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 2551–2600 of 2759 papers

TitleStatusHype
Temporal Action Detection Using a Statistical Language ModelCode0
Progressively Parsing Interactional Objects for Fine Grained Action Detection—0
Harnessing Object and Scene Semantics for Large-Scale Video Understanding—0
Mining 3D Key-Pose-Motifs for Action Recognition—0
VLAD3: Encoding Dynamics of Deep Features for Action Recognition—0
Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos—0
Regularizing Long Short Term Memory With 3D Human-Skeleton Sequences for Action Recognition—0
Action Classification via Concepts and Attributes—0
Going Deeper into Action Recognition: A Survey—0
Going Deeper into First-Person Activity Recognition—0
Action Recognition in Video Using Sparse Coding and Relative Features—0
Revisiting Human Action Recognition: Personalization vs. Generalization—0
Dominant Codewords Selection with Topic Model for Action Recognition—0
Improved Dense Trajectory with Cross Streams—0
Real-time Action Recognition with Enhanced Motion Vector CNNs—0
Actionness Estimation Using Hybrid Fully Convolutional Networks—0
Kernelized Covariance for Action Recognition—0
Convolutional Two-Stream Network Fusion for Video Action RecognitionCode0
Improving Human Action Recognition by Non-action Classification—0
The THUMOS Challenge on Action Recognition for Videos "in the Wild"—0
Online Human Action Detection using Joint Classification-Regression Recurrent Neural NetworksCode0
Long-term Temporal Convolutions for Action RecognitionCode0
NTU RGB+D: A Large Scale Dataset for 3D Human Activity AnalysisCode0
Trajectory Aligned Features For First Person Action Recognition—0
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding—0
Learning a Pose Lexicon for Semantic Action Recognition—0
Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (Extended Version)—0
Shuffle and Learn: Unsupervised Learning using Temporal Order Verification—0
Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks—0
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos—0
Multi-velocity neural networks for gesture recognition in videos—0
Modelling Temporal Information Using Discrete Fourier Transform for Video Classification—0
Persistent Homology of Attractors For Action Recognition—0
Learning zeroth class dictionary for human action recognition—0
Pose for Action - Action for Pose—0
Support Vector Machines with Time Series Distance Kernels for Action ClassificationCode0
Robust Multi-body Feature Tracker: A Segmentation-free Approach—0
Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation—0
Joint Recognition and Segmentation of Actions via Probabilistic Integration of Spatio-Temporal Fisher Vectors—0
Comparative Evaluation of Action Recognition Methods via Riemannian Manifolds, Fisher Vectors and GMMs: Ideal and Challenging Conditions—0
Learning a Deep Model for Human Action Recognition from Novel Viewpoints—0
Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier—0
Order-aware Convolutional Pooling for Video Based Action Recognition—0
RGB-D-based Action Recognition Datasets: A Survey—0
Face-space Action Recognition by Face-Object Interactions—0
Convolutional Architecture Exploration for Action Recognition and Image Classification—0
Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web—0
Harnessing the Deep Net Object Models for Enhancing Human Action Recognition—0
Origami: A 803 GOp/s/W Convolutional Network Accelerator—0
Action Recognition with Image Based CNN Features—0
Show:102550
← PrevPage 52 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
4InternVideoTop-1 Accuracy77.2—Unverified
5DejaVidTop-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
3OmniVec3-fold Accuracy99.6—Unverified
4VideoMAE V2-g3-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
8OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
9PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
10Text4Vis3-fold Accuracy98.2—Unverified