Search

Your search keyword '"Zhang, Yongdong"' showing total 550 results
Start Over Author "Zhang, Yongdong" Language english
550 results on '"Zhang, Yongdong"'

26. PCSK9 inhibitor recaticimab for hypercholesterolemia on stable statin dose: a randomized, double-blind, placebo-controlled phase 1b/2 study

Author

Xu, Mingtong, Zhu, Xiaoxue, Wu, Junyan, Zhang, Yuling, Zhao, Dong, Wang, Xuhong, Ding, Yanhua, Cao, Yu, Li, Chengqian, Hu, Wei, Sheng, Jianlong, Luo, Zhu, Zheng, Zeqi, Hu, Jinfang, Liu, Jianying, Zhou, Xiaoyang, Shen, Aizong, Ding, Xiaomei, Zhang, Yongdong, Zhao, Yonggang, Li, Yijing, Zhong, Sheng, An, Shimin, Zou, Jianjun, and Yan, Li

Published
2022
Full Text
View/download PDF

29. Exploring Visual Relationships via Transformer-based Graphs for Enhanced Image Captioning.

Author

Li, Jingyu, Mao, Zhendong, Li, Hao, Chen, Weidong, and Zhang, Yongdong

Subjects
JOINTS (Engineering), IMAGE representation, PRIOR learning, IMAGE reconstruction algorithms
Abstract

Image captioning (IC), bringing vision to language, has drawn extensive attention. A crucial aspect of IC is the accurate depiction of visual relations among image objects. Visual relations encompass two primary facets: content relations and structural relations. Content relations, which comprise geometric positions content (i.e., distances and sizes) and semantic interactions content (i.e., actions and possessives), unveil the mutual correlations between objects. In contrast, structural relations pertain to the topological connectivity of object regions. Existing Transformer-based methods typically resort to geometric positions to enhance the visual relations, yet only using the shallow geometric content is unable to precisely cover actional content correlations and structural connection relations. In this article, we adopt a comprehensive perspective to examine the correlations between objects, incorporating both content relations (i.e., geometric and semantic relations) and structural relations, with the aim of generating plausible captions. To achieve this, first, we construct a geometric graph from bounding box features and a semantic graph from the scene graph parser to model the content relations. Innovatively, we construct a topology graph that amalgamates the sparsity characteristics of the geometric and semantic graphs, enabling the representation of image structural relations. Second, we propose a novel unified approach to enrich image relation representations by integrating semantic, geometric, and structural relations into self-attention. Finally, in the language decoding stage, we further leverage the semantic relation as prior knowledge to generate accurate words. Extensive experiments on MS-COCO dataset demonstrate the effectiveness of our model, with improvements of CIDEr from 128.6% to 136.6%. Codes have been released at https://github.com/CrossmodalGroup/ER-SAN/tree/main/VG-Cap. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

32. Rumor propagation model with neutral state.

Author

Qiao, Xinran, Wang, Lanjun, Wang, Xiaowen, Zhu, Mengxiao, Hu, Bo, Zhang, Yongdong, and Liu, A.-A.

Subjects
RUMOR, SOCIAL networks, FAKE news, DYNAMICAL systems, MEDICAL model
Abstract

The development of social networks provides a broad platform for the dissemination of information and also leads to the proliferation of fake news and false information, which we collectively refer to as rumors. The spread of rumors causes unnecessary panic and loss to individuals and society. To reduce the negative impacts of rumors, an appropriate rumor control strategy is necessary. To come up with some reasonable strategies, we need to have a clearer understanding of the spread of rumors. In this paper, we analyze crowd attitudes during the spreading of rumors by setting the misinformation prevalent progress on the social network as a dynamic system. Considering that most people do not have a clear supportive or opposing attitude when exposed to rumor information, we introduce a new group, stiflers who remain neutral, based on the infectious disease model scheme. By deriving the mean-field equation describing the rumor propagation process, we judge the stability of the constructed model. Finally, we use the model to fit the real-world data related to COVID-19, and based on this, we discuss the properties of the model and propose related strategies. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

41. ExpertPrompting: Instructing Large Language Models to be Distinguished Experts

Author

Xu, Benfeng, Yang, An, Lin, Junyang, Wang, Quan, Zhou, Chang, Zhang, Yongdong, and Mao, Zhendong

Subjects
FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computation and Language (cs.CL)
Abstract

The answering quality of an aligned large language model (LLM) can be drastically improved if treated with proper crafting of prompts. In this paper, we propose ExpertPrompting to elicit the potential of LLMs to answer as distinguished experts. We first utilize In-Context Learning to automatically synthesize detailed and customized descriptions of the expert identity for each specific instruction, and then ask LLMs to provide answer conditioned on such agent background. Based on this augmented prompting strategy, we produce a new set of instruction-following data using GPT-3.5, and train a competitive open-source chat assistant called ExpertLLaMA. We employ GPT4-based evaluation to show that 1) the expert data is of significantly higher quality than vanilla answers, and 2) ExpertLLaMA outperforms existing open-source opponents and achieves 96\% of the original ChatGPT's capability. All data and the ExpertLLaMA model will be made publicly available at \url{https://github.com/OFA-Sys/ExpertLLaMA}.

Published
2023

42. Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization

Author

Huang, Mengqi, Mao, Zhendong, Chen, Zhuowei, and Zhang, Yongdong

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they encode fixed-size image regions into fixed-length codes and ignore their naturally different information densities, which results in insufficiency in important regions and redundancy in unimportant ones, and finally degrades the generation quality and speed. Moreover, the fixed-length coding leads to an unnatural raster-scan autoregressive generation. To address the problem, we propose a novel two-stage framework: (1) Dynamic-Quantization VAE (DQ-VAE) which encodes image regions into variable-length codes based on their information densities for an accurate and compact code representation. (2) DQ-Transformer which thereby generates images autoregressively from coarse-grained (smooth regions with fewer codes) to fine-grained (details regions with more codes) by modeling the position and content of codes in each granularity alternately, through a novel stacked-transformer architecture and shared-content, non-shared position input layers designs. Comprehensive experiments on various generation tasks validate our superiorities in both effectiveness and efficiency. Code will be released at https://github.com/CrossmodalGroup/DynamicVectorQuantization., CVPR 2023

Published
2023

43. Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition

Author

Zhang, Boqiang, Xie, Hongtao, Wang, Yuxin, Xu, Jianjun, and Zhang, Yongdong

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. However, due to lacking the perception of linguistic knowledge and information, recent vision models suffer from two problems: (1) the pure vision-based query results in attention drift, which usually causes poor recognition and is summarized as linguistic insensitive drift (LID) problem in this paper. (2) the visual feature is suboptimal for the recognition in some vision-missing cases (e.g. occlusion, etc.). To address these issues, we propose a $\textbf{L}$inguistic $\textbf{P}$erception $\textbf{V}$ision model (LPV), which explores the linguistic capability of vision model for accurate text recognition. To alleviate the LID problem, we introduce a Cascade Position Attention (CPA) mechanism that obtains high-quality and accurate attention maps through step-wise optimization and linguistic information mining. Furthermore, a Global Linguistic Reconstruction Module (GLRM) is proposed to improve the representation of visual features by perceiving the linguistic information in the visual space, which gradually converts visual features into semantically rich ones during the cascade process. Different from previous methods, our method obtains SOTA results while keeping low complexity (92.4% accuracy with only 8.11M parameters). Code is available at https://github.com/CyrilSterling/LPV., Accepted to IJCAI 2023

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results