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 1551–1600 of 2759 papers

TitleStatusHype
Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach—0
Towards Physical World Backdoor Attacks against Skeleton Action Recognition—0
Towards Real-Time Action Recognition on Mobile Devices Using Deep Models—0
Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition—0
Towards Scalable Neural Representation for Diverse Videos—0
Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition—0
Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition—0
Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition—0
Towards Universal Representation for Unseen Action Recognition—0
Tracking Human Pose by Tracking Symmetric Parts—0
Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition—0
Training for temporal sparsity in deep neural networks, application in video processing—0
Trajectory Aligned Features For First Person Action Recognition—0
Trajectory-aligned Space-time Tokens for Few-shot Action Recognition—0
Trajectory Convolution for Action Recognition—0
Transductive Universal Transport for Zero-Shot Action Recognition—0
Transductive Zero-Shot Action Recognition by Word-Vector Embedding—0
Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition—0
Transformed ROIs for Capturing Visual Transformations in Videos—0
Transformer-based Action recognition in hand-object interacting scenarios—0
Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition—0
Transformers in Action Recognition: A Review on Temporal Modeling—0
Transformers in Vision: A Survey—0
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection—0
TransNet: A Transfer Learning-Based Network for Human Action Recognition—0
Trear: Transformer-based RGB-D Egocentric Action Recognition—0
T-RECS: Training for Rate-Invariant Embeddings by Controlling Speed for Action Recognition—0
Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019—0
Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition—0
TSI: Temporal Saliency Integration for Video Action Recognition—0
TTPOINT: A Tensorized Point Cloud Network for Lightweight Action Recognition with Event Cameras—0
Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition—0
Two-stream joint matching method based on contrastive learning for few-shot action recognition—0
Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition—0
Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition—0
Two-Stream Networks for Lane-Change Prediction of Surrounding Vehicles—0
Two-Stream Region Convolutional 3D Network for Temporal Activity Detection—0
Two-Stream RNN/CNN for Action Recognition in 3D Videos—0
Two Stream Self-Supervised Learning for Action Recognition—0
Two-stream Spatiotemporal Feature for Video QA Task—0
Two-Stream Transformer Architecture for Long Video Understanding—0
Two-Stream Video Classification with Cross-Modality Attention—0
UC Merced Submission to the ActivityNet Challenge 2016—0
Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos—0
Uncertainty-Guided Probabilistic Transformer for Complex Action Recognition—0
Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models—0
Understanding Ethics, Privacy, and Regulations in Smart Video Surveillance for Public Safety—0
Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network—0
Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models—0
Understanding Video Transformers via Universal Concept Discovery—0
Show:102550
← PrevPage 32 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