no code implementations • 6 May 2024 • Yanhong Bai, Jiabao Zhao, Jinxin Shi, Zhentao Xie, Xingjiao Wu, Liang He
Detecting stereotypes and biases in Large Language Models (LLMs) is crucial for enhancing fairness and reducing adverse impacts on individuals or groups when these models are applied.
no code implementations • 19 Nov 2023 • Weijie Li, Yitian Wan, Xingjiao Wu, Junjie Xu, Cheng Jin, Liang He
Then, to better utilize image attributes in aesthetic assessment, we propose the Unified Multi-attribute Aesthetic Assessment Framework (UMAAF) to model both absolute and relative attributes of images.
1 code implementation • 29 Oct 2023 • Anran Wu, Luwei Xiao, Xingjiao Wu, Shuwen Yang, Junjie Xu, Zisong Zhuang, Nian Xie, Cheng Jin, Liang He
Our DCQA dataset is expected to foster research on understanding visualizations in documents, especially for scenarios that require complex reasoning for charts in the visually-rich document.
no code implementations • 15 Oct 2023 • Shuwen Yang, Anran Wu, Xingjiao Wu, Luwei Xiao, Tianlong Ma, Cheng Jin, Liang He
Firstly, utilizing compressed evidence features as input to the model results in the loss of fine-grained information within the evidence.
no code implementations • 21 Aug 2023 • Yanhong Bai, Jiabao Zhao, Jinxin Shi, Tingjiang Wei, Xingjiao Wu, Liang He
Detecting stereotypes and biases in Large Language Models (LLMs) can enhance fairness and reduce adverse impacts on individuals or groups when these LLMs are applied.
1 code implementation • 13 Apr 2023 • Kangliang Liu, Xiangcheng Du, Sijie Liu, Yingbin Zheng, Xingjiao Wu, Cheng Jin
Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases.
1 code implementation • CVPR 2023 • Xin Li, Tao Ma, Yuenan Hou, Botian Shi, Yuchen Yang, Youquan Liu, Xingjiao Wu, Qin Chen, Yikang Li, Yu Qiao, Liang He
Notably, LoGoNet ranks 1st on Waymo 3D object detection leaderboard and obtains 81. 02 mAPH (L2) detection performance.
no code implementations • 18 Oct 2022 • Xin Li, Botian Shi, Yuenan Hou, Xingjiao Wu, Tianlong Ma, Yikang Li, Liang He
To address these problems, we construct the homogeneous structure between the point cloud and images to avoid projective information loss by transforming the camera features into the LiDAR 3D space.
no code implementations • 23 Jul 2022 • Xiangcheng Du, Zhao Zhou, Yingbin Zheng, Xingjiao Wu, Tianlong Ma, Cheng Jin
Scene text erasing seeks to erase text contents from scene images and current state-of-the-art text erasing models are trained on large-scale synthetic data.
no code implementations • 25 Jan 2022 • Luwei Xiao, Xingjiao Wu, Wen Wu, Jing Yang, Liang He
This paper proposes a Multi-channel Attentive Graph Convolutional Network (MAGCN), consisting of two main components: cross-modality interactive learning and sentimental feature fusion.
no code implementations • 24 Jan 2022 • Xingjiao Wu, Luwei Xiao, Xiangcheng Du, Yingbin Zheng, Xin Li, Tianlong Ma, Liang He
Our framework is an unsupervised document layout analysis framework.
no code implementations • 27 Nov 2021 • Tianlong Ma, Xingjiao Wu, Xin Li, Xiangcheng Du, Zhao Zhou, Liang Xue, Cheng Jin
To measure the proposed image layer modeling method, we propose a manually-labeled non-Manhattan layout fine-grained segmentation dataset named FPD.
no code implementations • Information Sciences 2021 • Xingjiao Wu, Yingbin Zheng, Tianlong Ma, Hao Ye, Liang He
Layout analysis from a document image plays an important role in document content understanding and information extraction systems.
no code implementations • 4 Aug 2021 • Xingjiao Wu, Tianlong Ma, Xin Li, Qin Chen, Liang He
The HITL select key samples by using confidence.
no code implementations • 2 Aug 2021 • Xingjiao Wu, Luwei Xiao, Yixuan Sun, Junhang Zhang, Tianlong Ma, Liang He
Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for computers in the pipeline with the help of machine-based approaches.
no code implementations • 7 Apr 2021 • Xingjiao Wu, Ziling Hu, Xiangcheng Du, Jing Yang, Liang He
The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document retrieval.
no code implementations • 4 Nov 2019 • Xiangcheng Du, Tianlong Ma, Yingbin Zheng, Hao Ye, Xingjiao Wu, Liang He
In this paper, we study text recognition framework by considering the long-term temporal dependencies in the encoder stage.
no code implementations • 4 Jul 2019 • Xingjiao Wu, Baohan Xu, Yingbin Zheng, Hao Ye, Jing Yang, Liang He
Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting.
1 code implementation • 6 Dec 2018 • Xingjiao Wu, Yingbin Zheng, Hao Ye, Wenxin Hu, Jing Yang, Liang He
Crowd counting, i. e., estimation number of the pedestrian in crowd images, is emerging as an important research problem with the public security applications.