Search Results for author: Cong Zhang

Found 32 papers, 13 papers with code

Learning Topological Representations with Bidirectional Graph Attention Network for Solving Job Shop Scheduling Problem

no code implementations27 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).

Graph Attention Job Shop Scheduling +1

Aligning Crowd Feedback via Distributional Preference Reward Modeling

no code implementations15 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.

Evaluation of Infrastructure-based Warning System on Driving Behaviors-A Roundabout Study

no code implementations6 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.

Edge-computing Navigate

Semi-supervised Medical Image Segmentation via Query Distribution Consistency

no code implementations21 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.

Image Segmentation Segmentation +2

Collaborative Camouflaged Object Detection: A Large-Scale Dataset and Benchmark

1 code implementation6 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.

Object object-detection +1

HierCat: Hierarchical Query Categorization from Weakly Supervised Data at Facebook Marketplace

no code implementations21 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.

Decision-making with Speculative Opponent Models

no code implementations22 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).

Decision Making SMAC+ +1

Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling

1 code implementation20 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.

Job Shop Scheduling reinforcement-learning +2

Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings

1 code implementation23 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.

Acoustic Unit Discovery Contrastive Learning +5

Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning

1 code implementation13 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.

Deep Progressive Feature Aggregation Network for High Dynamic Range Imaging

no code implementations4 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.

Vocal Bursts Intensity Prediction

Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration

1 code implementation20 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.

Atari Games Q-Learning +2

Applying Feature Underspecified Lexicon Phonological Features in Multilingual Text-to-Speech

no code implementations14 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.

Language Acquisition

ByT5 model for massively multilingual grapheme-to-phoneme conversion

1 code implementation6 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.

Spherical Convolution empowered FoV Prediction in 360-degree Video Multicast with Limited FoV Feedback

1 code implementation29 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.

Saliency Detection Time Series +1

Phone-to-audio alignment without text: A Semi-supervised Approach

1 code implementation8 Oct 2021 Jian Zhu, Cong Zhang, David Jurgens

The task of phone-to-audio alignment has many applications in speech research.

Contrastive Learning

Applying Phonological Features in Multilingual Text-To-Speech

1 code implementation7 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.

Language Acquisition

Synchronising speech segments with musical beats in Mandarin and English singing

no code implementations18 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.

DeepFake-o-meter: An Open Platform for DeepFake Detection

no code implementations2 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.

DeepFake Detection Face Swapping

Comparing acoustic analyses of speech data collected remotely

no code implementations1 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.

Relating spin-foam to canonical loop quantum gravity by graphical calculus

no code implementations11 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

VSEGAN: Visual Speech Enhancement Generative Adversarial Network

no code implementations4 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).

Generative Adversarial Network Speech Enhancement

Discovering Clinically Meaningful Shape Features for the Analysis of Tumor Pathology Images

1 code implementation9 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.

Electric Vehicle Charging Infrastructure Planning: A Scalable Computational Framework

no code implementations17 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.

Profile Generation

DSP: A Differential Spatial Prediction Scheme for Comprehensive real industrial datasets

no code implementations23 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.

reinforcement-learning Reinforcement Learning (RL)

Factors in Finetuning Deep Model for object detection

no code implementations20 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.

Object object-detection +1

Cross-Scene Crowd Counting via Deep Convolutional Neural Networks

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.

Crowd Counting

Cannot find the paper you are looking for? You can Submit a new open access paper.