4 citations · 14 across the 20 of their papers we have counts for
5 papers · 1 filter
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…
VideoAdviser: Video Knowledge Distillation for Multimodal Transfer Learning
Yanan Wang, Donghuo Zeng, Shinya Wada +1
Multimodal transfer learning aims to transform pretrained representations of diverse modalities into a common domain space for effective multimodal fusion. However, conventional sy…
TV-watching partner robot: Analysis of User's Experience
Donghuo Zeng, Jianming Wu, Gen Hattori +1
Watching TV not only provides news information but also gives an opportunity for different generations to communicate. With the proliferation of smartphones, PC, and the Internet,…
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…
Do I Have Your Attention: A Large Scale Engagement Prediction Dataset and Baselines
Monisha Singh, Ximi Hoque, Donghuo Zeng +3
The degree of concentration, enthusiasm, optimism, and passion displayed by individual(s) while interacting with a machine is referred to as `user engagement'. Engagement comprises…