Xiao He

Xiao He (何潇) is a master student at degree China University of Geosciences, . He is supervised by Prof. Chang Tang and work with Pichao Wang.

Email  /  Google Scholar  /  Github

profile photo
News
  • [2024.08] One paper have been accepted by TKDE 2024.
  • [2024.07] One paper have been accepted by ACM MM 2024.
  • [2024.06] One paper have been accepted by IEEE JBHI 2024.
  • [2023.10] I won China National Scholarship for graduate students.
  • [2023.07] Two papers have been accepted by ACM MM 2024 (Oral).
  • [2023.07] One paper has been accepted by IEEE T-GRS.
  • More

Research

My research mainly focus on self-supervised learning/unsupervised learning, and their applications on graphs (e.g., graph clustering, KG embedding), language(e.g., LLMs, VLMs), recommendation systems, code intelligence, and bioinformatics.
* denotes equal contributions. The selected papers are listed as follows.

Heterogeneous Graph Guided Contrastive Learning for Spatially Resolved Transcriptomics Data
Xiao He, Chang Tang, Xinwang Liu, Chuankun Li, Shan An, Zhenglai Li
ACM MM (Oral), 2023
Paper / Code

We propose stGCL.

Multispectral Object Detection via Cross-Modal Conflict-Aware Learning
Xiao He, Chang Tang, Xin Zou, Wei Zhang
ACM MM (Oral), 2023
Paper / Code

We propose CALNet.

Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation
Xiao He, Chang Tang, Xinwang Liu, Wei Zhang, Kun Sun, Jiangfeng Xu
IEEE T-GRS , 2024
Paper / Code

We propose S2ADet and a News Dataset HOD3K.

Experience
  • Student Intern at Shanghai Artificial Intelligence Laboratory, 2024
Service
  • Reviewer for ACMMM'23/24
  • Reviewer for IEEE TIP, IEEE TCYB, IEEE TMM
  • Reviewer for Information Fusion, IEEE T-NNLS, Pattern Recognition
  • Reviewer for IEEE TCSVT, IEEE TGRS
Award
  • China National Scholarship for Graduate Student.
Miscellaneous

I enjoy playing Badminton🏸, Running🏃‍♂️, Hiking🥾 and Swimming🏊 with friends.

Web Site Hit Counter unique visitors since Nov 2022

Design and source code from Jon Barron's website