Jiahui Huang

Jiahui Huang

Auto-generated profile, based on publicly available information

Jiahui Huang

Adobe Research, San Jose, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 July 2025
Verified
Conference Paper
Open access
JXJinbo Xing
Jinbo Xing
LMLong Mai
Long Mai
CHCusuh Ham
Cusuh Ham
JHJiahui Huang
Jiahui Huang
AMAniruddha Mahapatra
Aniruddha Mahapatra
FLFeng Liu
Feng Liu


21 October 2022
Verified
Book Chapter
Closed access
PDF file
JHJiahui Huang
Jiahui Huang
YJYuhe Jin
Yuhe Jin
KYKwang Moo Yi
Kwang Moo Yi
LSLeonid Sigal
Leonid Sigal

6 May 2022 in Sensors
Verified
Journal Article
Open access
PDF file
JHJiahui Huang
Jiahui Huang
YCYew Ken Chia
Yew Ken Chia
SYSamson Yu
Samson Yu
KYKevin Yee
Kevin Yee
DKDennis Küster
Dennis Küster
GRGemma Roig
Gemma Roig
In this paper, we introduce an approach for future frames prediction based on a single input image. Our method is able to generate an entire video sequence based on the information contained in the input frame. We adopt an autoregressive approach in our generation process, i.e., the output from each time step is fed as the input to the next step. Unlike other video prediction methods that use “one shot” generation, our method is able to preserve much more details from the input image, while also capturing the critical pixel-level changes between the frames. We overcome the problem of generation quality degradation by introducing a “complementary mask” module in our architecture, and we show that this allows the model to only focus on the generation of the pixels that need to be changed, and to reuse those that should remain static from its previous frame. We empirically validate our methods against various video prediction models on the UT Dallas Dataset, and show that our approach is able to generate high quality realistic video sequences from one static input image. In addition, we also validate the robustness of our method by testing a pre-trained model on the unseen ADFES facial expression dataset. We also provide qualitative results of our model tested on a human action dataset: The Weizmann Action database.