-
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...
-
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
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...
-
Chapter and Conference Paper
Multi-scale Inter-frame Information Fusion Based Network for Cardiac MRI Reconstruction
Accelerated cine MRI reconstruction from under-sampled data is paramount in clinical diagnosis. Nonetheless, the existing method falls short in fully harnessing inter-frame information, thereby impeding its ov...
-
Article
Supervised biadjacency networks for stereo matching
Convolutional neural network (CNN) based stereo matching methods using cost volume techniques have gained prominence in stereo matching. State-of-the-art cost volume based methods use two weight-sharing featur...
-
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
Spatial attention-guided deformable fusion network for salient object detection
Most of salient object detection methods employ U-shape architecture as the understructure. Although promising performance has been achieved, they struggle to detect salient objects with non-rigid shapes and a...
-
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
Open AccessVirtual-scanning light-field microscopy for robust snapshot high-resolution volumetric imaging
High-speed three-dimensional (3D) intravital imaging in animals is useful for studying transient subcellular interactions and functions in health and disease. Light-field microscopy (LFM) provides a computatio...
-
Article
Teachers cooperation: team-knowledge distillation for multiple cross-domain few-shot learning
Although few-shot learning (FSL) has achieved great progress, it is still an enormous challenge especially when the source and target set are from different domains, which is also known as cross-domain few-sho...
-
Article
Heterogeneous memory enhanced graph reasoning network for cross-modal retrieval
Cross-modal retrieval (CMR) aims to retrieve the instances of a specific modality that are relevant to a given query from another modality, which has drawn much attention because of its importance in bridging ...
-
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
Triple discriminator generative adversarial network for zero-shot image classification
One key challenge in zero-shot classification (ZSC) is the exploration of knowledge hidden in unseen classes. Generative methods such as generative adversarial networks (GANs) are typically employed to generat...
-
Article
PSC-Net: learning part spatial co-occurrence for occluded pedestrian detection
Detecting pedestrians, especially under heavy occlusion, is a challenging computer vision problem with numerous real-world applications. This paper introduces a novel approach, termed as PSC-Net, for occluded ...
-
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...
-
Article
Special focus on deep learning for computer vision
-
Article
CGNet: cross-guidance network for semantic segmentation
Semantic segmentation is a fundamental task in image analysis. The issue of semantic segmentation is to extract discriminative features for distinguishing different objects and recognizing hard examples. Howev...
-
Article
Preserving details in semantics-aware context for scene parsing
Great success of scene parsing (also known as, semantic segmentation) has been achieved with the pipeline of fully convolutional networks (FCNs). Nevertheless, there are a lot of segmentation failures caused b...
-
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...
-
Chapter and Conference Paper
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
Single-stage instance segmentation approaches have recently gained popularity due to their speed and simplicity, but are still lagging behind in accuracy, compared to two-stage methods. We propose a fast singl...
