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
Unsupervised Segmentation of Action Segments in Egocentric Videos using Gaze—0
Unsupervised Statistical Feature-Guided Diffusion Model for Sensor-based Human Activity Recognition—0
Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal—0
Unsupervised Video Anomaly Detection for Stereotypical Behaviours in Autism—0
Using GAN to Enhance the Accuracy of Indoor Human Activity Recognition—0
Human Gaze Guided Attention for Surgical Activity Recognition—0
Utility-aware Privacy-preserving Data Releasing—0
VaCDA: Variational Contrastive Alignment-based Scalable Human Activity Recognition—0
VALERIAN: Invariant Feature Learning for IMU Sensor-based Human Activity Recognition in the Wild—0
VCHAR:Variance-Driven Complex Human Activity Recognition framework with Generative Representation—0
VecLSTM: Trajectory Data Processing and Management for Activity Recognition through LSTM Vectorization and Database Integration—0
VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition—0
VicTR: Video-conditioned Text Representations for Activity Recognition—0
Video2IMU: Realistic IMU features and signals from videos—0
Video-based Exercise Classification and Activated Muscle Group Prediction with Hybrid X3D-SlowFast Network—0
Video-based Pose-Estimation Data as Source for Transfer Learning in Human Activity Recognition—0
Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition—0
Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model—0
Virtual Fusion with Contrastive Learning for Single Sensor-based Activity Recognition—0
Vision-Based Activity Recognition in Children with Autism-Related Behaviors—0
Visually Guided Spatial Relation Extraction from Text—0
Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernel—0
Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM Agents—0
ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos—0
Wallcamera: Reinventing the Wheel?—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