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 1151–1175 of 1322 papers

TitleStatusHype
A Correlation Based Feature Representation for First-Person Activity RecognitionCode0
Latent hypernet: Exploring all Layers from Convolutional Neural Networks—0
Simultaneous Joint and Object Trajectory Templates for Human Activity Recognition from 3-D Data—0
An Integrated Approach to Crowd Video Analysis: From Tracking to Multi-level Activity Recognition—0
PoseTrack: A Benchmark for Human Pose Estimation and TrackingCode0
ActivityNet Challenge 2017 Summary—0
Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data AnalysisCode0
Batch-based Activity Recognition from Egocentric Photo-Streams RevisitedCode0
SBGAR: Semantics Based Group Activity RecognitionCode0
Unsupervised Segmentation of Action Segments in Egocentric Videos using Gaze—0
Multi-Person Brain Activity Recognition via Comprehensive EEG Signal Analysis—0
Latent Embeddings for Collective Activity Recognition—0
Human Activity Recognition Using Robust Adaptive Privileged Probabilistic Learning—0
Kernel Cross-CorrelatorCode0
CLAD: A Complex and Long Activities Dataset with Rich Crowdsourced Annotations—0
Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks—0
Action Classification and Highlighting in Videos—0
Batch-Based Activity Recognition from Egocentric Photo-Streams—0
A Survey of Human Activity Recognition Using WiFi CSICode0
Activity Recognition based on a Magnitude-Orientation Stream Network—0
Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable SensorsCode0
Early Improving Recurrent Elastic Highway Network—0
Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning—0
Zero-Shot Activity Recognition with Verb Attribute InductionCode0
Multi-kernel learning of deep convolutional features for action recognition—0
Show:102550
← PrevPage 47 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