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 301–325 of 1322 papers

TitleStatusHype
Directional Antenna Systems for Long-Range Through-Wall Human Activity RecognitionCode0
AdaRNN: Adaptive Learning and Forecasting of Time SeriesCode0
Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity RecognitionCode0
Dynamic Vision Sensors for Human Activity RecognitionCode0
Adversarial Attacks on Deep Neural Networks for Time Series ClassificationCode0
Human Activity Recognition using Continuous Wavelet Transform and Convolutional Neural NetworksCode0
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained DevicesCode0
A Novel Skeleton-Based Human Activity Discovery Using Particle Swarm Optimization with Gaussian MutationCode0
Spatio-Temporal Action Graph NetworksCode0
ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity RecognitionCode0
Deep Learning for Sensor-based Activity Recognition: A SurveyCode0
Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable SensorsCode0
DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity RecognitionCode0
Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity RecognitionCode0
ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework for Human Activity RecognitionCode0
Adversarial Domain Adaptation for Cross-user Activity Recognition Using Diffusion-based Noise-centred LearningCode0
AssembleNet++: Assembling Modality Representations via Attention ConnectionsCode0
Deep Heterogeneous Contrastive Hyper-Graph Learning for In-the-Wild Context-Aware Human Activity RecognitionCode0
Adaptive Client Selection with Personalization for Communication Efficient Federated LearningCode0
DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball ImageCode0
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networksCode0
Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural NetworksCode0
Generalized Relevance Learning Grassmann QuantizationCode0
Data Augmentation Techniques for Cross-Domain WiFi CSI-based Human Activity RecognitionCode0
WSense: A Robust Feature Learning Module for Lightweight Human Activity RecognitionCode0
Show:102550
← PrevPage 13 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