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 876–900 of 1322 papers

TitleStatusHype
HAMLET: A Hierarchical Multimodal Attention-based Human Activity Recognition Algorithm—0
Towards Deep Clustering of Human Activities from Wearables—0
Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition—0
Empowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity Recognition—0
AssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material -—0
Directional Temporal Modeling for Action Recognition—0
Creating a Large-scale Synthetic Dataset for Human Activity Recognition—0
Social Adaptive Module for Weakly-supervised Group Activity Recognition—0
Spectrum-Guided Adversarial Disparity LearningCode0
Attend And Discriminate: Beyond the State-of-the-Art for Human Activity Recognition using Wearable Sensors—0
Fusing Motion Patterns and Key Visual Information for Semantic Event Recognition in Basketball Videos—0
Knowledge Graph Driven Approach to Represent Video Streams for Spatiotemporal Event Pattern Matching in Complex Event Processing—0
Transfer Learning for Activity Recognition in Mobile HealthCode0
An Efficient Data Imputation Technique for Human Activity Recognition—0
Continual Learning in Human Activity Recognition: an Empirical Analysis of Regularization—0
ARC-Net: Activity Recognition Through Capsules—0
Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos—0
Handling Variable-Dimensional Time Series with Graph Neural Networks—0
Human Activity Recognition based on Dynamic Spatio-Temporal Relations—0
Automatic Operating Room Surgical Activity Recognition for Robot-Assisted Surgery—0
Background Knowledge Injection for Interpretable Sequence Classification—0
DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors—0
A dataset for complex activity recognition withmicro and macro activities in a cooking scenario—0
Learning-to-Learn Personalised Human Activity Recognition Models—0
AdaSense: Adaptive Low-Power Sensing and Activity Recognition for Wearable Devices—0
Show:102550
← PrevPage 36 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