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 2501–2550 of 2759 papers

TitleStatusHype
Image and Video Mining through Online Learning—0
Image-based human re-identification: Which covariates are actually (the most) important?—0
Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition—0
Improved Dense Trajectory with Cross Streams—0
Improving Zero-Shot Action Recognition using Human Instruction with Text Description—0
Improving Human Action Recognition by Non-action Classification—0
Improving Interpretability of Deep Neural Networks with Semantic Information—0
Improving performance of recurrent neural network with relu nonlinearity—0
Improving Skeleton-based Action Recognitionwith Robust Spatial and Temporal Features—0
Accelerating temporal action proposal generation via high performance computing—0
Improving the Multi-label Atomic Activity Recognition by Robust Visual Feature and Advanced Attention @ ROAD++ Atomic Activity Recognition 2024—0
Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds—0
Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition—0
Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments—0
Independent Sign Language Recognition with 3D Body, Hands, and Face Reconstruction—0
IndGIC: Supervised Action Recognition under Low Illumination—0
Inductive Attention for Video Action Anticipation—0
Inertial Sensor Data To Image Encoding For Human Action Recognition—0
Inferring Temporal Compositions of Actions Using Probabilistic Automata—0
Information Elevation Network for Fast Online Action Detection—0
Informed Democracy: Voting-based Novelty Detection for Action Recognition—0
InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models—0
Integrating Audio Narrations to Strengthen Domain Generalization in Multimodal First-Person Action Recognition—0
Intelligent 3D Network Protocol for Multimedia Data Classification using Deep Learning—0
Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition—0
Interaction Part Mining: A Mid-Level Approach for Fine-Grained Action Recognition—0
Interactive Generation of Laparoscopic Videos with Diffusion Models—0
Interactive Prototype Learning for Egocentric Action Recognition—0
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation—0
Interpretable Action Recognition on Hard to Classify Actions—0
Interpretable Deep Feature Propagation for Early Action Recognition—0
Interpretable Spatio-temporal Attention for Video Action Recognition—0
In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person Video—0
In the Eye of the Beholder: Gaze and Actions in First Person Video—0
Intra- and Inter-Action Understanding via Temporal Action Parsing—0
Invariant 3D Shape Recognition using Predictive Modular Neural Networks—0
Invariant recognition drives neural representations of action sequences—0
Investigation on Combining 3D Convolution of Image Data and Optical Flow to Generate Temporal Action Proposals—0
Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder—0
Is end-to-end learning enough for fitness activity recognition?—0
Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates—0
Is Temporal Prompting All We Need For Limited Labeled Action Recognition?—0
JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition—0
Joint Action Recognition and Pose Estimation From Video—0
Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition—0
Joint Denoising / Compression of Image Contours via Shape Prior and Context Tree—0
Joint Discriminative Bayesian Dictionary and Classifier Learning—0
Self-Supervised Joint Encoding of Motion and Appearance for First Person Action Recognition—0
Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition—0
Joint learning of images and videos with a single Vision Transformer—0
Show:102550
← PrevPage 51 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