Mingyang Li

thulimy AT 163.com

I am a Ph.D. student in Tsinghua-Berkeley Shenzhen Institute(TBSI), Tsinghua University, advised by Prof.Shao-Lun Huang and Prof.Lin Zhang of Tsinghua University and Prof.Yi Ma of UC Berkeley. My research interests lying on multi-modal learning, representation learning and model robustness.

Selected Publication (* means equal contribution)
PontTuset Revisiting Sparse Convolutional Model for Visual Recognition
Xili Dai*, Mingyang Li*, Pengyuan Zhai, Peter(Shengbang) Tong, Xingjian Gao, Shao-Lun Huang, Zhihui Zhu, Chong You, Yi Ma
NeurIPS 2022

[code] [paper]

PontTuset Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction
Xili Dai*, Peter(Shengbang) Tong*, Mingyang Li*, Ziyang Wu*, Kwan Ho Ryan Chan, Pengyuan Zhai, Yaodong Yu, Michael Psenka, Xiaojun Yuan, Heung Yeung Shum, Yi Ma
Entropy(SCI)

[code] [paper]

PontTuset A General Framework for Incomplete Cross-modal Retrieval with Missing Labels and Missing Modalities
Mingyang Li, Shao-Lun Huang, Lin Zhang
ICASSP 2022

[code] [paper]

PontTuset OTCMR: Bridging Heterogeneity Gap with Optimal Transport for Cross-modal Retrieval
Mingyang Li, Shao-Lun Huang, Lin Zhang
CIKM 2021

[code] [paper]

PontTuset Semantically Supervised Maximal Correlation for Cross-modal Retrieval
Mingyang Li, Yang Li, Shao-Lun Huang, Lin Zhang
ICIP 2020

[code] [paper]

PontTuset Incremental Learning of Structured Memory via Closed-Loop Transcription
Peter(Shengbang) Tong, Xili Dai, Ziyang Wu, Mingyang Li, Brent Yi, Yi Ma
Arxiv

[code] [paper]