◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Lei Ke

23 papers hereh-index 232.9k citations29 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author10
  • middle author11
  • last author2

Across the 23 of 23 papers where every author was matched, so the position is known.

fields
  • cs.CV23
same name
  • Lei Ke — 8 papers, h 4
  • Lei Ke — 7 papers, h 2
  • Lei Ke — 6 papers, h 4
  • Lei Ke — 4 papers, h 6
  • Lei Ke — 3 papers, h 2
  • Lei Ke — 1 paper, h 1

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20192026
most citedCascaded deep monocular 3D human pose estimation with evolutionary training data

173 citations · 374 across the 20 of their papers we have counts for

collaborators
Showing 2021Show all

4 papers · 1 filter

cs.CV2021★ 2 cited

Mask Transfiner for High-Quality Instance Segmentation

Lei Ke, Martin Danelljan, Xia Li +3

Two-stage and query-based instance segmentation methods have achieved remarkable results. However, their segmented masks are still very coarse. In this paper, we present Mask Trans…

cs.CV2021

Occlusion-Aware Video Object Inpainting

Lei Ke, Yu-Wing Tai, Chi-Keung Tang

Conventional video inpainting is neither object-oriented nor occlusion-aware, making it liable to obvious artifacts when large occluded object regions are inpainted. This paper pre…

cs.CV2021★ 3 cited

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

Lei Ke, Xia Li, Martin Danelljan +3

Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes. Most approaches only exploit the temporal dimens…

cs.CV2021★ 8 cited

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

Lei Ke, Yu-Wing Tai, Chi-Keung Tang

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries. Unlike previous two-stage inst…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.