Dual Self-Paced Cross-Modal Hashing

Authors: Yuan Sun, Jian Dai, Zhenwen Ren, Yingke Chen, Dezhong Peng, Peng Hu

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are conducted on three widelyused benchmark datasets to demonstrate the effectiveness and robustness of the proposed DSCMH over 12 state-of-the-art CMH methods.
Researcher Affiliation Academia 1 College of Computer Science, Sichuan University, Chengdu, China 2 National Innovation Center for UHD Video Technology, Chengdu, China 3 Department of Automation, Tsinghua University, Beijing, China 4 School of National Defense Science and Technology, Southwest University of Science and Technology, Mianyang, China 5 Department of Computer and Information Sciences, Northumbria University, UK
Pseudocode No The paper describes the method using mathematical equations and steps, but does not include structured pseudocode or an algorithm block.
Open Source Code No The paper does not provide concrete access to its own source code, such as a repository link or an explicit statement of code release.
Open Datasets Yes To evaluate the performance of our DSCMH, we compare it with thirteen baselines on three used-widely benchmark datasets, i.e., MIRFlickr, IAPR-TC12, and NUS-WIDE.
Dataset Splits No The paper specifies a 'query set' for evaluation but does not provide explicit training/validation/test dataset splits or mention a validation set for model tuning.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies, such as library names with version numbers, needed to replicate the experiment.
Experiment Setup Yes In the experiments, we empirically set m = 15, q = 1.2, and d = 1500. From the parameter analysis, we set α and λ as {10 3, 10 2}, {10 2, 10 3}, and {10 3, 10 4} on three datasets, respectively.