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 1601–1650 of 2759 papers

TitleStatusHype
View-invariant action recognition—0
Self-supervised Video Representation Learning by Uncovering Spatio-temporal StatisticsCode1
Online Spatiotemporal Action Detection and Prediction via Causal RepresentationsCode0
All About Knowledge Graphs for Actions—0
Effective Action Recognition with Embedded Key Point Shifts—0
A Prospective Study on Sequence-Driven Temporal Sampling and Ego-Motion Compensation for Action Recognition in the EPIC-Kitchens Dataset—0
DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 PandemicCode1
Visual Concept Reasoning Networks—0
Spatiotemporal Action Recognition in Restaurant VideosCode0
Two-Stream Networks for Lane-Change Prediction of Surrounding Vehicles—0
Decision Support for Video-based Detection of Flu Symptoms—0
Towards Improved Human Action Recognition Using Convolutional Neural Networks and Multimodal Fusion of Depth and Inertial Sensor Data—0
Multidomain Multimodal Fusion For Human Action Recognition Using Inertial Sensors—0
Object Properties Inferring from and Transfer for Human Interaction Motions—0
Accuracy and Performance Comparison of Video Action Recognition Approaches—0
ConvGRU in Fine-grained Pitching Action Recognition for Action Outcome PredictionCode0
Skeleton-based Action Recognition via Spatial and Temporal Transformer NetworksCode1
Self-supervised Video Representation Learning by Pace PredictionCode1
Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning—0
Learning Temporally Invariant and Localizable Features via Data Augmentation for Video RecognitionCode1
2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework—0
Spatiotemporal Contrastive Video Representation LearningCode1
Richly Activated Graph Convolutional Network for Robust Skeleton-based Action RecognitionCode0
PAN: Towards Fast Action Recognition via Learning Persistence of AppearanceCode1
Location-aware Graph Convolutional Networks for Video Question AnsweringCode1
Exploring Relations in Untrimmed Videos for Self-Supervised Learning—0
Self-supervised Temporal Discriminative Learning for Video Representation LearningCode1
Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognitionCode1
Graph Convolution with Low-rank Learnable Local FiltersCode1
Late Temporal Modeling in 3D CNN Architectures with BERT for Action RecognitionCode1
Recognition and 3D Localization of Pedestrian Actions from Monocular Video—0
RareAct: A video dataset of unusual interactionsCode1
Memory-augmented Dense Predictive Coding for Video Representation LearningCode1
SeCo: Exploring Sequence Supervision for Unsupervised Representation LearningCode1
Residual Frames with Efficient Pseudo-3D CNN for Human Action Recognition—0
Vision and Inertial Sensing Fusion for Human Action Recognition : A Review—0
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural NetworksCode1
Learning Actionness via Long-range Temporal Order Verification—0
Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition—0
Decoupling GCN with DropGraph Module for Skeleton-Based Action RecognitionCode1
A Recurrent Transformer Network for Novel View Action SynthesisCode0
Multi-view Action Recognition using Cross-view Video PredictionCode1
Learning Video Representations by Transforming Time—0
RubiksNet: Learnable 3D-Shift for Efficient Video Action RecognitionCode1
CoTeRe-Net: Discovering Collaborative Ternary Relations in VideosCode0
DDGCN: A Dynamic Directed Graph Convolutional Network for Action RecognitionCode1
On Dropping Clusters to Regularize Graph Convolutional Neural Networks—0
Shuffle and Attend: Video Domain Adaptation—0
Self-supervised Motion Representation via Scattering Local Motion Cues—0
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action RecognitionCode1
Show:102550
← PrevPage 33 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