1 citations · 2 across the 3 of their papers we have counts for
3 papers
cs.SD2024★ 1 cited
Anchor-aware Deep Metric Learning for Audio-visual Retrieval
Donghuo Zeng, Yanan Wang, Kazushi Ikeda +1
Metric learning minimizes the gap between similar (positive) pairs of data points and increases the separation of dissimilar (negative) pairs, aiming at capturing the underlying da…
cs.SD2023★ 1 cited
Two-Stage Triplet Loss Training with Curriculum Augmentation for Audio-Visual Retrieval
Donghuo Zeng, Kazushi Ikeda
The cross-modal retrieval model leverages the potential of triple loss optimization to learn robust embedding spaces. However, existing methods often train these models in a singul…
cs.CL2023
Topic-switch adapted Japanese Dialogue System based on PLATO-2
Donghuo Zeng, Jianming Wu, Yanan Wang +3
Large-scale open-domain dialogue systems such as PLATO-2 have achieved state-of-the-art scores in both English and Chinese. However, little work explores whether such dialogue syst…