no code implementations • 23 Apr 2024 • Kuicai Dong, Derrick Goh Xin Deik, Yi Quan Lee, Hao Zhang, Xiangyang Li, Cong Zhang, Yong liu
As they do not consider content structures, the resultant chunks can exclude vital information or include irrelevant content.
no code implementations • 27 Feb 2024 • Cong Zhang, Zhiguang Cao, Yaoxin Wu, Wen Song, Jing Sun
Existing learning-based methods for solving job shop scheduling problem (JSSP) usually use off-the-shelf GNN models tailored to undirected graphs and neglect the rich and meaningful topological structures of disjunctive graphs (DGs).
no code implementations • 15 Feb 2024 • Dexun Li, Cong Zhang, Kuicai Dong, Derrick Goh Xin Deik, Ruiming Tang, Yong liu
In this paper, we introduce the Distributional Preference Reward Model (DPRM), a simple yet effective framework to align large language models with a diverse set of human preferences.
no code implementations • 6 Dec 2023 • Cong Zhang, Chi Tian, Tianfang Han, Hang Li, Yiheng Feng, Yunfeng Chen, Robert W. Proctor, Jiansong Zhang
A real-world roundabout in Ann Arbor, Michigan was built in the co-simulation platform as the study area, and the merging scenarios were investigated.
no code implementations • 21 Nov 2023 • Rong Wu, Dehua Li, Cong Zhang
In this paper, we propose a novel Dual KMax UX-Net framework that leverages labeled data to guide the extraction of information from unlabeled data.
1 code implementation • 6 Oct 2023 • Cong Zhang, Hongbo Bi, Tian-Zhu Xiang, Ranwan Wu, Jinghui Tong, Xiufang Wang
In this paper, we provide a comprehensive study on a new task called collaborative camouflaged object detection (CoCOD), which aims to simultaneously detect camouflaged objects with the same properties from a group of relevant images.
1 code implementation • IEEE Transactions on Neural Networks and Learning Systems 2023 • Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He, Jie Zhang, Chen Lv.
Stochastic exploration is the key to the success of the Deep Q-network (DQN) algorithm.
no code implementations • 3 Aug 2023 • Cong Zhang, Honggang Qi, Yuezun Li, Siwei Lyu
DeepFakes have raised serious societal concerns, leading to a great surge in detection-based forensics methods in recent years.
no code implementations • 21 Feb 2023 • Yunzhong He, Cong Zhang, Ruoyan Kong, Chaitanya Kulkarni, Qing Liu, Ashish Gandhe, Amit Nithianandan, Arul Prakash
Query categorization at customer-to-customer e-commerce platforms like Facebook Marketplace is challenging due to the vagueness of search intent, noise in real-world data, and imbalanced training data across languages.
no code implementations • 22 Nov 2022 • Jing Sun, Shuo Chen, Cong Zhang, Yining Ma, Jie Zhang
To address this issue, we introduce Distributional Opponent-aided Multi-agent Actor-Critic (DOMAC), the first speculative opponent modelling algorithm that relies solely on local information (i. e., the controlled agent's observations, actions, and rewards).
1 code implementation • 20 Nov 2022 • Cong Zhang, Zhiguang Cao, Wen Song, Yaoxin Wu, Jie Zhang
Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics.
1 code implementation • 23 Oct 2022 • Jian Zhu, Zuoyu Tian, Yadong Liu, Cong Zhang, Chia-wen Lo
Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding.
1 code implementation • 13 Sep 2022 • Rongkai Zhang, Cong Zhang, Zhiguang Cao, Wen Song, Puay Siew Tan, Jie Zhang, Bihan Wen, Justin Dauwels
We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections.
no code implementations • 4 Aug 2022 • Jun Xiao, Qian Ye, Tianshan Liu, Cong Zhang, Kin-Man Lam
The primary challenges are ghosting artifacts caused by object motion between low dynamic range images and distorted content in under and overexposed regions.
1 code implementation • 20 Jun 2022 • Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He, Jie Zhang, Chen Lv
We theoretically prove that the policy improvement theorem holds for the preference-guided $\epsilon$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values.
no code implementations • 14 Apr 2022 • Cong Zhang, Huinan Zeng, Huang Liu, Jiewen Zheng
This mapping was tested for whether it could lead to the successful generation of native, non-native, and code-switched speech in the two languages.
1 code implementation • 6 Apr 2022 • Jian Zhu, Cong Zhang, David Jurgens
In this study, we tackle massively multilingual grapheme-to-phoneme conversion through implementing G2P models based on ByT5.
1 code implementation • 29 Jan 2022 • Jie Li, Ling Han, Cong Zhang, Qiyue Li, Zhi Liu
Most of the current prediction methods combining saliency detection and FoV information neither take into account that the distortion of projected 360-degree videos can invalidate the weight sharing of traditional convolutional networks, nor do they adequately consider the difficulty of obtaining complete multi-user FoV information, which degrades the prediction performance.
1 code implementation • 8 Oct 2021 • Jian Zhu, Cong Zhang, David Jurgens
The task of phone-to-audio alignment has many applications in speech research.
1 code implementation • 7 Oct 2021 • Cong Zhang, Huinan Zeng, Huang Liu, Jiewen Zheng
We tested whether this mapping could lead to the successful generation of native, non-native, and code-switched speech in the two languages.
no code implementations • 18 Jun 2021 • Cong Zhang, Jian Zhu
Generating synthesised singing voice with models trained on speech data has many advantages due to the models' flexibility and controllability.
no code implementations • 2 Mar 2021 • Yuezun Li, Cong Zhang, Pu Sun, Honggang Qi, Siwei Lyu
In recent years, the advent of deep learning-based techniques and the significant reduction in the cost of computation resulted in the feasibility of creating realistic videos of human faces, commonly known as DeepFakes.
no code implementations • 1 Mar 2021 • Cong Zhang, Kathleen Jepson, Georg Lohfink, Amalia Arvaniti
Face-to-face speech data collection has been next to impossible globally due to COVID-19 restrictions.
no code implementations • 11 Feb 2021 • Jinsong Yang, Cong Zhang, Yongge Ma
On the other hand, the action of a Euclidean Hamiltonian constraint operator on certain spin network states is calculated by graphical method.
General Relativity and Quantum Cosmology
no code implementations • 4 Feb 2021 • Xinmeng Xu, Yang Wang, Dongxiang Xu, Yiyuan Peng, Cong Zhang, Jie Jia, Binbin Chen
This paper proposes a novel frameworkthat involves visual information for speech enhancement, by in-corporating a Generative Adversarial Network (GAN).
1 code implementation • 9 Dec 2020 • Esteban Fernández Morales, Cong Zhang, Guanghua Xiao, Chul Moon, Qiwei Li
With the advanced imaging technology, digital pathology imaging of tumor tissue slides is becoming a routine clinical procedure for cancer diagnosis.
no code implementations • 17 Nov 2020 • Wanshi Hong, Cong Zhang, Cy Chan, Bin Wang
The optimal charging infrastructure planning problem over a large geospatial area is challenging due to the increasing network sizes of the transportation system and the electric grid.
5 code implementations • NeurIPS 2020 • Cong Zhang, Wen Song, Zhiguang Cao, Jie Zhang, Puay Siew Tan, Chi Xu
Priority dispatching rule (PDR) is widely used for solving real-world Job-shop scheduling problem (JSSP).
no code implementations • 23 Aug 2020 • Jun-Jie Zhang, Cong Zhang, Neal N. Xiong
The improved deep reinforcement learning network is then used to search for and learn the hyperparameters of each sample point in the inverse distance weighted model.
no code implementations • CVPR 2016 • Wanli Ouyang, Xiaogang Wang, Cong Zhang, Xiaokang Yang
Our analysis and empirical results show that classes with more samples have higher impact on the feature learning.
1 code implementation • 9 Apr 2016 • Kai Kang, Hongsheng Li, Junjie Yan, Xingyu Zeng, Bin Yang, Tong Xiao, Cong Zhang, Zhe Wang, Ruohui Wang, Xiaogang Wang, Wanli Ouyang
Temporal and contextual information of videos are not fully investigated and utilized.
no code implementations • 20 Jan 2016 • Wanli Ouyang, Xiaogang Wang, Cong Zhang, Xiaokang Yang
Our analysis and empirical results show that classes with more samples have higher impact on the feature learning.
no code implementations • CVPR 2015 • Cong Zhang, Hongsheng Li, Xiaogang Wang, Xiaokang Yang
To address this problem, we propose a deep convolutional neural network (CNN) for crowd counting, and it is trained alternatively with two related learning objectives, crowd density and crowd count.
Ranked #15 on Crowd Counting on WorldExpo’10