Search Results for author: Cheng Xu

Found 23 papers, 10 papers with code

G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors

1 code implementation18 Aug 2024 Haoxin Yang, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Jing Qin, Yi Wang, Pheng-Ann Heng, Shengfeng He

This paper introduces G\textsuperscript{2}Face, which leverages both generative and geometric priors to enhance identity manipulation, achieving high-quality reversible face anonymization without compromising data utility.

Decoder Face Anonymization +1

An Enhanced Fake News Detection System With Fuzzy Deep Learning

1 code implementation IEEE Access 2024 Cheng Xu, M-Tahar Kechadi

Our study presents detailed comparisons and ablation experiments on both LIAR and LIAR2 datasets and establishes our results as the baseline for LIAR2.

Deep Learning Fact Checking +2

Benchmark Data Contamination of Large Language Models: A Survey

no code implementations6 Jun 2024 Cheng Xu, Shuhao Guan, Derek Greene, M-Tahar Kechadi

The rapid development of Large Language Models (LLMs) like GPT-4, Claude-3, and Gemini has transformed the field of natural language processing.

Survey

Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction

no code implementations1 Jun 2024 Cheng Xu, Fei Hou, Wencheng Wang, Hong Qin, Zhebin Zhang, Ying He

While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures.

3D Reconstruction Surface Reconstruction

ArSen-20: A New Benchmark for Arabic Sentiment Detection

1 code implementation 5th Workshop on African Natural Language Processing 2024 Yang Fang, Cheng Xu

Sentiment detection remains a pivotal task in natural language processing, yet its development in Arabic lags due to a scarcity of training materials compared to English.

Arabic Sentiment Analysis

Towards Flexible, Scalable, and Adaptive Multi-Modal Conditioned Face Synthesis

no code implementations26 Dec 2023 Jingjing Ren, Cheng Xu, Haoyu Chen, Xinran Qin, Lei Zhu

Recent progress in multi-modal conditioned face synthesis has enabled the creation of visually striking and accurately aligned facial images.

Denoising Face Generation

Wildfire Smoke Detection with Cross Contrast Patch Embedding

1 code implementation16 Nov 2023 Chong Wang, Cheng Xu, Adeel Akram, Zhilin Shan, Qixing Zhang

By using two different negative instance sampling strategies on positive images and negative images respectively, the problem of supervision signal confusion caused by label diversity in the process of network training is alleviated.

AROT-COV23: A Dataset of 500K Original Arabic Tweets on COVID-19

1 code implementation 4th Workshop on African Natural Language Processing 2023 Cheng Xu, Nan Yan

This paper presents a dataset called AROT-COV23 (ARabic Original Tweets on COVID-19 as of 2023) containing about 500, 000 original Arabic COVID-19-related tweets from January 2020 to January 2023.

Singularity: Planet-Scale, Preemptive and Elastic Scheduling of AI Workloads

no code implementations16 Feb 2022 Dharma Shukla, Muthian Sivathanu, Srinidhi Viswanatha, Bhargav Gulavani, Rimma Nehme, Amey Agrawal, Chen Chen, Nipun Kwatra, Ramachandran Ramjee, Pankaj Sharma, Atul Katiyar, Vipul Modi, Vaibhav Sharma, Abhishek Singh, Shreshth Singhal, Kaustubh Welankar, Lu Xun, Ravi Anupindi, Karthik Elangovan, Hasibur Rahman, Zhou Lin, Rahul Seetharaman, Cheng Xu, Eddie Ailijiang, Suresh Krishnappa, Mark Russinovich

At the heart of Singularity is a novel, workload-aware scheduler that can transparently preempt and elastically scale deep learning workloads to drive high utilization without impacting their correctness or performance, across a global fleet of AI accelerators (e. g., GPUs, FPGAs).

Deep Learning Scheduling

Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection

1 code implementation16 Dec 2021 Shuaizheng Hao, Hongzhe Liu, Ningwei Wang, Cheng Xu

Common object detection models consist of classification and regression branches, due to different task drivers, these two branches have different sensibility to the features from the same scale level and the same spatial location.

object-detection Object Detection +1

Prediction of Prognosis and Survival of Patients with Gastric Cancer by Weighted Improved Random Forest Model

no code implementations Archives of Medical Science 2021 Cheng Xu, Jing Wang, TianLong Zheng, Yue Cao, Fan Ye

Among the 10 public datasets, the Random Forest weighted in accuracy has the best performance on 6 datasets, with an average increase of 1. 44% in accuracy and an average increase of 1. 2% in AUC.

Epidemiology

Detection and Classification of Breast Cancer Metastates Based on U-Net

no code implementations9 Sep 2019 Lin Xu, Cheng Xu, Yi Tong, Yu Chun Su

This paper presents U-net based breast cancer metastases detection and classification in lymph nodes, as well as patient-level classification based on metastases detection.

Classification General Classification

Infer Implicit Contexts in Real-time Online-to-Offline Recommendation

1 code implementation8 Jul 2019 Xichen Ding, Jie Tang, Tracy Liu, Cheng Xu, Yaping Zhang, Feng Shi, Qixia Jiang, Dan Shen

Understanding users' context is essential for successful recommendations, especially for Online-to-Offline (O2O) recommendation, such as Yelp, Groupon, and Koubei.

Rethinking Loss Design for Large-scale 3D Shape Retrieval

no code implementations3 Jun 2019 Zhaoqun Li, Cheng Xu, Biao Leng

In this paper, we propose the Collaborative Inner Product Loss (CIP Loss) to obtain ideal shape embedding that discriminative among different categories and clustered within the same class.

3D Object Retrieval 3D Shape Classification +2

Angular Triplet-Center Loss for Multi-view 3D Shape Retrieval

no code implementations21 Nov 2018 Zhaoqun Li, Cheng Xu, Biao Leng

How to obtain the desirable representation of a 3D shape, which is discriminative across categories and polymerized within classes, is a significant challenge in 3D shape retrieval.

3D Object Retrieval 3D Shape Classification +4

Learning Discriminative 3D Shape Representations by View Discerning Networks

2 code implementations11 Aug 2018 Biao Leng, Cheng Zhang, Xiaocheng Zhou, Cheng Xu, Kai Xu

In this network, a Score Generation Unit is devised to evaluate the quality of each projected image with score vectors.

3D Shape Recognition 3D Shape Representation +1

Double Supervised Network with Attention Mechanism for Scene Text Recognition

no code implementations2 Aug 2018 Yuting Gao, Zheng Huang, Yuchen Dai, Cheng Xu, Kai Chen, Jie Tuo

In this paper, we propose Double Supervised Network with Attention Mechanism (DSAN), a novel end-to-end trainable framework for scene text recognition.

Scene Text Recognition

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