no code implementations • 4 Feb 2024 • Eric Khiu, Hasti Toossi, David Anugraha, Jinyu Liu, Jiaxu Li, Juan Armando Parra Flores, Leandro Acros Roman, A. Seza Doğruöz, En-Shiun Annie Lee
Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs).
no code implementations • 5 Nov 2023 • Jinyu Liu, Hongye Guo, Qinghu Tang, En Lu, Qiuna Cai, Qixin Chen
To address this challenge, we modify the common reinforcement learning(RL) process by proposing a new bid representation method called Neural Network Embedded Bids (NNEBs).
1 code implementation • 12 Jul 2022 • Jiashuo Yu, Jinyu Liu, Ying Cheng, Rui Feng, Yuejie Zhang
In this paper, we analyze the modality asynchrony and undifferentiated instances phenomena of the multiple instance learning (MIL) procedure, and further investigate its negative impact on weakly-supervised audio-visual learning.
Anomaly Detection In Surveillance Videos audio-visual learning +1
no code implementations • 10 Apr 2022 • Jinyu Liu, Ying Cheng, Yuejie Zhang, Rui-Wei Zhao, Rui Feng
Visual-only self-supervised learning has achieved significant improvement in video representation learning.
no code implementations • 2 Apr 2022 • Jianrong Wang, Jinyu Liu, Longxuan Zhao, Shanyu Wang, Ruiguo Yu, Li Liu
Acoustic-to-articulatory inversion (AAI) is to obtain the movement of articulators from speech signals.
no code implementations • 11 Oct 2021 • Mengjuan Liu, Jinyu Liu, Zhengning Hu, Yuchen Ge, Xuyun Nie
In this paper, we first utilize a widely accepted linear bidding function to compute every impression's base price and optimize it by a mutable adjustment factor derived from the RTB auction environment, to avoid optimizing every impression's bidding price directly.
no code implementations • journal 2020 • Lei Fan, GUOQING QI2, Jun Xing, JIYU JIN, Jinyu Liu, AND ZHISEN WANG
The correlation coef cients between the Fourier Transform of the noises on two arbitrarily spaced spectrum lines are derived, and the MSE calculation formula is derived in additive white noise background based on the correlation coef cients.