no code implementations • 3 May 2023 • Chen Zhu, Liang Du, Xin Wang, Wenwu Zhu
Click-Through Rate (CTR) prediction is the most critical task in product and content recommendation, and learning effective feature interaction is the key challenge to exploiting user preferences for products.
no code implementations • 4 Mar 2023 • Shima Imani, Liang Du, Harsh Shrivastava
Large Language Models (LLMs) have limited performance when solving arithmetic reasoning tasks and often provide incorrect answers.
no code implementations • 15 Jan 2023 • Jiayi Han, Longbin Zeng, Liang Du, Weiyang Ding, Jianfeng Feng
In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions.
no code implementations • 11 Oct 2022 • Yue He, Minyue Jiang, Xiaoqing Ye, Liang Du, Zhikang Zou, Wei zhang, Xiao Tan, Errui Ding
In this paper, we target at finding an enhanced feature space where the lane features are distinctive while maintaining a similar distribution of lanes in the wild.
no code implementations • 24 Aug 2022 • Liang Du, Xiaoqing Ye, Xiao Tan, Edward Johns, Bo Chen, Errui Ding, xiangyang xue, Jianfeng Feng
A feasible method is investigated to construct conceptual scenes without external datasets.
no code implementations • ICCV 2021 • Zhikang Zou, Xiaoqing Ye, Liang Du, Xianhui Cheng, Xiao Tan, Li Zhang, Jianfeng Feng, xiangyang xue, Errui Ding
Low-cost monocular 3D object detection plays a fundamental role in autonomous driving, whereas its accuracy is still far from satisfactory.
1 code implementation • 3 Dec 2021 • Zheyuan Zhou, Liang Du, Xiaoqing Ye, Zhikang Zou, Xiao Tan, Li Zhang, xiangyang xue, Jianfeng Feng
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image.
no code implementations • 20 Sep 2021 • Xiaoyuan Fan, Daniel Moscovitz, Liang Du, Walid Saad
As probably the most complicated and critical infrastructure system, U. S. power grids become increasingly vulnerable to extreme events such as cyber-attacks and severe weather, as well as higher DER penetrations and growing information mismatch among system operators, utilities (transmission or generation owners), and end-users.
no code implementations • ACL 2022 • Zhihui Guo, Pramod Sharma, Andy Martinez, Liang Du, Robin Abraham
Molecular representation learning plays an essential role in cheminformatics.
no code implementations • 30 Jul 2021 • Ruobin Gao, Liang Du, P. N. Suganthan, Qin Zhou, Kum Fai Yuen
Electricity load forecasting is crucial for the power systems' planning and maintenance.
1 code implementation • CVPR 2021 • Li Wang, Liang Du, Xiaoqing Ye, Yanwei Fu, Guodong Guo, xiangyang xue, Jianfeng Feng, Li Zhang
The objective of this paper is to learn context- and depth-aware feature representation to solve the problem of monocular 3D object detection.
Ranked #10 on Monocular 3D Object Detection on KITTI Cars Moderate
no code implementations • 30 Sep 2020 • Liang Du, Haiying Zhang, Xin Ren, Xiaolin Lv
Multiple kernel methods based on k-means aims to integrate a group of kernels to improve the performance of kernel k-means clustering.
no code implementations • CVPR 2020 • Liang Du, Xiaoqing Ye, Xiao Tan, Jianfeng Feng, Zhenbo Xu, Errui Ding, Shilei Wen
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques.
no code implementations • 1 Mar 2020 • Liang Du, Jingang Tan, xiangyang xue, Lili Chen, Hongkai Wen, Jianfeng Feng, Jiamao Li, Xiaolin Zhang
We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation.
no code implementations • 4 Nov 2019 • Shen Zhang, Shibo Zhang, Sufei Li, Liang Du, Thomas G. Habetler
However, the number of objectives that would need to be optimized would significantly increase with the number of operating points considered in the optimization, thus posting a potential problem in regards to the visualization techniques currently in use, such as in the scatter plots of Pareto fronts, the parallel coordinates, and in the principal component analysis (PCA), inhibiting their ability to provide machine designers with intuitive and informative visualizations of all of the design candidates and their ability to pick a few for further fine-tuning with performance verification.
no code implementations • ICCV 2019 • Liang Du, Jingang Tan, Hongye Yang, Jianfeng Feng, Xiangyang Xue, Qibao Zheng, Xiaoqing Ye, Xiaolin Zhang
Despite the great success achieved by supervised fully convolutional models in semantic segmentation, training the models requires a large amount of labor-intensive work to generate pixel-level annotations.
no code implementations • ECCV 2018 • Xiaoqing Ye, Jiamao Li, Hexiao Huang, Liang Du, Xiaolin Zhang
Semantic segmentation of 3D unstructured point clouds remains an open research problem.
no code implementations • CVPR 2015 • Liang Du, Haibin Ling
As shown in our experiments, the algorithm effectively balances feature sharing and feature exclusion between the two tasks; and, for face verification, the algorithm effectively removes distracting features used in age verification.
1 code implementation • 3 Apr 2015 • Liang Du, Yi-Dong Shen
Traditional unsupervised methods select the features which can faithfully preserve the intrinsic structures of data, where the intrinsic structures are estimated using all the input features of data.
no code implementations • 25 Sep 2014 • Liang Wu, Hui Xiong, Liang Du, Bo Liu, Guandong Xu, Yong Ge, Yanjie Fu, Yuanchun Zhou, Jianhui Li
Specifically, this method can capture both the inherent information in the source codes and the semantic information hidden in the comments, descriptions, and identifiers of the source codes.