Junbin Xiao (肖俊斌)

Ph.D in Computer Science
image

I am a Research Fellow at NUS, working with Prof Angela Yao and Tat-Seng Chua. Previously, I obtained my PhD at the Department of Computer Science, National University of Singapore (NUS), supervised by Prof. Tat-Seng Chua and closely collaborated with Prof. Angela Yao . From Nov. 2021 to Apr. 2022, I worked as a research intern at Sea AI Lab (SAIL) and was jointly advised by Dr. Pan Zhou and Prof. Shuicheng Yan. Prior to that, I received my M.S.Eng degree from the Institute of Computing Technology, Chinese Academy of Sciences at 2018 and B.Eng. degree from Sichuan University at 2015, respectively.

I devote myself to fine-grained video understanding and its interaction with natural languages, with a special focus on VideoQA. The techniques emphasize video structural representation learning, large language models, robustness and interpretability. I am looking forward to working with Research Interns/Assistants/Visiting Students. (If you are interested in my research, please contact to junbin at comp dot nus dot edu dot sg. Students with CV/NLP/MultiModal background are preferred.)


News

Invited to be reviewer in ICLR'25 and CVPR'25'.

| Aug. 2024

I will give a talk about NExT-GQA: Visually Grounded VideoQA inivited by Twelve Labs

CVPR'24 | Jul. 2024

Two papers about video-language models and trustworthy K-VQA are accepted to ACL'24 and MM'24 respectively

| Jul. 2024

Our exploration of VQA in trustworthiness,3D object affordance and ego-car accident (3 papers) all are accepted to CVPR'24

CVPR'24 | Feb. 2024

Invited to be reviewer in CVPR'24 and ICLR'24.

| Oct. 2023

Two papers are accepted to T-PAMI'23 and ACM MM'23 respectively.

Aug. 2023

Two papers are accepted to T-PAMI'23 and ICCV'23 respectively.

Jul. 2023

Invited to serve as PC Member in AAAI'24.

AAAI | Jul. 2023

Invited to be reviewer in NeurIPS'23 dataset and benchmark track.

NeurIPS | Jun. 2023

Invited to be reviewer in ACM MM'23.

ACM MM | Apr. 2023

Invited to be reviewer in ICCV'23.

ICCV | Feb. 2023

Invited to be reviewer in CVPR'23.

CVPR | Oct. 2022

Receive the Dean's Graduate Research Excellence Award.

NUS | Aug. 2022

Invited to serve as PC member in AAAI'23.

AAAI | Aug. 2022

One VideoQA paper wins the Best Paper FinalList in CVPR'22.

CVPR | Jun. 2022

Featured Publications

NExT-GQA
Can I Trust Your Answer? Visually Grounded Video Question Answering

Junbin Xiao, Angela Yao, Yicong Li, Tat-Seng Chua

[ CVPR'24 (Highlight) / Project Page / Github / Cite]
TranSTR
Discovering Spatio-Temporal Rationales for Video Question Answering

Yicong Li, Junbin Xiao*(Corresponding Author), Chun Feng, Xiang Wang*, Tat-Seng Chua

[ ICCV'23 / Project Page / Github / Cite]
CoVGT
Contrastive Video Question Answering via Video Graph Transformer

Junbin Xiao, Pan Zhou, Angela Yao, Yicong Li, Richang Hong, Shuicheng Yan, Tat-Seng Chua

[T-PAMI'23 / Project Page / Github / Cite]
VideoQA Survey
Video Question Answering: Datasets, Algorithms and Challenges

Yaoyao Zhong*, Junbin Xiao*(Equal Contribution), Wei Ji*, Yicong Li, Weihong Deng, Tat-Seng Chua

[EMNLP'22 / Project Page / Github / Cite]
VGT
Video Graph Transformer for Video Question Answering

Junbin Xiao, Pan Zhou, Tat Seng Chua, Shuicheng Yan

[ ECCV'22 / Project Page / Github / Poster / Cite]
EIGV
Equivariant and Invariant Grounding for Video Question Answering

Yicong Li, Xiang Wang, Junbin Xiao, Tat Seng Chua

[ACM MM'22 / Project Page / Github / Poster / Cite]
IGV
Invariant Grounding for Video Question Answering

Yicong Li, Xiang Wang, Junbin Xiao, Wei Ji, Tat-Seng Chua

[CVPR'22, Best Paper Finalist / Project Page / Github / Poster / Cite]
HQGA
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering

Junbin Xiao, Angela Yao, Zhiyuan Liu, Yicong Li, Wei Ji, Tat-Seng Chua

[AAAI'22, Oral / Project Page / Github / Poster / Cite]
VidVRD-II
Video Visual Relation Detection via Interactive Inference

Xindi Shang, Yicong Li, Junbin Xiao, Wei Ji, Tat-Seng Chua

[ACM MM'21 / Project Page / Github / Poster / Cite]
NExT-QA Dataset
NExT-QA: Next Phase of Question Answering to Explaining Temporal Actions

Junbin Xiao, Xindi Shang, Yao Angela, Tat-Seng Chua

[CVPR'21, Strong Accept / Project Page / Github / Poster / Cite]
Video Relation Grounding
Visual Relation Grounding in Videos

Junbin Xiao, Xindi Shang, Xun Yang, Sheng Tang, Tat-Seng Chua

[ECCV'20, Spotlight / Project Page / Github / Poster / Cite]
Video Relation Dataset
Annotating Object and Relations in User-Generated Videos

Xindi Shang, Donglin Di, Junbin Xiao, Yu Cao, Xun Yang, Tat-Seng Chua

[ICMR'19, Oral / Project Page / Github / Poster / Cite]

Others

Reviewer for Conference: NeurIPS(Y23, Y24), ICLR(Y24,Y25), CVPR(Y22-Y24), ICCV(Y23), ECCV(Y22,Y24), AAAI(Y21-Y25), ACL(Y24), ACM MM(Y19-Y24), EMNLP(Y24), ACCV(Y24), ICASSP(Y21-Y22) etc.

Reviewer for Journal: TIP, TMM, TNNLS, ToMM, IPM, etc