Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning

Authors: Gengyu Lyu, Xiang Deng, Yanan Wu, Songhe Feng7647-7654

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments have demonstrated that our proposed method significantly outperforms state-of-the-art methods.
Researcher Affiliation Academia Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer and Information Technology, Beijing Jiaotong University {18112030, 20120346, 19112034, shfeng}@bjtu.edu.cn
Pseudocode Yes Algorithm 1: The Training Process of D-VSM
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes Emotions1 http://mulan.sourceforge.net/datasets-mlc.html... Corel5k (Duygulu et al. 2002) and Espgame (Von Ahn and Dabbish 2004)... Pascal (Everingham et al. 2010) and Mirflickr (Huiskes and Lew 2008)
Dataset Splits Yes Finally, we conduct experimental comparison between our proposed D-VSM and all comparing methods, where five-fold cross-validation is performed on each data set.
Hardware Specification No The paper does not provide specific hardware details (GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not list specific software components with their version numbers.
Experiment Setup Yes In our experiments, we set k = 5.