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
Book ChapterDOI
Self-challenging Improves Cross-Domain Generalization.
TL;DR: A simple training heuristic, Representation Self-Challenging (RSC), is introduced that significantly improves the generalization of CNN to the out-of-domain data and is presented theoretical properties and conditions of RSC for improving cross-domain generalization.
Proceedings ArticleDOI
Entity Hierarchy Embedding
TL;DR: This work proposes a principled framework of embedding entities that integrates hierarchical information from large-scale knowledge bases and shows that both the entity vectors and category distance metrics encode meaningful semantics.
Proceedings Article
Sparse topical coding
Jun Zhu,Eric P. Xing +1 more
TL;DR: The sparse topical coding (STC) as discussed by the authors is a non-probabilistic formulation of topic models for discovering latent representations of large collections of data, which relaxes the normalization constraint of admixture proportions and the constraint of defining a normalized likelihood function.
Proceedings Article
Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM
TL;DR: A novel notion of semantic saliency is defined that assesses the relevance of each shot with the event of interest and prioritize the shots according to their saliency scores since shots that are semantically more salient are expected to contribute more to the final event detector.
Proceedings Article
Online Inference for the Infinite Topic-Cluster Model: Storylines from Streaming Text
TL;DR: The time-dependent topic-cluster model is presented, a hierarchical approach for combining Latent Dirichlet Allocation and clustering via the Recurrent Chinese Restaurant Process which inherits the advantages of both of its constituents, namely interpretability and concise representation.