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 1251–1275 of 1322 papers

TitleStatusHype
Improving Human Activity Recognition Through Ranking and Re-ranking—0
Gated networks: an inventory—0
A Deep Structured Model with Radius-Margin Bound for 3D Human Activity Recognition—0
Context Aware Active Learning of Activity Recognition Models—0
Learning Ensembles of Potential Functions for Structured Prediction With Latent Variables—0
ActionNet-VE Dataset: A Dataset for Describing Visual Events by Extending VIRAT Ground 2.0—0
A Hierarchical Deep Temporal Model for Group Activity RecognitionCode0
Deep Activity Recognition Models with Triaxial Accelerometers—0
Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition—0
Application of Machine Learning Techniques in Human Activity Recognition—0
Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition—0
Manipulated Object Proposal: A Discriminative Object Extraction and Feature Fusion Framework for First-Person Daily Activity Recognition—0
Shopper Analytics: a customer activity recognition system using a distributed RGB-D camera network—0
Feature Learning for Interaction Activity Recognition in RGBD Videos—0
Multi-Type Activity Recognition in Robot-Centric Scenarios—0
Deep Structured Models For Group Activity Recognition—0
Sentence Directed Video Object Codetection—0
Encoding Based Saliency Detection for Videos and Images—0
Nested Motion Descriptors—0
Activity recognition from videos with parallel hypergraph matching on GPUs—0
Compact CNN for Indexing Egocentric Videos—0
Detecting Falls with X-Factor Hidden Markov Models—0
Latent Hierarchical Model for Activity Recognition—0
Activity Recognition Using A Combination of Category Components And Local Models for Video Surveillance—0
Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data—0
Show:102550
← PrevPage 51 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