Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Sequential recommendation via agent-based irrelevancy skipping.
Neural Netw
January 2025
School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006, China. Electronic address:
Sequential Recommendation is based on modelling sequential dependencies in user interactions to produce subsequent recommendation results. However, due to the diversity of users' interests and the uncertainty of their behaviours, not all historical interactions in users' interaction sequences are relevant to their next-interaction intents, which hinders generating accurate sequential recommendations. To this end, a novel Sequential Recommendation method, Dynamic-Skip for Sequential Recommendation (DyS4Rec), is proposed in this study.
View Article and Find Full Text PDFUltrasonic collaborative pulse extraction of sugarcane polyphenol with good antiaging and α-glucosidase inhibitory activity.
Int J Biol Macromol
January 2025
SCUT-Zhuhai Institute of Modern Industrial Innovation, School of Food Science and Engineering, South China University of Technology, 381 Wushan Road, Guangzhou 510640, China; Guangdong Province Key Laboratory for Green Processing of Natural Products and Product Safety, Engineering Research Center of Starch and Vegetable Protein Processing Ministry of Education, South China University of Technology, Guangzhou 510640, China; Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center), Guangzhou 510640, China. Electronic address:
Sugarcane, as one important and heavily planted industrial crop, is meaningful to develop its byproducts. In this paper, the ultrasonic collaborative pulse was beneficial for the yield improvement and good bioactivity protection. The sugarcane polyphenol extract (SPE) yield reached 2.
View Article and Find Full Text PDFExplicitly diverse visual question generation.
Neural Netw
December 2024
Department of Computing, Hong Kong Polytechnic University, Hong Kong SAR, China.
Visual question generation involves the generation of meaningful questions about an image. Although we have made significant progress in automatically generating a single high-quality question related to an image, existing methods often ignore the diversity and interpretability of generated questions, which are important for various daily tasks that require clear question sources. In this paper, we propose an explicitly diverse visual question generation model that aims to generate diverse questions based on interpretable question sources.
View Article and Find Full Text PDFScore mismatching for generative modeling.
Neural Netw
July 2024
South China University of Technology, Guangzhou, 510006, Guangdong, China. Electronic address:
We propose a new score-based model with one-step sampling. Previously, score-based models were burdened with heavy computations due to iterative sampling. For substituting the iterative process, we train a standalone generator to compress all the time steps with the gradient backpropagated from the score network.
View Article and Find Full Text PDFA life cycle cost analysis of different shore power incentive policies on both shore and ship sides based on system dynamics and a Chinese port case.
Environ Sci Pollut Res Int
April 2024
Department of Electronic Business/Institute of Digital Business & Intelligent Logistics, South China University of Technology, Guangzhou, China.
Shore power (SP) is widely recognized as an efficient strategy for reducing air pollution in port areas. Unfortunately, the adoption of SP has been relatively low, resulting in limited emission reductions and financial losses. To address these challenges, this paper focuses on enhancing the utilization rate of SP, which is meaningful for emission control and environmental protection.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!