-
Article
Inherit or discard: learning better domain-specific child networks from the general domain for multi-domain NMT
Multi-domain NMT aims to develop a parameter-sharing model for translating general and specific domains, such as biology, legal, etc., which often struggle with the parameter interference problem. Existing app...
-
Article
Dehaze on small-scale datasets via self-supervised learning
Real-world dehazing datasets usually suffer from small scales because of high collection costs. If networks are trained with such insufficient data, it leads to not only low performance on objective metrics, b...
-
Article
CEA-Net: a co-interactive external attention network for joint intent detection and slot filling
Intent detection and slot filling are two crucial tasks for spoken language understanding, and they are closely related. The accuracy of spoken language understanding depends strongly on the effectiveness of t...
-
Article
Fast shape recognition via a bi-level restraint reduction of contour coding
Shape recognition is an active research topic in the field of computer vision and graphic computing. Nevertheless, existing methods are still poor in accuracy and efficiency in some extent, which greatly limit...
-
Chapter and Conference Paper
Device-Free Cross-Environment Human Action Recognition Using Wi-Fi Signals
The research of human action recognition (HAR) based on Wi-Fi signals shows great application value in fields of human-computer interaction. However, many existing Wi-Fi-based HAR systems are vulnerable to env...
-
Chapter and Conference Paper
Simulation Research on Thermal Management of Hydrogen Fuel Cell for UAV
The relatively high energy density of fuel cell UAVs has attracted more attention, and the working efficiency of fuel cell has a great impact on fuel cell UAVs. This study examines the influences of three cool...
-
Article
UAVs rounding up inspired by communication multi-agent depth deterministic policy gradient
UAVs rounding up is a game between UAV swarm and targets. The main challenge lies in achieving efficient collaboration between UAVs and the setting of rounding-up points. This paper extends our work in three a...
-
Chapter and Conference Paper
PathTR: Context-Aware Memory Transformer for Tumor Localization in Gigapixel Pathology Images
With the development of deep learning and computational pathology, whole-slide images (WSIs) are widely used in clinical diagnosis. A WSI, which refers to the scanning of conventional glass slides into digital...
-
Chapter and Conference Paper
An Efficient Embedding Framework for Uncertain Attribute Graph
Graph data with uncertain connections between entities is commonly represented using uncertain graphs. This paper tackles the challenge of graph embedding within such uncertain attribute graphs. Current graph ...
-
Chapter and Conference Paper
Uncovering Multivariate Structural Dependency for Analyzing Irregularly Sampled Time Series
Predictive analytics on Irregularly Sampled Multivariate Time Series (IS-MTS) presents a challenging problem in many real-world applications. Previous methods have primarily focused on incorporating temporal i...
-
Chapter and Conference Paper
Using Crossmodal Correspondence Between Colors and Music to Enhance Online Art Exhibition Visitors’ Experience
Background music has been widely used in online art exhibitions to enhance visitors’ art appreciation experience. At present, what music to use is highly dependent on exhibition designers’ personal understandi...
-
Chapter and Conference Paper
UKGAT: Uncertain Knowledge Graph Embedding Enriched KGAT for Recommendation
Heterogeneous Information Networks (HINs) with complex structures and rich semantics, which show great flexibility in modeling the heterogeneous data of HINs, are widely used in recommendation systems. Effecti...
-
Chapter and Conference Paper
An Integrated Chinese Malicious Webpages Detection Method Based on Pre-trained Language Models and Feature Fusion
This paper proposed an integrated Chinese malicious webpages detection method. Firstly, we collected and released a Chinese malicious webpages detection dataset called “ChiMalPages” containing URLs and HTML/Ja...
-
Chapter and Conference Paper
An Approach to the Synchronization of Dynamic Complex Network Combining Degree Distribution and Eigenvector Criteria
Synchronization is an important behavior of a dynamic complex network. Traditional methods, like changing network structure, enhancing coupling capability and utilizing external control strategies, etc., canno...
-
Article
Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training
Video quality assessment (VQA) is an important problem in computer vision. The videos in computer vision applications are usually captured in the wild. We focus on automatically assessing the quality of in-the...
-
Chapter and Conference Paper
Hepatocellular Carcinoma Segmentation from Digital Subtraction Angiography Videos Using Learnable Temporal Difference
Automatic segmentation of hepatocellular carcinoma (HCC) in Digital Subtraction Angiography (DSA) videos can assist radiologists in efficient diagnosis of HCC and accurate evaluation of tumors in clinical prac...
-
Chapter and Conference Paper
Changes of Multiple Object Tracking Performance in a 15 Days’ - 6° Head-Down Tilt Bed Rest Experiment
Human-computer interface (HCI) design should fully consider the basic human visual ability including multiple object tracking (MOT). A MOT test was conducted in a 15 days’ - 6° head-down tilt bed rest (HDTBR) ...
-
Chapter and Conference Paper
OMT: An Operate-Based Approach for Modelling Multi-topic Influence Diffusion in Online Social Networks
Influence diffusion modelling in online social networks has been widely studied and applied in public opinion management, viral marketing, and rumour detection. Most existing studies focus on the network topol...
-
Chapter and Conference Paper
Multi-level Relationship Capture Network for Automated Skin Lesion Recognition
Automated skin lesion recognition of dermoscopy images is effective for improving diagnostic performance. Current popular solutions either leverage a single image to learn better feature representations or tak...
-
Chapter and Conference Paper
Clinical-Inspired Network for Skin Lesion Recognition
Automated skin lesion recognition methods are useful for improving the diagnostic accuracy in dermoscopy images. However, several challenges delayed the pace of the development of these methods, including limi...