Search

Your search keyword '"WANG, Dongsheng"' showing total 4,861 results
Start Over Author "WANG, Dongsheng"
4,861 results on '"WANG, Dongsheng"'

52. Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings

Author

Wang, Dongsheng, Guo, Dandan, Zhao, He, Zheng, Huangjie, Tanwisuth, Korawat, Chen, Bo, and Zhou, Mingyuan

Subjects
Computer Science - Machine Learning, Statistics - Methodology, Statistics - Machine Learning
Abstract

A topic model is often formulated as a generative model that explains how each word of a document is generated given a set of topics and document-specific topic proportions. It is focused on capturing the word co-occurrences in a document and hence often suffers from poor performance in analyzing short documents. In addition, its parameter estimation often relies on approximate posterior inference that is either not scalable or suffers from large approximation error. This paper introduces a new topic-modeling framework where each document is viewed as a set of word embedding vectors and each topic is modeled as an embedding vector in the same embedding space. Embedding the words and topics in the same vector space, we define a method to measure the semantic difference between the embedding vectors of the words of a document and these of the topics, and optimize the topic embeddings to minimize the expected difference over all documents. Experiments on text analysis demonstrate that the proposed method, which is amenable to mini-batch stochastic gradient descent based optimization and hence scalable to big corpora, provides competitive performance in discovering more coherent and diverse topics and extracting better document representations., Comment: Proceedings of ICLR, 2022

Published
2022

78. Short Range Correlation Transformer for Occluded Person Re-Identification

Author

Zhao, Yunbin, Zhu, Songhao, Wang, Dongsheng, and Liang, Zhiwei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Occluded person re-identification is one of the challenging areas of computer vision, which faces problems such as inefficient feature representation and low recognition accuracy. Convolutional neural network pays more attention to the extraction of local features, therefore it is difficult to extract features of occluded pedestrians and the effect is not so satisfied. Recently, vision transformer is introduced into the field of re-identification and achieves the most advanced results by constructing the relationship of global features between patch sequences. However, the performance of vision transformer in extracting local features is inferior to that of convolutional neural network. Therefore, we design a partial feature transformer-based person re-identification framework named PFT. The proposed PFT utilizes three modules to enhance the efficiency of vision transformer. (1) Patch full dimension enhancement module. We design a learnable tensor with the same size as patch sequences, which is full-dimensional and deeply embedded in patch sequences to enrich the diversity of training samples. (2) Fusion and reconstruction module. We extract the less important part of obtained patch sequences, and fuse them with original patch sequence to reconstruct the original patch sequences. (3) Spatial Slicing Module. We slice and group patch sequences from spatial direction, which can effectively improve the short-range correlation of patch sequences. Experimental results over occluded and holistic re-identification datasets demonstrate that the proposed PFT network achieves superior performance consistently and outperforms the state-of-the-art methods.

Published
2022

90. Entering a Data Era

Author

Xu, Guanghui, Wang, Dongsheng, Chen, Sheng-Hong, Series Editor, di Prisco, Marco, Series Editor, Vayas, Ioannis, Series Editor, Xu, Guanghui, Wang, Dongsheng, Chang, George K., Translated by, Wang, Hao, Translated by, Wang, Fei, Translated by, Shen, Shihui, Translated by, Gomes Correia, António, Translated by, and Nazarian, Soheil, Translated by

Published
2023
Full Text
View/download PDF

91. Empowering Machines to Learn

Author

Xu, Guanghui, Wang, Dongsheng, Chen, Sheng-Hong, Series Editor, di Prisco, Marco, Series Editor, Vayas, Ioannis, Series Editor, Xu, Guanghui, Wang, Dongsheng, Chang, George K., Translated by, Wang, Hao, Translated by, Wang, Fei, Translated by, Shen, Shihui, Translated by, Gomes Correia, António, Translated by, and Nazarian, Soheil, Translated by

Published
2023
Full Text
View/download PDF

92. Intelligent Engineering Construction

Author

Xu, Guanghui, Wang, Dongsheng, Chen, Sheng-Hong, Series Editor, di Prisco, Marco, Series Editor, Vayas, Ioannis, Series Editor, Xu, Guanghui, Wang, Dongsheng, Chang, George K., Translated by, Wang, Hao, Translated by, Wang, Fei, Translated by, Shen, Shihui, Translated by, Gomes Correia, António, Translated by, and Nazarian, Soheil, Translated by

Published
2023
Full Text
View/download PDF

93. The Road to the Future

Author

Xu, Guanghui, Wang, Dongsheng, Chen, Sheng-Hong, Series Editor, di Prisco, Marco, Series Editor, Vayas, Ioannis, Series Editor, Xu, Guanghui, Wang, Dongsheng, Chang, George K., Translated by, Wang, Hao, Translated by, Wang, Fei, Translated by, Shen, Shihui, Translated by, Gomes Correia, António, Translated by, and Nazarian, Soheil, Translated by

Published
2023
Full Text
View/download PDF

94. Systematic Approach to Representing Objects

Author

Xu, Guanghui, Wang, Dongsheng, Chen, Sheng-Hong, Series Editor, di Prisco, Marco, Series Editor, Vayas, Ioannis, Series Editor, Xu, Guanghui, Wang, Dongsheng, Chang, George K., Translated by, Wang, Hao, Translated by, Wang, Fei, Translated by, Shen, Shihui, Translated by, Gomes Correia, António, Translated by, and Nazarian, Soheil, Translated by

Published
2023
Full Text
View/download PDF

95. Understanding Perception Technology

Author

Xu, Guanghui, Wang, Dongsheng, Chen, Sheng-Hong, Series Editor, di Prisco, Marco, Series Editor, Vayas, Ioannis, Series Editor, Xu, Guanghui, Wang, Dongsheng, Chang, George K., Translated by, Wang, Hao, Translated by, Wang, Fei, Translated by, Shen, Shihui, Translated by, Gomes Correia, António, Translated by, and Nazarian, Soheil, Translated by

Published
2023
Full Text
View/download PDF

96. What is Intelligent Construction?

Author

Xu, Guanghui, Wang, Dongsheng, Chen, Sheng-Hong, Series Editor, di Prisco, Marco, Series Editor, Vayas, Ioannis, Series Editor, Xu, Guanghui, Wang, Dongsheng, Chang, George K., Translated by, Wang, Hao, Translated by, Wang, Fei, Translated by, Shen, Shihui, Translated by, Gomes Correia, António, Translated by, and Nazarian, Soheil, Translated by

Published
2023
Full Text
View/download PDF

97. TopicNet: Semantic Graph-Guided Topic Discovery

Author

Duan, Zhibin, Xu, Yishi, Chen, Bo, Wang, Dongsheng, Wang, Chaojie, and Zhou, Mingyuan

Subjects
Computer Science - Machine Learning, Computer Science - Information Retrieval
Abstract

Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy. However, it is unclear how to incorporate prior beliefs such as knowledge graph to guide the learning of the topic hierarchy. To address this issue, we introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as an inductive bias to influence learning. TopicNet represents each topic as a Gaussian-distributed embedding vector, projects the topics of all layers into a shared embedding space, and explores both the symmetric and asymmetric similarities between Gaussian embedding vectors to incorporate prior semantic hierarchies. With an auto-encoding variational inference network, the model parameters are optimized by minimizing the evidence lower bound and a regularization term via stochastic gradient descent. Experiments on widely used benchmarks show that TopicNet outperforms related deep topic models on discovering deeper interpretable topics and mining better document~representations.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results