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 1301–1322 of 1322 papers

TitleStatusHype
Towards Using Unlabeled Data in a Sparse-coding Framework for Human Activity Recognition—0
Reshaping Visual Datasets for Domain Adaptation—0
Transfer Learning in a Transductive Setting—0
Relevance Topic Model for Unstructured Social Group Activity Recognition—0
Automated Activity Recognition in Clinical Documents—0
Seeing What You're Told: Sentence-Guided Activity Recognition In Video—0
Activity Modeling in Smart Home using High Utility Pattern Mining over Data Streams—0
Poselet Key-Framing: A Model for Human Activity Recognition—0
Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs—0
First-Person Activity Recognition: What Are They Doing to Me?—0
Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera—0
HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences—0
Kernel Learning for Extrinsic Classification of Manifold Features—0
Decoding Children's Social Behavior—0
Recognizing Activities via Bag of Words for Attribute Dynamics—0
Recognize Human Activities from Partially Observed Videos—0
Two-person interaction detection using body-pose features and multiple instance learning—0
Probabilistic Event Calculus for Event RecognitionCode0
A Probabilistic Logic Programming Event CalculusCode0
Beyond Actions: Discriminative Models for Contextual Group Activities—0
A Logic Programming Approach to Activity Recognition—0
Fast and Scalable Training of Semi-Supervised CRFs with Application to Activity Recognition—0
Show:102550
← PrevPage 27 of 27Next →
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