Rui Gan — accepted AI-conference papers

2024

Correcting Pronoun Homophones with Subtle Semantics in Chinese Speech Recognition

Zhaobo Zhang, Rui Gan, Pingpeng Yuan, Hai Jin

COLING 2024main

Speech recognition is becoming prevalent in daily life. However, due to the similar semantic context of the entities and the overlap of Chinese pronunciation, the pronoun homophone, especially “他/她/它 (he/she/it)”, (their pronunciation is “Tā”) is usually recognized incorrectly. It poses a challenge…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2017

Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF

Falong Shen, Rui Gan, Shuicheng Yan, Gang Zeng

CVPR 2017poster

This paper describes a fast and accurate semantic image segmentation approach that encodes not only segmentation-specified features but also high-order context compatibilities and boundary guidance constraints. We introduce a structured patch prediction technique to make a trade-off between classifi…

Cited by 79 PDF ↗code ↗Scholar ↗