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 1201–1225 of 1322 papers

TitleStatusHype
Ratio Utility and Cost Analysis for Privacy Preserving Subspace Projection—0
Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies—0
Boosted Multiple Kernel Learning for First-Person Activity Recognition—0
An Analysis of Parallelized Motion Masking Using Dual-Mode Single Gaussian ModelsCode0
Concurrent Activity Recognition with Multimodal CNN-LSTM Structure—0
Probabilistic Sensor Fusion for Ambient Assisted Living—0
Self-Adaptation of Activity Recognition Systems to New Sensors—0
An Interval-Based Bayesian Generative Model for Human Complex Activity Recognition—0
A Deep Learning Approach To Multiple Kernel Fusion—0
Human Action Attribute Learning From Video Data Using Low-Rank Representations—0
Jointly learning heterogeneous features for rgb-d activity recognition—0
Unsupervised Human Action Detection by Action Matching—0
Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition—0
UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones—0
Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation—0
Answering Image Riddles using Vision and Reasoning through Probabilistic Soft Logic—0
Deep Recurrent Neural Network for Mobile Human Activity Recognition with High Throughput—0
Action2Activity: Recognizing Complex Activities from Sensor Data—0
DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data ProcessingCode1
Detecting Unseen Falls from Wearable Devices using Channel-wise Ensemble of Autoencoders—0
Dataiku's Solution to SPHERE's Activity Recognition Challenge—0
Contextual Relationship-based Activity Segmentation on an Event Stream in the IoT Environment with Multi-user Activities—0
A framework for mining process models from emails logs—0
OSL𝛼: Online Structure Learning Using Background Knowledge AxiomatizationCode1
Mouse Movement and Probabilistic Graphical Models Based E-Learning Activity Recognition Improvement Possibilistic Model—0
Show:102550
← PrevPage 49 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