-
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...
-
Chapter and Conference Paper
Blockchain-Based Trusted Synchronization Operation Framework for Open Production Logistics System
The contemporary manufacturing landscape grapples with the escalating dynamic and individualized demands. To swiftly meet personalized production orders, manufacturers are tap** into open production logistic...
-
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
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 AccessMesenchymal stem cells protect against TBI-induced pyroptosis in vivo and in vitro through TSG-6
Pyroptosis, especially microglial pyroptosis, may play an important role in central nervous system pathologies, including traumatic brain injury (TBI). Transplantation of mesenchymal stem cells (MSCs), such as...
-
Chapter and Conference Paper
Training a Lightweight ViT Network for Image Retrieval
Recently, Vision Transformer (ViT) networks have achieved promising advancements on many computer vision tasks. However, a ViT network has a large number of parameters, which is not conducive to deploy of the ...
-
Chapter and Conference Paper
Personalized Education: Blind Knowledge Distillation
Knowledge distillation compresses a large model (teacher) to a smaller one by letting the student imitate the outputs of the teacher. An interesting question is why the student still typically underperforms th...
-
Article
Stabilization of Chinese Gallnut (Galla Chinensis) Tannins by Spray-Drying Microencapsulation for Natural Hair Coloring
Chinese gallnut (Galla chinensis) is rich in hydrolyzable tannins, which, when mordanted with ferrous ions, produces intense black color on keratinous fiber and makes it a desirable natural hair dye in Asian coun...
-
Chapter
Other Chemical Hazards
This chapter reviews five groups of chemical hazards, including 5-HMF, trans-fatty acids, MCPDs and their esters, glycidol and its esters, and acrolein and other alkenals. Their analytical methods, formation m...
-
Article
Distributed cross-media multiple binary subspace learning
Due to the ubiquitous existence of large-scale data in today’s real-world applications, including learning on cross-media data, we propose a semi-supervised learning method, named Multiple Binary Subspace Regr...
-
Chapter and Conference Paper
Marginal Fisher Regression Classification for Face Recognition
This paper presents a novel marginal Fisher regression classification (MFRC) method by incorporating the ideas of marginal Fisher analysis (MFA) and linear regression classification (LRC). The MFRC aims at minimi...
-
Article
Editorial of the special issue on cross-media analysis
-
Article
Formation of 0.84 Nm Hydrated Kaolinite as an Environmentally Friendly Precursor of a Kaolinite Intercalation Compound
Creating an environmentally friendly precursor to form a kaolinite intercalation compound is important for promoting the applications of nanohybrid kaolinite in electrochemical sensors, low- or zero-toxicity d...
-
Article
Societally connected multimedia across cultures
The advance of the Internet in the past decade has radically changed the way people communicate and collaborate with each other. Physical distance is no more a barrier in online social networks, but cultural d...
-
Article
The heterogeneous feature selection with structural sparsity for multimedia annotation and hashing: a survey
There is a rapid growth of the amount of multimedia data from real-world multimedia sharing web sites, such as Flickr and Youtube. These data are usually of high dimensionality, high order, and large scale. Mo...
-
Article
Open AccessIncremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking
Appearance modeling is very important for background modeling and object tracking. Subspace learning-based algorithms have been used to model the appearances of objects or scenes. Current vector subspace-based...
-
Article
A general framework for relation graph clustering
Relation graphs, in which multi-type (or single type) nodes are related to each other, frequently arise in many important applications, such as Web mining, information retrieval, bioinformatics, and epidemiolo...
-
Chapter and Conference Paper
Spectral Graph Partitioning Based on a Random Walk Diffusion Similarity Measure
Spectral graph partitioning is a powerful tool for unsupervised data learning. Most existing algorithms for spectral graph partitioning directly utilize the pairwise similarity matrix of the data to perform gr...
-
Chapter and Conference Paper
Robust Visual Tracking Based on an Effective Appearance Model
Most existing appearance models for visual tracking usually construct a pixel-based representation of object appearance so that they are incapable of fully capturing both global and local spatial layout inform...
-
Article
Intelligent Indexing and Semantic Retrieval of Multimodal Documents
Finding useful information from large multimodal document collections such as the WWW without encountering numerous false positives poses a challenge to multimedia information retrieval systems (MMIR). This re...
