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 1101–1150 of 2759 papers

TitleStatusHype
Action in Mind: A Neural Network Approach to Action Recognition and Segmentation—0
Differential Recurrent Neural Networks for Action Recognition—0
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition—0
Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution—0
AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition—0
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs—0
InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models—0
DevNet: A Deep Event Network for Multimedia Event Detection and Evidence Recounting—0
AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos—0
Developing Motion Code Embedding for Action Recognition in Videos—0
ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition—0
2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework—0
Detekcja upadku i wybranych akcji na sekwencjach obrazów cyfrowych—0
Detection of Manipulation Action Consequences (MAC)—0
Audio-Visual Contrastive Learning with Temporal Self-Supervision—0
Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition—0
Self-supervised Contrastive Learning for Audio-Visual Action Recognition—0
Adaptive RNN Tree for Large-Scale Human Action Recognition—0
A Two-stream Neural Network for Pose-based Hand Gesture Recognition—0
Detecting Hands in Egocentric Videos: Towards Action Recognition—0
Adaptive Recursive Circle Framework for Fine-grained Action Recognition—0
Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition—0
A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories—0
Informed Democracy: Voting-based Novelty Detection for Action Recognition—0
Integrating Audio Narrations to Strengthen Domain Generalization in Multimodal First-Person Action Recognition—0
Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks—0
Attributes' Importance for Zero-Shot Pose-Classification Based on Wearable Sensors—0
Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps—0
Depth and Skeleton Associated Action Recognition without Online Accessible RGB-D Cameras—0
Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition—0
Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections—0
Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition—0
Density-Guided Label Smoothing for Temporal Localization of Driving Actions—0
Attentive Action and Context Factorization—0
DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition—0
Delving Into Egocentric Actions—0
Attention Transfer from Web Images for Video Recognition—0
Delta Sampling R-BERT for limited data and low-light action recognition—0
Attention Spiking Neural Networks—0
Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics—0
Inertial Sensor Data To Image Encoding For Human Action Recognition—0
Deformable Tube Network for Action Detection in Videos—0
Attention-Oriented Action Recognition for Real-Time Human-Robot Interaction—0
Defending Multimodal Fusion Models against Single-Source Adversaries—0
Deep-VFX: Deep Action Recognition Driven VFX for Short Video—0
Adaptive Down-Sampling and Dimension Reduction in Time Elastic Kernel Machines for Efficient Recognition of Isolated Gestures—0
Inferring Temporal Compositions of Actions Using Probabilistic Automata—0
Deep-Temporal LSTM for Daily Living Action Recognition—0
Deep Spatio-temporal Manifold Network for Action Recognition—0
Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition—0
Show:102550
← PrevPage 23 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