← Search

Jason Chang

2 accepted papers

2021

Context-Aware Scene Graph Generation With Seq2Seq Transformers

ICCV 2021poster

Scene graph generation is an important task in computer vision aimed at improving the semantic understand- ing of the visual world. In this task, the model needs to detect objects and predict visual relationships between them. Most of the existing models predict relationships in parallel assuming th…

Cited by 98PDFcodeScholar
2015

A Dirichlet Process Mixture Model for Spherical Data

AISTATS 2015poster

Directional data, naturally represented as points on the unit sphere, appear in many applications. However, unlike the case of Euclidean data, flexible mixture models on the sphere that can capture correlations, handle an unknown number of components and extend readily to high-dimensional data have…

Cited by 69SourcePDFScholar