no code implementations • 21 Apr 2024 • Donghuo Zeng, Roberto S. Legaspi, Yuewen Sun, Xinshuai Dong, Kazushi Ikeda, Peter Spirtes, Kun Zhang
In this paper, we present a novel approach that tracks a user's latent personality dimensions (LPDs) during ongoing persuasion conversation and generates tailored counterfactual utterances based on these LPDs to optimize the overall persuasion outcome.
no code implementations • 21 Apr 2024 • Donghuo Zeng, Yanan Wang, Kazushi Ikeda, Yi Yu
However, the model training fails to fully explore the space due to the scarcity of training data points, resulting in an incomplete representation of the overall positive and negative distributions.
no code implementations • 20 Oct 2023 • Donghuo Zeng, Kazushi Ikeda
We propose a two-stage training paradigm that guides the model's learning process from semi-hard to hard triplets.
no code implementations • 27 Sep 2023 • Yanan Wang, Donghuo Zeng, Shinya Wada, Satoshi Kurihara
In this work, to achieve high efficiency-performance multimodal transfer learning, we propose VideoAdviser, a video knowledge distillation method to transfer multimodal knowledge of video-enhanced prompts from a multimodal fundamental model (teacher) to a specific modal fundamental model (student).
no code implementations • 22 Feb 2023 • Donghuo Zeng, Jianming Wu, Yanan Wang, Kazunori Matsumoto, Gen Hattori, Kazushi Ikeda
Furthermore, our proposed topic-switch algorithm achieves an average score of 1. 767 and outperforms PLATO-JDS by 0. 267, indicating its effectiveness in improving the user experience of our system.
1 code implementation • 1 Feb 2023 • Monisha Singh, Ximi Hoque, Donghuo Zeng, Yanan Wang, Kazushi Ikeda, Abhinav Dhall
The experiments show the usefulness of the proposed dataset.
no code implementations • 7 Nov 2022 • Donghuo Zeng, Yanan Wang, Jianming Wu, Kazushi Ikeda
In this paper, to reduce the interference of hard negative samples in representation learning, we propose a new AV-CMR model to optimize semantic features by directly predicting labels and then measuring the intrinsic correlation between audio-visual data using complete cross-triple loss.
no code implementations • 1 Dec 2020 • Donghuo Zeng, Yi Yu, Keizo Oyama
This work present a music dataset named MusicTM-Dataset, which is utilized in improving the representation learning ability of different types of cross-modal retrieval (CMR).
no code implementations • 29 Jul 2020 • Donghuo Zeng, Yi Yu, Keizo Oyama
In this paper, we propose an unsupervised generative adversarial alignment representation (UGAAR) model to learn deep discriminative representations shared across three major musical modalities: sheet music, lyrics, and audio, where a deep neural network based architecture on three branches is jointly trained.
no code implementations • 21 Aug 2019 • Donghuo Zeng
A cross-modal retrieval process is to use a query in one modality to obtain relevant data in another modality.
no code implementations • 10 Aug 2019 • Haoting Liang, Donghuo Zeng, Yi Yu, Keizo Oyama
Since many online music services emerged in recent years so that effective music recommendation systems are desirable.
2 code implementations • 10 Aug 2019 • Donghuo Zeng, Yi Yu, Keizo Oyama
In particular, two significant contributions are made: i) a better representation by constructing deep triplet neural network with triplet loss for optimal projections can be generated to maximize correlation in the shared subspace.
no code implementations • 10 Aug 2019 • Donghuo Zeng, Yi Yu, Keizo Oyama
ii) We propose an end-to-end deep model for cross-modal audio-visual learning where S-DCCA is trained to learn the semantic correlation between audio and visual modalities.