SOTAVerified

Activity Recognition

Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.

Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 651–675 of 1322 papers

TitleStatusHype
Multiscale Manifold Warping—0
Multi-Scale Supervised Network for Human Pose Estimation—0
Multi-Stage Based Feature Fusion of Multi-Modal Data for Human Activity Recognition—0
Multi-stage RGB-based Transfer Learning Pipeline for Hand Activity Recognition—0
Multi-task Self-Supervised Learning for Human Activity Detection—0
Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures—0
Multi-Type Activity Recognition in Robot-Centric Scenarios—0
Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition—0
Ensemble Learning for Fusion of Multiview Vision with Occlusion and Missing Information: Framework and Evaluations with Real-World Data and Applications in Driver Hand Activity Recognition—0
Multi-View Fusion Transformer for Sensor-Based Human Activity Recognition—0
MU-MAE: Multimodal Masked Autoencoders-Based One-Shot Learning—0
MuMu: Cooperative Multitask Learning-based Guided Multimodal Fusion—0
MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation—0
Natively neuromorphic LMU architecture for encoding-free SNN-based HAR on commercial edge devices—0
Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition—0
NERULA: A Dual-Pathway Self-Supervised Learning Framework for Electrocardiogram Signal Analysis—0
Nested Motion Descriptors—0
Neural Style Transfer Enhanced Training Support For Human Activity Recognition—0
Neuro-Symbolic Approaches for Context-Aware Human Activity Recognition—0
New Convex Relaxations for MRF Inference With Unknown Graphs—0
Non-Linear Temporal Subspace Representations for Activity Recognition—0
Non-local Graph Convolutional Network for joint Activity Recognition and Motion Prediction—0
Non-stationary BERT: Exploring Augmented IMU Data For Robust Human Activity Recognition—0
Novel evaluation of surgical activity recognition models using task-based efficiency metrics—0
Nuisance-Label Supervision: Robustness Improvement by Free Labels—0
Show:102550
← PrevPage 27 of 53Next →
All datasetsRWF-2000Stanford40First-Person Hand Action BenchmarkSelf-stimulatory Behavior Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Structured Keypoint PoolingAccuracy93.4—Unverified
2Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics datasetAccuracy90.4—Unverified
3Human Skeletons + Change DetectionAccuracy90.25—Unverified
4Separable Convolutional LSTMAccuracy89.75—Unverified
5SPIL ConvolutionAccuracy89.3—Unverified
6Flow Gated NetworkAccuracy87.25—Unverified
#ModelMetricClaimedVerifiedStatus
1FocusCLIPTop-3 Accuracy (%)10.47—Unverified
2CLIPTop-3 Accuracy (%)6.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Boutaleb et al.1:1 Accuracy97.91—Unverified
#ModelMetricClaimedVerifiedStatus
1all-landmark-modelActivity Recognition0.76—Unverified