Y
Ying Lu
Researcher at École centrale de Lyon
Publications - 11
Citations - 189
Ying Lu is an academic researcher from École centrale de Lyon. The author has contributed to research in topics: Discriminative model & Transfer of learning. The author has an hindex of 6, co-authored 10 publications receiving 158 citations.
Papers
More filters
Journal ArticleDOI
Discriminative Transfer Learning Using Similarities and Dissimilarities
TL;DR: A new discriminative TL (DTL) method is proposed, combining a series of hypotheses made by both the model learned with target training samples and the additional models learned with source category samples to improve classifier performance.
Journal ArticleDOI
Discriminative and Geometry-Aware Unsupervised Domain Adaptation
TL;DR: It is argued that an effective DA method for classification should: 1) search a shared feature subspace where the source and target data are not only aligned in terms of distributions as most state-of-the-art DA methods do but also discriminative in that instances of different classes are well separated.
Proceedings ArticleDOI
Combining Geometric, Textual and Visual Features for Predicting Prepositions in Image Descriptions
Arnau Ramisa,Josiah Wang,Ying Lu,Emmanuel Dellandréa,Francesc Moreno-Noguer,Robert Gaizauskas +5 more
TL;DR: This work investigates the role that geometric, textual and visual features play in the task of predicting a preposition that links two visual entities depicted in an image, and finds clear evidence that all three features contribute to the prediction task.
Journal ArticleDOI
Knowledge Transfer in Vision Recognition: A Survey
TL;DR: This survey firstly discusses the different kinds of reusable knowledge existing in a vision recognition task, and then categorize different knowledge transfer approaches depending on where the knowledge comes from andWhere the knowledge goes.
Posted Content
Discriminative and Geometry Aware Unsupervised Domain Adaptation
TL;DR: Zhang et al. as discussed by the authors proposed a discriminative and geometry-aware domain adaptation (DGA-DA) method, which considers the geometric structure of the underlying data manifold when inferring data labels on the target domain.