AIMC Topic: Pattern Recognition, Automated

Clear Filters Showing 61 to 70 of 1689 articles

Multi-Label Zero-Shot Learning Via Contrastive Label-Based Attention.

International journal of neural systems
Multi-label zero-shot learning (ML-ZSL) strives to recognize all objects in an image, regardless of whether they are present in the training data. Recent methods incorporate an attention mechanism to locate labels in the image and generate class-spec...

DCTCNet: Sequency discrete cosine transform convolution network for visual recognition.

Neural networks : the official journal of the International Neural Network Society
The discrete cosine transform (DCT) has been widely used in computer vision tasks due to its ability of high compression ratio and high-quality visual presentation. However, conventional DCT is usually affected by the size of transform region and res...

Contrastive independent subspace analysis network for multi-view spatial information extraction.

Neural networks : the official journal of the International Neural Network Society
Multi-view classification integrates features from different views to optimize classification performance. Most of the existing works typically utilize semantic information to achieve view fusion but neglect the spatial information of data itself, wh...

An efficient framework based on local multi-representatives and noise-robust synthetic example generation for self-labeled semi-supervised classification.

Neural networks : the official journal of the International Neural Network Society
While self-labeled methods can exploit unlabeled and labeled instances to train classifiers, they are also restricted by the labeled instance number and distribution. SEG-SSC, k-means-SSC, LC-SSC, and LCSEG-SSC are sophisticated solutions for overcom...

PFENet: Towards precise feature extraction from sparse point cloud for 3D object detection.

Neural networks : the official journal of the International Neural Network Society
Accurate 3D point cloud object detection is crucially important for autonomous driving vehicles. The sparsity of point clouds in 3D scenes, especially for smaller targets like pedestrians and bicycles that contain fewer points, makes detection partic...

Real-Time On-Device Continual Learning Based on a Combined Nearest Class Mean and Replay Method for Smartphone Gesture Recognition.

Sensors (Basel, Switzerland)
Sensor-based gesture recognition on mobile devices is critical to human-computer interaction, enabling intuitive user input for various applications. However, current approaches often rely on server-based retraining whenever new gestures are introduc...

An adversarial transformer for anomalous lamb wave pattern detection.

Neural networks : the official journal of the International Neural Network Society
Lamb waves are widely used for defect detection in structural health monitoring, and various methods are developed for Lamb wave data analysis. This paper presents an unsupervised Adversarial Transformer model for anomalous Lamb wave pattern detectio...

Human-Centric Transformer for Domain Adaptive Action Recognition.

IEEE transactions on pattern analysis and machine intelligence
We study the domain adaptation task for action recognition, namely domain adaptive action recognition, which aims to effectively transfer action recognition power from a label-sufficient source domain to a label-free target domain. Since actions are ...

Adaptive Gait Feature Learning Using Mixed Gait Sequence.

IEEE transactions on neural networks and learning systems
Gait recognition has become a mainstream technology for identification, as it can recognize the identity of subjects from a distance without any cooperation. However, when subjects wear coats (CL) or backpacks (BG), their gait silhouette will be occl...

SemiHAR: Improving Semisupervised Human Activity Recognition via Multitask Learning.

IEEE transactions on neural networks and learning systems
Semisupervised human activity recognition (SemiHAR) has attracted attention in recent years from various domains, such as digital health and ambient intelligence. Currently, it still faces two challenges. For one thing, discriminative features may ex...