Jing Tan (谈婧)

I'm a third-year Ph.D. Candidate in MMLab at The Chinese University of Hong Kong, supervised by Prof. Dahua Lin. I work on scene-level visual creation and manipulation using structured representations and multimodal generative models.

Previously, I obtained the B.Sc degree from Nanjing University in 2020, and the Master degree from Nanjing University under the supervision of Prof. Limin Wang in 2023.

I was an applied scientist intern at AWS AI Lab during the summer of 2025, where I collaborated with Prof. Zhuowen Tu and Prof. Jiajun Wu.

Email  /  CV  /  Scholar  /  Twitter  /  Github

profile photo

Research (Google Scholar)

In my research, I consistently leverage the inherent structure of visual data. In video understanding, I exploit the natural temporal and semantic structure of videos to enable efficient perception. In visual scene generation, I study how structured scene representations support reliable and controllable creation and manipulation of visual content.

Image Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
Jing Tan, Zhaoyang Zhang, Yantao Shen, Jiarui Cai, Shuo Yang, Jiajun Wu, Wei Xia, Zhuowen Tu, Stefano Soatto
Under Review,
project page / code / arXiv

We show, in the context of geometric object transforations in scene images, that RL is more suitable than SFT to solve visual editing problems with verifiable rewards, in terms of data efficiency and editing accuracy.
Imagine360: Immersive 360 Video Generation from Perspective Anchor
Jing Tan*, Shuai Yang*, Tong Wu, Jingwen He, Yuwei Guo, Ziwei Liu, Dahua Lin
NeurIPS, 2025 (* equal contribution)
project page / code / video / arXiv

Imagine360 lifts standard perspective video into 360-degree video with rich and structured motion, unlocking dynamic scene experience from full 360 degrees.
LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation
Shuai Yang*, Jing Tan*, Mengchen Zhang, Tong Wu, Yixuan Li, Gordon Wetzstein, Ziwei Liu, Dahua Lin
SIGGRAPH (Conference Track), 2025 (* equal contribution)
project page / code / video / arXiv

LayerPano3D generates full-view, explorable panoramic 3D scene from a single text prompt.
Image Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection
Jing Tan, Yuhong Wang, Gangshan Wu, Limin Wang
T-PAMI, 2023
arXiv / code / blog

We present Temporal Perceiver (TP), a general architecture based on Transformer decoders as a unified solution to detect arbitrary generic boundaries, including shot-level, event-level and scene-level temporal boundaries.
Image PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points
Jing Tan, Xiaotong Zhao, Xintian Shi, Bin Kang, Limin Wang
NeurIPS, 2022
arXiv / code / blog

PointTAD effectively tackles multi-label TAD by introducing a set of learnable query points to represent the action keyframes.
Image Relaxed Transformer Decoders for Direct Action Proposal Generation
Jing Tan*, Jiaqi Tang*, Limin Wang, Gangshan Wu
ICCV, 2021 (* equal contribution)
pdf / code / blog

The first transformer-based framework for temporal action proposal generation.

Here are some collaborative works on 3D object generation and video generation related topics.

Image SS4D: Native 4D Generative Model via Structured Spacetime Latents
Zhibin Li*, Mengchen Zhang*, Tong Wu, Jing Tan, Jiaqi Wang, Dahua Lin
SIGGRAPH Asia (TOG), 2025
project page / arXiv / code

SS4D is a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video.
Image GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography
Mengchen Zhang, Tong Wu, Jing Tan, Ziwei Liu, Gordon Wetzstein, Dahua Lin
ICCV, 2025
project page / arXiv / code

GenDoP is an auto-regressive model that generate artistic and expressive camera trajectories from text prompts and geometric cues.
Image IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
Zhibin Li, Tong Wu, Jing Tan, Mengchen Zhang, Jiaqi Wang, Dahua Lin
ICLR, 2025
project page / arXiv / code / data

IDArb is a Diffusion-based intrinsic decomposition framework for an arbitrary number of image inputs under varying illuminations.
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
Zhenzhi Wang, Yixuan Li, Yanhong Zeng, Youqing Fang, Yuwei Guo, Wenran Liu, Jing Tan, Kai Chen, Tianfan Xue, Bo Dai, Dahua Lin
NeurIPS D&B Track, 2024
project page / arXiv / code

Camera-controllable human image animation dataset and framework.
Image Dual DETRs for Multi-Label Temporal Action Detection
Yuhan Zhu, Guozhen Zhang, Jing Tan, Gangshan Wu, Limin Wang
CVPR, 2024
arXiv / code

A new Dual-level query-based TAD framework to precisely detect actions from both instance-level and boundary-level.

Experience
AWS Agentic AI
Applied Scientist Intern
June 2025 – Nov. 2025
Bellevue, WA, US
  • Conducted research in collaboration with Prof. Zhuowen Tu and Prof. Jiajun Wu on reinforcement learning–guided spatial-aware image editing, with Yantao Shen as the internship manager.
  • Leveraged RLVR to enable precise geometric object transformations in images following text instructions.
Tencent, PCG
Research Intern
Dec. 2021 – Mar. 2023
Beijing, China
  • Worked on multi-label temporal action detection via learnable query points.
  • Developed a more general video action detection framework capable of localizing specific actions among multiple simultaneous actions.

Selected Honors & Awards

  • CSIG Master’s Thesis Incentive Program Awardee, China Society of Image and Graphics, 2025
  • Outstanding Master’s Thesis Award (3/226), Nanjing University, 2024
  • National Scholarship (6/226), Ministry of Education of China, 2022
  • 3rd Place, GEBD-LOVEU Challenge @ CVPR Workshop, 2022

Academic Services

  • Regular Conference reviewer for CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR; Reviewer for SIGGRAPH 2025.
  • Journal reviewer for IJCV and TIP.
  • Teaching Assistant for IERG4998 and IERG4999 at CUHK.



Thanks Jon Barron for sharing the source code of this website template.