X
Xing Li
Researcher at Tsinghua University
Publications - Â 8
Citations - Â 234
Xing Li is an academic researcher from Tsinghua University. The author has contributed to research in topics: Image retrieval & Visual Word. The author has an hindex of 6, co-authored 8 publications receiving 231 citations.
Papers
More filters
Proceedings ArticleDOI
Multi-model similarity propagation and its application for web image retrieval
TL;DR: An iterative similarity propagation approach to explore the inter-relationships between Web images and their textual annotations for image retrieval and shows that the proposed approach can significantly improve Web image retrieval performance.
Proceedings ArticleDOI
Data-driven approach for bridging the cognitive gap in image retrieval
TL;DR: A data-driven approach that uses Web images and their surrounding textual annotations as the source of training data to bridge the cognitive gap is proposed and an image thesaurus is constructed that contains a set of codewords each representing a semantically related subspace in the feature space.
Proceedings ArticleDOI
Grouping web image search result
TL;DR: A Web image search result organizing method to facilitate user browsing by segmenting the images into homogeneous regions and quantizing the environmental regions into image codewords, which are then extracted and ranked based on a regression model learned from human labeled training data.
Proceedings ArticleDOI
Iteratively clustering web images based on link and attribute reinforcements
TL;DR: A reinforcement clustering framework that reinforces images and texts' attributes via inter-type links and inversely uses these attributes to update these links to promise the discovery of the semantic structure of images, which is the basis of image clustering.
Journal ArticleDOI
Exploring statistical correlations for image retrieval
TL;DR: A Context Expansion approach is explored to take advantages of such correlations by expanding the key regions of the queries using highly correlated environmental regions according to an image thesaurus to improve the performance of image retrieval.