Y
Yichen Wei
Researcher at Microsoft
Publications - 115
Citations - 24370
Yichen Wei is an academic researcher from Microsoft. The author has contributed to research in topics: Object detection & Pose. The author has an hindex of 48, co-authored 114 publications receiving 17410 citations. Previous affiliations of Yichen Wei include Fudan University & Northwestern University.
Papers
More filters
Efficient Optimization of Photo Collage
TL;DR: This paper presents efficient optimization techniques based on a novel formulation on markov random fields and several insights unexploited by previous approaches that achieves up to hundreds-fold performance improvement, and user/application specific constraints can be easily integrated.
Patent
Unsupervised object class discovery via bottom up multiple class learning
TL;DR: In this article, a method for unsupervised object class discovery via bottom-up multiple class learning is described, which can include receiving multiple images containing one or more object classes.
Posted Content
Simple Baselines for Human Pose Estimation and Tracking
Bin Xiao,Haiping Wu,Yichen Wei +2 more
TL;DR: In this article, the authors provide simple and effective baseline methods for pose estimation and compare them with the state-of-the-art methods in the field of human pose estimation.
Patent
Dynamic Collage for Visualizing Large Photograph Collections
Yichen Wei,Yasuyuki Matsushita +1 more
TL;DR: In this article, a dynamic collage mechanism coupled to a source of photographs computes a collage for visible output, and dynamically updates the collage on a scheduled basis by adding different photograph(s) in place of other photographs(s).
Proceedings ArticleDOI
Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
TL;DR: In this article, the authors introduce a new fundamental characteristic, i.e., the dynamic range, from real-world metric tools to deep visual recognition, and learn a scalable metric space to accommodate visual concepts across multiple semantic scales.