode0
Detecting Hands in Egocentric Videos: Towards Action Recognition—0
A Compact Kernel Approximation for 3D Action Recognition—0
Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks—0
Natural Language Descriptions for Human Activities in Video Streams—0
Two-stream Flow-guided Convolutional Attention Networks for Action RecognitionCode0
Learning Spatio-Temporal Features with 3D Residual Networks for Action RecognitionCode0
Hierarchical Multi-scale Attention Networks for Action Recognition—0
Human Action Recognition System using Good Features and Multilayer Perceptron Network—0
Recognizing Involuntary Actions from 3D Skeleton Data Using Body StatesCode0
Attentive Semantic Video Generation using CaptionsCode0
Pillar Networks++: Distributed non-parametric deep and wide networks—0
Eigen Evolution Pooling for Human Action Recognition—0
ConvNet Architecture Search for Spatiotemporal Feature LearningCode1
Fast, invariant representation for human action in the visual system—0
Lattice Long Short-Term Memory for Human Action Recognition—0
Extensible Hierarchical Method of Detecting Interactive Actions for Video Understanding—0
Attention Transfer from Web Images for Video Recognition—0
Unsupervised Representation Learning by Sorting SequencesCode0
When Kernel Methods meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data—0
Action recognition by learning pose representations—0
Enhanced skeleton visualization for view invariant human action recognition—0
Learning from Video and Text via Large-Scale Discriminative ClusteringCode0
Automatic Curation of Golf Highlights using Multimodal Excitement Features—0
Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos—0
Multi-kernel learning of deep convolutional features for action recognition—0
Discriminative convolutional Fisher vector network for action recognition—0
Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks—0
Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition—0
Skeleton-based Action Recognition Using LSTM and CNN—0
Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition—0
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action RecognitionCode0
Zero-Shot Action Recognition With Error-Correcting Output Codes—0
Spatio-Temporal Vector of Locally Max Pooled Features for Action Recognition in Videos—0
Spatiotemporal Multiplier Networks for Video Action RecognitionCode1
Temporal Residual Networks for Dynamic Scene RecognitionCode0
Multi-Task Clustering of Human Actions by Sharing Information—0
Modeling Sub-Event Dynamics in First-Person Action Recognition—0
Joint Discriminative Bayesian Dictionary and Classifier Learning—0
Binary Coding for Partial Action Analysis With Limited Observation Ratios—0
Deep Sequential Context Networks for Action Prediction—0
Global Context-Aware Attention LSTM Networks for 3D Action Recognition—0
Alternative Semantic Representations for Zero-Shot Human Action Recognition—0
Recurrent Residual Learning for Action Recognition—0
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates—0
Detekcja upadku i wybranych akcji na sekwencjach obrazów cyfrowych—0
Show:102550
← PrevPage 48 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