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 901–950 of 2759 papers

TitleStatusHype
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition—0
Extensible Hierarchical Method of Detecting Interactive Actions for Video Understanding—0
DynamoNet: Dynamic Action and Motion Network—0
Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds—0
Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition—0
F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning—0
MultiFuser: Multimodal Fusion Transformer for Enhanced Driver Action Recognition—0
FACTS: Fine-Grained Action Classification for Tactical Sports—0
Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain—0
FASTER Recurrent Networks for Efficient Video Classification—0
Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition—0
Fast, invariant representation for human action in the visual system—0
Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition—0
Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos—0
Dynamic Sampling Networks for Efficient Action Recognition in Videos—0
FBK-HUPBA Submission to the EPIC-Kitchens Action Recognition 2020 Challenge—0
Dynamic Probabilistic Network Based Human Action Recognition—0
Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization—0
Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter—0
Feature Hallucination for Self-supervised Action Recognition—0
Featureless: Bypassing feature extraction in action categorization—0
Feature sampling and partitioning for visual vocabulary generation on large action classification datasets—0
Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019—0
Channel-Temporal Attention for First-Person Video Domain Adaptation—0
Graph Based Skeleton Modeling for Human Activity Analysis—0
Federated Action Recognition on Heterogeneous Embedded Devices—0
Dynamic Matrix Decomposition for Action Recognition—0
Dynamic Inference: A New Approach Toward Efficient Video Action Recognition—0
Graph Convolutional Module for Temporal Action Localization in Videos—0
Graph learning in robotics: a survey—0
Chop & Learn: Recognizing and Generating Object-State Compositions—0
Few-shot Action Recognition via Intra- and Inter-Video Information Maximization—0
Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice—0
Few-Shot Action Recognition with Compromised Metric via Optimal Transport—0
Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition—0
Adversarial Domain Adaptation for Action Recognition Around the Clock—0
Few Shot Activity Recognition Using Variational Inference—0
Analysis of Real-Time Hostile Activitiy Detection from Spatiotemporal Features Using Time Distributed Deep CNNs, RNNs and Attention-Based Mechanisms—0
Few-Shot Video Classification via Temporal Alignment—0
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition—0
FILS: Self-Supervised Video Feature Prediction In Semantic Language Space—0
fine-CLIP: Enhancing Zero-Shot Fine-Grained Surgical Action Recognition with Vision-Language Models—0
Knowledge Distillation for Human Action Anticipation—0
Gradient Weighted Superpixels for Interpretability in CNNs—0
Fine-grained activity recognition for assembly videos—0
Class-Incremental Learning for Action Recognition in Videos—0
Fine-grained Multi-Modal Self-Supervised Learning—0
Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition—0
Fine-grained Video Categorization with Redundancy Reduction Attention—0
Dynamic Appearance: A Video Representation for Action Recognition with Joint Training—0
Show:102550
← PrevPage 19 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