Hi, thanks for stopping by! I am now a second-year Ph.D. Student at The University of North Carolina at Chapel Hill, advised by Prof. Mohit Bansal. Previously, I did my undergraduate study at Shanghai Jiao Tong University.
While at UNC, I spent my summer time at Adobe Research (2024), Amazon Alexa (2023). Prior to UNC, I did research projects at SenseTime Research (2021), and with MIT-IBM Watson AI Lab (2021).
I am interested in wide topics in computer vision, especially in video, including video+X (language, audio, robotics) understanding & generation, trustworthy video reasoning, and robust video representation learning.
Find me here: shoubin -atsign- cs . unc . edu
π₯ News
- 2024.09: π One paper accepted to EMNLP main 2024. Check LLoVi for long VideoQA with LLM.
- 2024.07: πΉ One paper accepted to ACM MM 2024. Check IVA-0 for controllable image animation.
- 2024.06: π¬ Gave an invited talk at Google.
- 2024.05: π¬ Start summer intern at Adobe as Research Scientist.
- 2023.09: βοΈ One paper accepted to NeurIPS 2023. Check SeViLA for Video Loc+QA.
- 2023.07: 𦴠One paper accepted to IEEE TCSVT. Check MoPRL for skeletal anomaly detection.
- 2023.05: π Start summer intern at Amazon as Research Scientist.
- 2022.09: βͺοΈ Join UNC-CH MURGe-Lab .
- 2022.06: π Graduate from Shanghai Jiao Tong University (excellent graduates).
- 2021.10: π One paper accepted to NeurIPS 2021. Check STAR for real-world situated reasoning.
π Pre-print (*: equal contribution/co-first author)
Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level
Andong Deng, Tongjia Chen, Shoubin Yu, Wenshuo Chen, Taojiannan Yang, Lincoln Spencer, Erhang Zhang, Yapeng Tian, Ajmal Saeed Mian, Mohit Bansal, Chen Chen
(To appear)Code | Project Page
- We present GroundMoRe, a new benchmark for novel Motion-Grounded Video Reasoning, designed to assess multimodal modelsβ reasoning and perception capabilities for motion understanding.
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
Ziyang Wang*, Shoubin Yu*, Elias Stengel-Eskin*, Jaehong Yoon, Feng Cheng, Gedas Bertasius, Mohit Bansal
- We present VideoTree, an adaptive tree-based video presentation/prompting with simple visual clusturing for long video reasoning with LLM.
RACCooN: Remove, Add, and Change Video Content with Auto-Generated Narratives
Jaehong Yoon*, Shoubin Yu*, Mohit Bansal
- We present RACCooN, a versatile and user-friendly video-to-paragraph-to-video framework, enables users to remove, add, or change video content via updating auto-generated narratives.
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion
Shoubin Yu*, Jaehong Yoon*, Mohit Bansal
- We present CREMA, an efficient & modular modality-fusion framework for injecting any new modality into video reasoning.
π Publications
A Simple LLM Framework for Long-Range Video Question-Answering
Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, Gedas Bertasius
- We present LLoVi, a simple yet effective framework with LLM for long-range video question-answering.
Zero-Shot Controllable Image-to-Video Animation via Motion Decomposition
Shoubin Yu, Jacob Zhiyuan Fang, Skyler Zheng, Gunnar Sigurdsson, Vicente Ordonez, Robinson Piramuthu, Mohit Bansal
- We present IVA-0, a Image-to-Video animationor, enables precise control from users through in-place and out-of-place motion decomposition.
Self-Chained Image-Language Model for Video Localization and Question Answering
Shoubin Yu, Jaemin Cho, Prateek Yadav, Mohit Bansal
- We propose SeViLA, which self-chained BLIP-2 for 2-stage video question-answering (localization + QA) & refine localization with QA feedback.
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
Shoubin Yu, Zhongyin Zhao, Haoshu Fang, Andong Deng,Haisheng Su, Dongliang Wang, Weihao Gan, Cewu Lu, Wei Wu
- We propose MoPRL, a transformer-based model incorporated with skeletal motion prior for efficient video anomaly detection.
STAR: A Benchmark for Situated Reasoning in Real-World Videos
Bo Wu, Shoubin Yu, Zhenfang Chen, Joshua B. Tenenbaum, Chuang Gan
- We propose STAR, a benchmark for neural-symbolic video reasoning in real-world scenes.
π Honors and Awards
- CN Patent CN114724062A, 2022
- The Hui-Chun Chin and Tsung Dao Lee Scholar, 2020
- CN Patent CN110969107A, 2019
- Meritorious Award in Mathematical Contest in Modeling, 2019
- Second Prize in Shanghai, China Undergraduate Mathematical Contest in Modeling, 2019
π§ Service
- Conference reviewer: CVPR, ECCV, NeurIPS, ACL, EACL, CoNLL, AAAI
- Journal reviewer: IEEE Transactions on Circuits and Systems for Video Technology
π Educations
- 2022.09 - Present
- The University of North Carolina at Chapel Hill
- Computer Science, Ph.D.
- 2017.09 - 2022.06
- Shanghai Jiao Tong University
- Information Security, B.Eng.
π» Internships
- 2023.05 - 2023.11, Research Scientist Intern
- work with Jocob Zhiyuan Fang, Robinson Piramuthu
- 2021.01 - 2022.04, Research Intern
- work with Haisheng Su, Wei Wu