Zhejiang Gongshang University

About: Zhejiang Gongshang University is a education organization based out in Hangzhou, China. It is known for research contribution in the topics: Adsorption & Supply chain. The organization has 8258 authors who have published 7670 publications receiving 90296 citations. The organization is also known as: Zhèjiāng Gōngshāng Dàxué.

Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval

Abstract: The rapid growth of user-generated videos on the Internet has intensified the need for text-based video retrieval systems. Traditional methods mainly favor the concept-based paradigm on retrieval with simple queries, which are usually ineffective for complex queries that carry far more complex semantics. Recently, embedding-based paradigm has emerged as a popular approach. It aims to map the queries and videos into a shared embedding space where semantically-similar texts and videos are much closer to each other. Despite its simplicity, it forgoes the exploitation of the syntactic structure of text queries, making it suboptimal to model the complex queries. To facilitate video retrieval with complex queries, we propose a Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos. Specifically, given a complex user query, we first recursively compose a latent semantic tree to structurally describe the text query. We then design a tree-augmented query encoder to derive structure-aware query representation and a temporal attentive video encoder to model the temporal characteristics of videos. Finally, both the query and videos are mapped into a joint embedding space for matching and ranking. In this approach, we have a better understanding and modeling of the complex queries, thereby achieving a better video retrieval performance. Extensive experiments on large scale video retrieval benchmark datasets demonstrate the effectiveness of our approach.

Fish Oil Emulsions Stabilized with Caseinate Glycated by Dextran: Physicochemical Stability and Gastrointestinal Fate

Abstract: Incorporation of fish oil containing ω-3 polyunsaturated fatty acids (PUFAs) into functional foods remains challenging. In this study, caseinate and glycoconjugates (CD6, CD40, CD70, CD100) of caseinate to dextrans of different molecular weights (D6, D40, D70, D100 kDa) were used to stabilize fish oil emulsions, and the impact on physicochemical stability and gastrointestinal fate was investigated. The glycoconjugate of CD6 exhibited significantly higher conjugation efficiency, lower surface hydrophobicity ( H0), and lower surface activity than other glycoconjugates. The glycoconjugate of CD70 displayed the best emulsifying activity and emulsion stability. Except CD6 stabilized emulsions, all other emulsions showed fine storage stability over 14 d at 22 ± 1 °C. The glycoconjugate stabilized emulsions exhibited significantly lower peroxide value (PV) ( P < 0.05) than that of the caseinate stabilized one. During in vitro gastrointestinal tract digestion, the glycation of caseinate with dextrans changed the ζ-potential, average particle size ( D32), and particle size distribution of the emulsions, which influenced flocculation and coalescence of droplets, as demonstrated by confocal microscopy. Caseinate after glycation with dextrans significantly retarded the release of free fatty acids from emulsions ( P < 0.05) during in vitro lipolysis. These results suggested that the dextrans attached to caseinate by glycation played a vital role in physicochemical stability and gastrointestinal fate of emulsions, mainly by its steric hindrance to effectively prevent flocculation and coalescence of droplets.