researcher

Junwei Liang

HKUST (Guangzhou) | Tencent | Google | Carnegie Mellon University

13 papers hereh-index 161.4k citations41 works total

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

author position

first author7
middle author4
last author1

Across the 12 of 13 papers where every author was matched, so the position is known.

fields

cs.CV12
cs.MM1

affiliations

HKUST (Guangzhou) | Tencent | Google | Carnegie Mellon University

Homepage

same name

Junwei Liang — 22 papers, h 10
Junwei Liang — 12 papers, h 5
Junwei Liang — 4 papers, h 2
Junwei Liang — 4 papers, h 4
Junwei Liang — 3 papers, h 6
Junwei Liang — 2 papers, 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

20162023

most citedFocal Visual-Text Attention for Visual Question Answering

76 citations · 204 across the 13 of their papers we have counts for

collaborators

Showing 2016 · cs.CVShow all

1 paper · 2 filters

cs.CV2016★ 4 cited

Exploiting Multi-modal Curriculum in Noisy Web Data for Large-scale Concept Learning

Junwei Liang, Lu Jiang, Deyu Meng +1

Learning video concept detectors automatically from the big but noisy web data with no additional manual annotations is a novel but challenging area in the multimedia and the machi…