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 1751–1800 of 2759 papers

TitleStatusHype
Can We Learn Heuristics For Graphical Model Inference Using Reinforcement Learning?—0
Audio-Visual Instance Discrimination with Cross-Modal AgreementCode1
SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action RecognitionCode1
Action recognition in real-world videos—0
Human and Machine Action Prediction Independent of Object Information—0
TAEN: Temporal Aware Embedding Network for Few-Shot Action Recognition—0
Combining Deep Learning Classifiers for 3D Action Recognition—0
Spatio-Temporal Dual Affine Differential Invariant for Skeleton-based Action Recognition—0
FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding—0
SpeedNet: Learning the Speediness in VideosCode1
Spatiotemporal Fusion in 3D CNNs: A Probabilistic View—0
ASL Recognition with Metric-Learning based Lightweight Network—0
Improved Residual Networks for Image and Video RecognitionCode1
Temporal Pyramid Network for Action RecognitionCode1
What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition—0
Human action recognition with a large-scale brain-inspired photonic computer—0
A Local-to-Global Approach to Multi-modal Movie Scene SegmentationCode1
Deep Multimodal Feature Encoding for Video OrderingCode1
Conquering the cnn over-parameterization dilemma: A volterra filtering approach for action recognitionCode1
TEA: Temporal Excitation and Aggregation for Action RecognitionCode1
Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention—0
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action RecognitionCode1
Speech2Action: Cross-modal Supervision for Action Recognition—0
Omni-sourced Webly-supervised Learning for Video RecognitionCode2
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D NetworksCode1
Action Localization through Continual Predictive Learning—0
Modeling Cross-view Interaction Consistency for Paired Egocentric Interaction Recognition—0
Ensembles of Deep Neural Networks for Action Recognition in Still Images—0
Temporally Coherent Embeddings for Self-Supervised Video Representation LearningCode1
Temporal Extension Module for Skeleton-Based Action Recognition—0
STH: Spatio-Temporal Hybrid Convolution for Efficient Action Recognition—0
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action RecognitionCode1
Feedback Graph Convolutional Network for Skeleton-based Action Recognition—0
Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos—0
Gimme Signals: Discriminative signal encoding for multimodal activity recognitionCode1
Skeleton Based Action Recognition using a Stacked Denoising Autoencoder with Constraints of Privileged Information—0
Top-1 Solution of Multi-Moments in Time Challenge 2019Code1
Beyond the Camera: Neural Networks in World Coordinates—0
On Compositions of Transformations in Contrastive Self-Supervised LearningCode1
Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition—0
Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a VideoCode0
The iCub multisensor datasets for robot and computer vision applications—0
Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition—0
Infrared and 3D skeleton feature fusion for RGB-D action recognitionCode1
Evolving Losses for Unsupervised Video Representation Learning—0
Human Action Recognition using Local Two-Stream Convolution Neural Network Features and Support Vector Machines—0
Knowledge Integration Networks for Action Recognition—0
A Survey on 3D Skeleton-Based Action Recognition Using Learning Method—0
Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition—0
Learning spatio-temporal representations with temporal squeeze pooling—0
Show:102550
← PrevPage 36 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