E
Eric P. Xing
Researcher at Carnegie Mellon University
Publications - 725
Citations - 48035
Eric P. Xing is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Inference & Topic model. The author has an hindex of 99, co-authored 711 publications receiving 41467 citations. Previous affiliations of Eric P. Xing include Microsoft & Intel.
Papers
More filters
Proceedings Article
Record-to-Text Generation with Style Imitation.
TL;DR: A new way of stylistic control is studied by using existing sentences as “soft” templates, that is, a model learns to imitate the writing style of any given exemplar sentence, with automatic adaptions to faithfully describe the record.
Book ChapterDOI
Multi-Level structured image coding on high-dimensional image representation
TL;DR: A novel Multi-Level Structured Image Coding approach to uncover the structure embedded in representations with rich regular structural information by learning a structured dictionary from Object Bank, which can compute a lower-dimensional and more compact encoding of the image features while preserving and accentuating the rich semantic and spatial information of OB.
Posted Content
Learning HMMs with Nonparametric Emissions via Spectral Decompositions of Continuous Matrices
TL;DR: This paper studies the estimation of an $m$-state hidden Markov model (HMM) with only smoothness assumptions, such as Holderian conditions, on the emission densities and develops a computationally efficient spectral algorithm for learning nonparametric HMMs.
Proceedings ArticleDOI
Big Data: New Paradigm or "Sound and Fury, Signifying Nothing"?
TL;DR: A distinguished panel of eminent scientists, from both Industry and Academia, will share their point of view and take questions from the moderator and the audience to answer what Big Data means from a scientific perspective.
Journal ArticleDOI
Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion
TL;DR: Semantic-Aligned-Matching DETR++ (SAM-DETR++) is a plug-and-play module that projects object queries and encoded image features into the same feature embedding space, where each object query can be easily matched to relevant regions with similar semantics.