Human action recognition via multi-task learning base on spatial-temporal feature
Explore this paper's citation graph
Summary
A novel human action recognition method using regularized multi-task learning that completely represents the local visual characteristics of the human body structure and has significantly better performance than the standard Bag- of-Words+Support Vector Machine (BoW+SVM) method and other state-of-the-art methods.
- Type
- article
- Published
- 2015-11-01
- Cited by
- 80
- References
- 57
- OpenAlex
- https://openalex.org/W648994142
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:40339931
Keywords
Computer science, Artificial intelligence, Action recognition, Pattern recognition (psychology), Task (project management)
References
- A View-based Multiple Objects Tracking and Human Action Recognition for Interactive Virtual Environments
- Multi-Task Feature Learning Via Efficient l2, 1-Norm Minimization
- Simultaneous segmentation and classification of human actions in video streams using deeply optimized Hough transform
- Task-Dependent Visual-Codebook Compression
- Mining flickr landmarks by modeling reconstruction sparsity
- Slow Feature Analysis for Human Action Recognition
- Location Discriminative Vocabulary Coding for Mobile Landmark Search
- Single/multi-view human action recognition via regularized multi-task learning
- A probabilistic, discriminative and distributed system for the recognition of human actions from multiple views
- Laplacian group sparse modeling of human actions
- Evaluation of Local Spatio-temporal Features for Action Recognition
- Human Action Recognition in Large-Scale Datasets Using Histogram of Spatiotemporal Gradients
- Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis
- Partwise bag-of-words-based multi-task learning for human action recognition
- Human Action Recognition With Multiple-Instance Markov Model
- 3-D Object Retrieval With Hausdorff Distance Learning
- Pose-based human action recognition via sparse representation in dissimilarity space
- A Spatio-Temporal Descriptor Based on 3D-Gradients
- Bio-inspired Dynamic 3D Discriminative Skeletal Features for Human Action Recognition
- Coupled hidden conditional random fields for RGB-D human action recognition
Cited by
- Lower Limb Action Recognition with Motion Data of a Human Joint
- A novel spatio-temporal saliency approach for robust dim moving target detection from airborne infrared image sequences
- Human actions recognition from motion capture recordings using signal resampling and pattern recognition methods
- Human motion segmentation and recognition using machine vision for mechanical assembly operation
- Evaluation of regularized multi-task leaning algorithms for single/multi-view human action recognition
- Computer vision based crowd disaster avoidance system: A survey
- 3D human action recognition model based on image set and regularized multi-task leaning
- CSIR4G: An effective and efficient cross-scenario image retrieval model for glasses
- Human Action Classification Based on Silhouette Indexed Interest Points for Multiple Domains
- A semantic tree method for image classification and video action recognition
- Discriminative parts learning for 3D human action recognition
- MMA: a multi-view and multi-modality benchmark dataset for human action recognition
- Automated multi-feature human interaction recognition in complex environment
- Multi-task learning with group information for human action recognition
- Insights on Research-based Approaches in Human Activity Recognition System
- Context-Dependent Random Walk Graph Kernels and Tree Pattern Graph Matching Kernels With Applications to Action Recognition
- Human Action Recognition Based on RGB-D and Local Interactive Regions Detection
- Abnormal Human Activity Recognition using Bayes Classifier and Convolutional Neural Network
- Dynamic Field Monitoring Based on Multitask Learning in Sensor Networks
- Online human action recognition based on incremental learning of weighted covariance descriptors
Related papers
- The Benefit of Multitask Representation Learning
- Human action recognition using meta learning for RGB and depth information
- Multi-Task Model and Feature Joint Learning
- Task Sensitive Feature Exploration and Learning for Multitask Graph Classification
- Representation Learning via Semi-Supervised Autoencoder for Multi-task Learning
- Scalable Multitask Representation Learning for Scene Classification
- Multitask Learning with Heterogeneous Tasks
- Multitask, Multilabel, and Multidomain Learning With Convolutional Networks for Emotion Recognition