Skip to content

Latest commit

 

History

History
48 lines (30 loc) · 4.2 KB

index.md

File metadata and controls

48 lines (30 loc) · 4.2 KB

About me

Now I am a third-year Ph.D student in the GeWu-Lab, Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu. Now my main research focuses on multimodal learning towards real-world scene understanding, aiming to guide the machine to perceive and understand natural scenes like human beings.

I have received my master's dergee in the Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, advised by Prof. Longjun Liu, in June 2021. Before that, I got my bachelor's degree in the Honors College, Northwestern Polytechnical University, in June 2018. I also have several industrial work experiences, in iFlytek, Baidu, and Tencent, respectively.

Research interests

2018~2021   Neural architecture search and its application.

2022~   Multimodal learning and sence understanding.

Education

  • 2014.09~2018.06   B.E. in Automation,
    Northwestern Polytechnical University.

  • 2018.09~2021.06   M.S. in Control Science and Engineering,
    Xi'an Jiaotong University.

  • 2022.09~    Ph.D in Artificial Intelligence,
    Renmin University of China.

Work Experience

  • 2020.07~2020.09   Research intern, iFlytek AI Research.
  • 2021.07~2022.03   R&D, Intelligent Driving Group, Baidu.
  • 2022.04~2022.08   Research assistant, Renmin University of China.
  • 2023.08~2024.08   Research intern, Wechat advertisement department, Corporate Development Group, Tencent.

Publication

  • Wenxuan Hou†, Guangyao Li†, Yapeng Tian, and Di Hu. Towards Long Form Audio-visual Video Understanding. ACM TOMM 2024. project page, link
  • Wenxuan Hou, Ruoxuan Feng, Yixin Xu, Yapeng Tian, and Di Hu. Towards Better Egocentric Action Understanding in a Multi-Input Multi-Output View. ICCV 2023 AV4D Workshop. link
  • Guangyao Li, Wenxuan Hou, and Di Hu. Progressive Spatio-temporal Perception for Audio-Visual Question Answering. ACM MM 2023. link
  • Wenxuan Hou, Longjun Liu, Haonan Zhang, Hongbin Sun, and Nanning Zheng. DFSNet: Dividing-Fuse Deep Neural Networks with Searching Strategy for Distributed DNN Architecture. Neurocomputing, 2021. link
  • Haonan Zhang, Longjun Liu, Hengyi Zhou, Wenxuan Hou, Hongbin Sun, and and Nanning Zheng. AKECP: Adaptive Knowledge Extraction from Feature Maps for Fast and Efficient Channel Pruning. ACM MM 2021. link
  • Anguo Zhu, Longjun Liu, Wenxuan Hou, Hongbin Sun, and Nanning Zheng. HSC: Leveraging horizontal shortcut connections for improving accuracy and computational efficiency of lightweight CNN. Neurocomputing, 2021. link
  • Wenxuan Hou, Longjun Liu, Jinxia Gao, Anguo Zhu, Keyang Pan, Hongbin Sun, and Nanning Zheng. Exploring Effective DNN Models for Forensic Age Estimation based on Panoramic Radiograph Images. IJCNN 2021. link
  • Jinxia Gao, Longjun Liu, Peng Gao, Yihuan Zheng, Wenxuan Hou, and Junhui Wang. Intelligent occlusion stabilization splint with stress-sensor system for bruxism diagnosis and treatment. Sensors, 2020. link

Academic Services

  • Conference Reviewer: AAAI 2024, IJCAI 2025, AAAI 2025.
  • Journal Reviewer: IJCV, TMM, TASLP.