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 1226–1250 of 1322 papers

TitleStatusHype
Online Learning of Event DefinitionsCode0
Learning Tree-Structured Detection Cascades for Heterogeneous Networks of Embedded Devices—0
Impact of Physical Activity on Sleep:A Deep Learning Based Exploration—0
Robust Automated Human Activity Recognition and its Application to Sleep Research—0
Hierarchical Deep Temporal Models for Group Activity RecognitionCode0
Untrimmed Video Classification for Activity Detection: submission to ActivityNet ChallengeCode0
Laplacian LRR on Product Grassmann Manifolds for Human Activity Clustering in Multi-Camera Video Surveillance—0
Situation Recognition: Visual Semantic Role Labeling for Image UnderstandingCode0
Discriminative Hierarchical Rank Pooling for Activity Recognition—0
First Person Action Recognition Using Deep Learned Descriptors—0
Learning Latent Sub-events in Activity Videos Using Temporal Attention FiltersCode0
Going Deeper into First-Person Activity Recognition—0
Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables—0
Attributes for Improved Attributes: A Multi-Task Network for Attribute Classification—0
Privacy-Preserving Human Activity Recognition from Extreme Low Resolution—0
Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video—0
Temporally Robust Global Motion Compensation by Keypoint-based Congealing—0
Learning from Imbalanced Multiclass Sequential Data Streams Using Dynamically Weighted Conditional Random Fields—0
Mobile Big Data Analytics Using Deep Learning and Apache Spark—0
Learning Privately from Multiparty Data—0
Appearance Based Robot and Human Activity Recognition System—0
Shape Distributions of Nonlinear Dynamical Systems for Video-based Inference—0
Egocentric Activity Recognition with Multimodal Fisher Vector—0
Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition—0
An Event Calculus Production Rule System for Reasoning in Dynamic and Uncertain Domains—0
Show:102550
← PrevPage 50 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