Junhua Liu

Junhua Liu
Undergraduate Student
Research assistant at FNii; Research intern at Sensetime
Second Floor, Zhixin Building, Shenzhen, Guangdong, China, 518172

junhualiu at cuhk dot edu dot en, jeshualiu at gmail dot com

Email  /  CV  /  Google Scholar  /  Github  /  Twitter  /  Research Statement  / 


I am currently a third-year B.S. student advised by Prof. Fangxin Wang at The Future Network of Intelligence Institute. Recently, I am research intern at SenseTime Research advised by Prof. Yan Wang and Yuanyuan Wang, and visiting scholar at Carnegie Mellon University advised by Prof. Anthony Rowe. My broad interest lies at the intersection of computer network, omnidirectional vision and human computer interaction with a current focus on Emerging Multimedia Systems for AR/VR, AGI and AIGC applications.

Prior to that, I am honored to be research assistant conducting HCI at Harvard CAMLab and dialogue system at AIRS NLP group. I am also lucky to learn research from Prof. Shuguang Cui, Prof. Huazhe Xu, Prof. Zeyu Wang, Prof. Yan Song.

I am looking for 24 Fall PhD position. Feel free to email me if you are interested.


New

Dec 2022
One paper was accepted by IEEE VR 2023 as first author
June 2022
I joined the Video Codec group in SenseTime Research Institute as a Research Intern.
June 2022
One paper was accepted by ACM MM 2022 as co-first author.
Mar 2022
I joined the Harvard Univ. as a Research Assistant.
Sep 2022
I joined the Intelligent Networking and Multimedia Lab as a Research Assistant.
July 2022
I joined NLP Lab in AIRS as a Research Assistant.
Dec 2021
One paper was accepted by IEEE VR 2022 as short paper.

Publications

Show selected publication/ show all by date / show all by topic/ full publications & under review
Conference

Fumos: Scalable Plug-and-play Architecture for Progressive 3D Video Streaming Arxiv 23

First author. In submission, 2023. (Preprint accessible by Email)

You only stream weights: Fast, Adaptive, Unified Internet Streaming Arxiv 23

First author. In submission, 2023. (Preprint accessible by Email)

FSVVD: A Dataset of Full Scene Volumetric Video MMSys'23

Kaiyuan Hu, Yili Jin, Haowen Yang, Junhua Liu, Fangxin Wang
ACM Multimedia Systems (MMSys), 2023. (Top conference in Multimedia)

Junhua Liu, Yuanyuan Wang, Mallesh Dasari, Yan Wang, Yufeng Wang, Shuguang Cui, Fangxin Wang
In submission, 2023.

CaV3: Cache-assisted Viewport Adaptive Volumetric Video Streaming VR 23

Junhua Liu, Boxiang Zhu, Fangxin Wang, Yili Jin, Wenyi Zhang, Zihan Xu, Shuguang Cui.
IEEE Virtual Reality and 3D User Interfaces (IEEE VR)(Oral)(CCF-A), 2023.

Where Are You Looking? A Large-Scale Dataset of Head and Gaze Behavior for 360-Degree Videos and a Pilot Study. MM 23

Yili Jin*, Junhua Liu*, Fangxin Wang, Shuguang Cui
ACM Multimedia (MM)(CCF-A), 2022.

Journal

IoTJ 23

Yili Jin, Junhua Liu, Fangxin Wang, Shuguang Cui
IEEE Internet of Things Journal (JCR Q1), 2023. Extended version of VR 2022.


Academic Service

  • Conference reviewer: ICASSP 2023, IEEE VR 2023, ACM MM 2023
  • Journal reviewer:

Teaching

  • To be updated

Software and Dataset

Volumetric Video
Volumetric Video of Full scene [MMSys'23]
360-degree Video
Large-Scale Dataset with gaze and head behavior: [MM'22]

Talks


Experience

Future Network of Intelligence Institute (Dec. 2021 - Now)

Research Assistant, Intelligent Networking and Multimedia Lab
SenseTime Technology, China (Aug. 2022 - Now)

Research Intern, ISP&Codec Group
Harvard University (Mar. 2022 - Jun. 2022)

Research Assistant, CAMLab
AIRS, Shenzhen (Jan. 2022 - Feb. 2022)

Research Intern, Student Robotics Association and NLP Project

Awards

  • Admission scholarship(Top 800 in College Entrance Examination)
  • Bowen Scholarship II(top 0.25% province-wide)
  • Undergraduate Research Award(Top 8% in the school)
  • 2022 Shaw Overcoming Award(Only 3 in the school)

Miscellaneous

This page has been visited for Free Hit Counters Times.