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 1301–1322 of 1322 papers

TitleStatusHype
Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition—0
DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization—0
DIVERSIFY to Generalize: Learning Generalized Representations for Time Series Classification—0
DNN Transfer Learning from Diversified Micro-Doppler for Motion Classification—0
Domain Adaptation for Inertial Measurement Unit-based Human Activity Recognition: A Survey—0
Domain-Adversarial Anatomical Graph Networks for Cross-User Human Activity Recognition—0
Domain Generalization for Activity Recognition via Adaptive Feature Fusion—0
Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition—0
Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition—0
Don't freeze: Finetune encoders for better Self-Supervised HAR—0
DOO-RE: A dataset of ambient sensors in a meeting room for activity recognition—0
Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles—0
Drive Safe: Cognitive-Behavioral Mining for Intelligent Transportation Cyber-Physical System—0
DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition—0
DS-MS-TCN: Otago Exercises Recognition with a Dual-Scale Multi-Stage Temporal Convolutional Network—0
Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition—0
Asymmetric Residual Neural Network for Accurate Human Activity Recognition—0
Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network—0
Dynamic Feature Selection for Efficient and Interpretable Human Activity Recognition—0
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition—0
Dynamic Programming for Instance Annotation in Multi-instance Multi-label Learning—0
DynImp: Dynamic Imputation for Wearable Sensing Data Through Sensory and Temporal Relatedness—0
Show:102550
← PrevPage 27 of 27Next →
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