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 1076–1100 of 1322 papers

TitleStatusHype
Wi-Motion: A Robust Human Activity Recognition Using WiFi Signals—0
Mobile Sensor Data AnonymizationCode1
A Preliminary Study on Hyperparameter Configuration for Human Activity Recognition—0
HAR-Net:Fusing Deep Representation and Hand-crafted Features for Human Activity Recognition—0
Audio-Based Activities of Daily Living (ADL) Recognition with Large-Scale Acoustic Embeddings from Online VideosCode0
Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos—0
Ubicoustics: Plug-and-Play Acoustic Activity RecognitionCode0
Custom Dual Transportation Mode Detection by Smartphone Devices Exploiting Sensor DiversityCode0
Optimized Gated Deep Learning Architectures for Sensor Fusion—0
Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention—0
Representation Flow for Action RecognitionCode0
Arianna+: Scalable Human Activity Recognition by Reasoning with a Network of Ontologies—0
Human activity recognition based on time series analysis using U-Net—0
Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence—0
Classification of grasping tasks based on EEG-EMG coherence—0
On the Role of Event Boundaries in Egocentric Activity Recognition from Photostreams—0
Hierarchical Relational Networks for Group Activity Recognition and RetrievalCode0
stagNet: An Attentive Semantic RNN for Group Activity Recognition—0
Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset—0
Online Human Activity Recognition using Low-Power Wearable Devices—0
Deep Adaptive Temporal Pooling for Activity Recognition—0
Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition—0
The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary—0
Starting Movement Detection of Cyclists Using Smart Devices—0
Multi-Scale Supervised Network for Human Pose Estimation—0
Show:102550
← PrevPage 44 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