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 726–750 of 1322 papers

TitleStatusHype
PosePilot: An Edge-AI Solution for Posture Correction in Physical Exercises—0
Pose Uncertainty Aware Movement Synchrony Estimation via Spatial-Temporal Graph Transformer—0
Post-training Iterative Hierarchical Data Augmentation for Deep Networks—0
Pragmatic classification of movement primitives for stroke rehabilitation—0
Predicting Human Depression with Hybrid Data Acquisition utilizing Physical Activity Sensing and Social Media Feeds—0
Predicting User-specific Future Activities using LSTM-based Multi-label Classification—0
PresSim: An End-to-end Framework for Dynamic Ground Pressure Profile Generation from Monocular Videos Using Physics-based 3D Simulation—0
PressureTransferNet: Human Attribute Guided Dynamic Ground Pressure Profile Transfer using 3D simulated Pressure Maps—0
Privacy in Multimodal Federated Human Activity Recognition—0
Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images—0
Privacy-Preserving Eye-tracking Using Deep Learning—0
Privacy-Preserving Human Activity Recognition from Extreme Low Resolution—0
PrivHAR: Recognizing Human Actions From Privacy-preserving Lens—0
Probabilistic Sensor Fusion for Ambient Assisted Living—0
Probing Fine-Grained Action Understanding and Cross-View Generalization of Foundation Models—0
Process-aware Human Activity Recognition—0
Process Optimization and Deployment for Sensor-Based Human Activity Recognition Based on Deep Learning—0
Progress Estimation and Phase Detection for Sequential Processes—0
Progressive Relation Learning for Group Activity Recognition—0
POND: Multi-Source Time Series Domain Adaptation with Information-Aware Prompt Tuning—0
PromptGAR: Flexible Promptive Group Activity Recognition—0
Provable Robustness for Streaming Models with a Sliding Window—0
Provably Secure Federated Learning against Malicious Clients—0
Pyramid Recurrent Neural Networks for Multi-Scale Change-Point Detection—0
Qiniu Submission to ActivityNet Challenge 2018—0
Show:102550
← PrevPage 30 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