-
Chapter and Conference Paper
Neighborhood Preserving Projections (NPP): A Novel Linear Dimension Reduction Method
Dimension reduction is a crucial step for pattern recognition and information retrieval tasks to overcome the curse of dimensionality. In this paper a novel unsupervised linear dimension reduction method, Neighbo...
-
Chapter and Conference Paper
Balance between Diversity and Relevance for Image Search Results
Image search reranking has received great attention since it overcomes the drawback of “only textual features utilization” in nowadays web-scale image search engines. Most of existing methods focus on relevanc...
-
Chapter and Conference Paper
Weighted Deformable Part Model for Robust Human Detection
Due to human pose articulation, variation in human shapes and appearances, especially occlusion between human and objects, one challenging problem in human detection is detect partially or completely occluded ...
-
Chapter and Conference Paper
Frequency Domain Directional Filtering Based Rain Streaks Removal from a Single Color Image
Bad weather conditions, such as rain or snow, degrade outdoor vision system performance. Rain removal from a single image has been investigated extensively. However, existing built rain streak models are great...
-
Chapter and Conference Paper
Interactive Head 3D Reconstruction Based Combine of Key Points and Voxel
In the 3D reconstruction of the head, we can extract a large number of key points from the face, but not enough key points from the hair. The 3D reconstruction method based key points do well in the facial rec...
-
Article
Incrementally Detecting Moving Objects in Video with Sparsity and Connectivity
Moving object detection is crucial for cognitive vision-based robot tasks. However, due to noise, dynamic background, variations in illumination, and high frame rate, it is a challenging task to robustly and e...
-
Chapter and Conference Paper
Zero-Shot Learning with Deep Canonical Correlation Analysis
Zero-shot learning (ZSL) improves the scalability of conventional image classification systems by allowing some testing categories having no training data. One key component is to learn a shared embedding spac...
-
Chapter and Conference Paper
ECG Waveform Extraction from Paper Records
Electrocardiogram (ECG) is one of the most practiced methods to detect any abnormalities in human heart function. ECG waveforms are usually recorded as paper form. However, ECG paper records are inconvenient f...
-
Article
Learning Tone Map** Function for Dehazing
-
Chapter and Conference Paper
Cross-Modal Retrieval with Discriminative Dual-Path CNN
Cross-modal retrieval aims at searching semantically similar examples in one modality by using a query from another modality. Its typical applications including image-based text retrieval (IBTR) and text-based...
-
Chapter and Conference Paper
ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation
Segmentation is a fundamental task in medical image analysis. However, most existing methods focus on primary region extraction and ignore edge information, which is useful for obtaining accurate segmentation....
-
Chapter and Conference Paper
Count- and Similarity-Aware R-CNN for Pedestrian Detection
Recent pedestrian detection methods generally rely on additional supervision, such as visible bounding-box annotations, to handle heavy occlusions. We propose an approach that leverages pedestrian count and pr...
-
Article
Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification
Target-dependent sentiment classification aims at identifying the sentiment polarities of targets in a given sentence. Previous approaches utilize recurrent neural network with attention mechanism incorporated...
-
Chapter and Conference Paper
Illumination-Guided Transformer-Based Network for Multispectral Pedestrian Detection
Multi-modal information (e.g., visible and thermal) can generate reliable and robust pedestrian detection results in various computer vision applications. Despite its broad applications, it remains a crucial p...
-
Article
Zero-shot classification with unseen prototype learning
Zero-shot learning (ZSL) aims at recognizing instances from unseen classes via training a classification model with only seen data. Most existing approaches easily suffer from the classification bias from unse...
-
Article
COREN: Multi-Modal Co-Occurrence Transformer Reasoning Network for Image-Text Retrieval
Cross-modal image-text retrieval aims at retrieving the images according to the given query texts and vice versa, which is a challenging task due to the inherent heterogeneous gap between computer vision and n...
-
Article
SSNet: a joint learning network for semantic segmentation and disparity estimation
Joint learning for semantic segmentation and disparity estimation is adopted to scene parsing for mutual benefit. However, existing joint learning approaches unify the two task briefly which may result in nega...
-
Article
Multi-feature self-attention super-resolution network
In recent years, single-image super-resolution (SISR) methods based on the attention mechanism have been widely explored and achieved remarkable performances. However, most existing networks only explore chann...
-
Article
Uncertainty-aware enhanced dark experience replay for continual learning
The replay-based approaches are a notable family of methods among many efforts on Continual Learning, where memory sampling strat- egy and rehearsal mode are two fundamental aspects to alleviate the catastroph...