Jinkun Cao

I am a Robotics PhD student in CMU with Prof. Kris Kitani.

Prior to CMU, I worked with Prof. Cewu Lu in Shanghai Jiao-Tong Univ. I also visited UC Berkeley in 2019, advised by Prof. Fisher Yu and Prof. Trevor Darrell. I was also fortunate to collaborate with Prof. Yang Gao in Tsinghua and interned in industry such as Tencent YouTu Lab and Bytedance AI Lab. I also collaborate with Jiangmiao Pang and OpenMMLab. I am interested in broad vision and robotics topics, especially:

video analysis for multi-object tracking, forecasting and planning.
computer vision in 3d and physical world.
unsupervised learning and data-efficient learning.

Github | Google Scholar | Resume | Linkedin
Email: jinkuncao [AT] gmail.com / jinkunc [AT] andrew.cmu.edu

News

[2022/9]: A paper is accepted to BMVC'2022 for multi-object tracking. The paper is coming to the public soon.
[2022/9]: MED paper is accepted by NeurIPS'2022. We study the disentanglement property of high-dimensional representation models and introduce contrastive learning methods into disentanglement benchmarks. Stay tuned for a heavily revised veresion of paper.
[2022/8]: OC-SORT is supported by mmtracking now. Try it for more flexible and advanced features!
[2022/3]: The code of OC-SORT is released. It achieves SOTA performance on multiple MOT datasets in a pure motion-based fashion.
[2022/3]: We are organizing "Multiple Object Tracking in Complex Environments Workshop” in ECCV'2022, Tel Aviv, Israel.
[2022/2]: DanceTrack is accepted in CVPR'2022. We propose a challenging multi-object tracking dataset.

Preprints

Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking

Jinkun Cao, Xinshuo Weng, Rawal Khirodkar, Jiangmiao Pang, Kris Kitani

[arxiv] [code]

TransTrack: Multiple Object Tracking with Transformer

Peize Sun, Jinkun Cao, Yi Jiang, Rufeng Zhang, Enze Xie, Zehuan Yuan, Changhu Wang, Ping Luo

[arxiv] [code]

Publications

* indicates equal contribution

Track Targets by Dense Spatio-Temporal Position Encoding

Jinkun Cao, Hao Wu, Kris Kitani

BMVC 2022 [Oral] [paper is coming]

An Empirical Study on Disentanglement of Negative-free Contrastive Learning

Jinkun Cao, Ruiqian Nai, Qing Yang, Jialei Huang, Yang Gao

NeurIPS 2022 [arxiv] [code]

DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion

Peize Sun*, Jinkun Cao*, Yi Jiang, Zehuan Yuan, Song Bai, Kris Kitani, Ping Luo

CVPR 2022 [arxiv] [code] [project page] [codalab]

Instance-aware predictive navigation in multi-agent environments

Jinkun Cao, Xin Wang, Trevor Darrell, Fisher Yu

ICRA 2021 [arxiv] [code]

Attribute Restoration Framework for Anomaly Detection

Fei Ye, Chaoqing Huang, Jinkun Cao, Maosen Li, Ya Zhang, Cewu Lu

IEEE Trans on MM 2020 [arxiv]

Cross-Domain Adaptation for Animal Pose Estimation

Jinkun Cao, Hongyang Tang, Hao-Shu Fang, Xiaoyong Shen, Cewu Lu, Yu-Wing Tai

ICCV 2019 [Oral] (4.3% acceptance rate) [arxiv] [dataset]

Pairwise Body-Part Attention for Recognizing Human-Object Interactions

Hao-Shu Fang, Jinkun Cao, Yu-Wing Tai, Cewu Lu

ECCV 2018 [paper]

Services

Conference Reviewer: , ICRA, CVPR, ICML, ECCV, NeurIPS, AAAI
Journal Reviewer: RA-L, IEEE Multimedia
Workshop Organizer:
- "Multiple Object Tracking in Complex Environments Workshop” in ECCV'2022