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 851–900 of 2759 papers

TitleStatusHype
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens—0
Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model—0
Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion—0
FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification—0
GCF-Net: Gated Clip Fusion Network for Video Action Recognition—0
Event and Activity Recognition in Video Surveillance for Cyber-Physical Systems—0
Event-based Action Recognition Using Timestamp Image Encoding Network—0
Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation—0
Global Context-Aware Attention LSTM Networks for 3D Action Recognition—0
EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond—0
Behavior Recognition Based on the Integration of Multigranular Motion Features—0
EA-VTR: Event-Aware Video-Text Retrieval—0
AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos—0
Early Action Recognition with Action Prototypes—0
EventTransAct: A video transformer-based framework for Event-camera based action recognition—0
Event Transformer+. A multi-purpose solution for efficient event data processing—0
Bayesian Non-Parametric Inference for Manifold Based MoCap Representation—0
Bypass Enhancement RGB Stream Model for Pedestrian Action Recognition of Autonomous Vehicles—0
FSD-10: A Dataset for Competitive Sports Content Analysis—0
EAGLE: Egocentric AGgregated Language-video Engine—0
Evolving Losses for Unsupervised Video Representation Learning—0
Evolving Skeletons: Motion Dynamics in Action Recognition—0
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition—0
DynamoNet: Dynamic Action and Motion Network—0
Examining Interpretable Feature Relationships in Deep Networks for Action recognition—0
CAMREP- Concordia Action and Motion Repository—0
EXMOVES: Classifier-based Features for Scalable Action Recognition—0
Egocentric and Exocentric Methods: A Short Survey—0
Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition—0
MultiFuser: Multimodal Fusion Transformer for Enhanced Driver Action Recognition—0
Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition—0
Canonical Correlation Analysis for Misaligned Satellite Image Change Detection—0
Fully-Coupled Two-Stream Spatiotemporal Networks for Extremely Low Resolution Action Recognition—0
Exploiting deep residual networks for human action recognition from skeletal data—0
Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition—0
Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition—0
Exploiting Spatial-Temporal Modelling and Multi-Modal Fusion for Human Action Recognition—0
Exploiting Structure Sparsity for Covariance-based Visual Representation—0
Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks—0
Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition—0
Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition—0
Dynamic Sampling Networks for Efficient Action Recognition in Videos—0
Exploring Missing Modality in Multimodal Egocentric Datasets—0
CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition—0
Exploring Relations in Untrimmed Videos for Self-Supervised Learning—0
Exploring Sub-Pseudo Labels for Learning from Weakly-Labeled Web Videos—0
Cascaded Interactional Targeting Network for Egocentric Video Analysis—0
Exploring the Impact of Hand Pose and Shadow on Hand-washing Action Recognition—0
CASPER: Cognitive Architecture for Social Perception and Engagement in Robots—0
Dynamic Probabilistic Network Based Human Action Recognition—0
Show:102550
← PrevPage 18 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
2OmniVec3-fold Accuracy99.6—Unverified
3VideoMAE V2-g3-fold Accuracy99.6—Unverified
4OmniVec23-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
8PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
9OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
10Text4Vis3-fold Accuracy98.2—Unverified