Yi Jiang

Yi Jiang

I am a Research Lead at Media Intelligence of ByteDance Ads Generative AI, where I work on computer vision and machine learning.

I got my Master's degree from the Department of Computer Science and Engineering, Zhejiang University.

My previous research focus is on instance understanding in spatial & temporal, including large scale & open-vocabulary object recognition, detection, segmentation, tracking and Pretraining. Most of my works have released codes on Github, with over 12.0K stars.

Recently, my research focuses on visual foundation models, deep generative models(Diffusion models and its application) and large language models.

Email / Google Scholar / Github

Research Highlight

UNINEXT accepted by CVPR'23. UNINEXT unifies 10 instance perception tasks using a single model with the same model parameters
ByteTrack ranks 1th of the most influential papers in ECCV 2022. Code is available on github with 3.4k stars
Spark accepted by ICLR'23 as Spotlight. Spark is the first successful BERT/MAE-style pretraining on any convolutional networks
Unicorn accepted by ECCV'22 as Oral Presentation . Unicorn accomplishes the great unification of the tracking network architecture and learning paradigm
IDOL and Seqformer accepted by ECCV'22 as Oral Presentation , serving as strong baseline for video instance segmentation
Sparse R-CNN accepted by CVPR'21. Sparse R-CNN is integrated into several famous frameworks(Detectron2, MMDetection, PaddlePaddle)

Publications (* equal contribution, ^† corresponding author)

	CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection Chuofan Ma, Yi Jiang^†, Xin Wen,Zehuan Yuan, Xiaojuan Qi. Advances in Neural Information Processing Systems(NeurIPS), 2023 Paper
	Segment Every Reference Object in Spatial and Temporal Spaces Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo. International Conference on Computer Vision (ICCV), 2023 Paper
	Exploring Transformers for Open-world Instance Segmentation Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo. International Conference on Computer Vision (ICCV), 2023 Paper
	EGC: Image Generation and Classification via a Diffusion Energy-Based Model Qiushan Guo, Chuofan Ma, Yi Jiang, Zehuan Yuan, Yizhou Yu, Ping Luo. International Conference on Computer Vision (ICCV), 2023 Paper / Project
	UNINEXT : Universal Instance Perception as Object Discovery and Retrieval Bin Yan, Yi Jiang^†, Jiannan Wu, Dong Wang, Ping Luo, Zehuan Yuan, Huchuan Lu Computer Vision and Pattern Recognition (CVPR), 2023 Paper / Code UNINEXT unifies 10 instance perception tasks and achieves state of the art performance using a single model with the same model parameters.
	InstMove: Instance Motion for Object-centric Video Segmentation Qihao Liu, Junfeng Wu, Yi Jiang, Xiang Bai, Alan Yuille, Song Bai Computer Vision and Pattern Recognition (CVPR), 2023 Paper / Code
	Spark : Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling Keyu Tian, Yi Jiang^†, Qishuai Diao, Chen Lin, Liwei Wang, Zehuan Yuan International Conference on Learning Representations (ICLR), 2023 [Spotlight notable-top-25% of Accepted Papers] Paper / Code Spark is the first successful BERT/MAE-style pretraining on any convolutional networks
	Learning Object-Language Alignments for Open-Vocabulary Object Detection, Chuang Lin, Peize Sun, Yi Jiang, Ping Luo, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan, Jianfei Cai International Conference on Learning Representations (ICLR), 2023 Paper / Code
	Rethinking Resolution in the Context of Efficient Video Recognition Chuofan Ma, Qiushan Guo, Yi Jiang^†, Zehuan Yuan, Ping Luo, Xiaojuan Qi^† Advances in Neural Information Processing Systems (NeurIPS), 2022 Paper / Code
	Unicorn 🦄 : Towards Grand Unification of Object Tracking Bin Yan, Yi Jiang^†, Peize Sun, Dong Wang, Zehuan Yuan, Ping Luo, Huchuan Lu European Conference on Computer Vision (ECCV), 2022 [Oral Presentation Top 2.7%] Paper / Code For the first time, we accomplish the great unification of various object tracking task with unify network architecture and learning paradigm
	In Defense of Online Models for Video Instance Segmentation Junfeng Wu, QiHao Liu, Yi Jiang, Song Bai, Alan Yuille, Xiang Bai European Conference on Computer Vision (ECCV), 2022 [Oral Presentation Top 2.7%] Paper / Code
	SeqFormer: Sequential Transformer for Video Instance Segmentation Junfeng Wu, Yi Jiang, Song Bai, Wenqing Zhang, Xiang Bai European Conference on Computer Vision (ECCV), 2022 [Oral Presentation Top 2.7%] Paper / Code
	Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation Chuang Lin, Yi Jiang^†, Jianfei Cai, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan European Conference on Computer Vision (ECCV), 2022 Paper / Code
	ByteTrack: Multi-Object Tracking by Associating Every Detection Box Yifu Zhang, Peize Sun, Yi Jiang, Dongdong Yu, Fucheng Weng, Zehuan Yuan, Ping Luo, Wenyu Liu, Xinggang Wang European Conference on Computer Vision (ECCV), 2022 Paper / Code ByteTrack ranks 1th of the most influential papers in ECCV 2022.
	Language as Queries for Referring Video Object Segmentation Jiannan Wu, Yi Jiang, Peize Sun, Zehuan Yuan, Ping Luo Computer Vision and Pattern Recognition (CVPR), 2022 Paper / 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 Computer Vision and Pattern Recognition (CVPR), 2022 Paper / Code
	Objects in Semantic Topology Shuo Yang, Peize Sun, Yi Jiang, Xiaobo Xia, Ruiheng Zhang, Zehuan Yuan, Changhu Wang, Ping Luo, Min Xu International Conference on Learning Representations (ICLR), 2022 Paper
	What Makes for End-to-End Object Detection? Peize Sun, Yi Jiang, Enze Xie, Wenqi Shao, Zehuan Yuan, Changhu Wang, Ping Luo International Conference on Machine Learning (ICML), 2021 Paper / Code
	Sparse R-CNN: End-to-End Object Detection with Learnable Proposals Peize Sun^, Rufeng Zhang^, Yi Jiang^, Tao Kong, Chenfeng Xu, Wei Zhan, Masayoshi Tomizuka, Lei Li, Zehuan Yuan, Changhu Wang, Ping Luo Computer Vision and Pattern Recognition (CVPR)*, 2021 Paper / Code
	Single person dense pose estimation via geometric equivariance consistency Qinchuan Zhang, Yi Jiang, Qin Zhou, Yiru Zhao, Yao Liu, Hongtao Lu, Xian-Sheng Hua IEEE Transactions on Multimedia (TMM), 2021 Paper
	Learning to Segment the Tail Xinting Hu, Yi Jiang, Kaihua Tang, Jingyuan Chen, Chunyan Miao, Hanwang Zhang Computer Vision and Pattern Recognition (CVPR), 2020 Paper / Code
	SimpleDet - A Simple and Versatile Framework for Object Detection and Instance Recognition Yuntao Chen, Chenxia Han, Yanghao Li, Zehao Huang, Yi Jiang, Naiyan Wang, Zhaoxiang Zhang Journal of Machine Learning Research (JMLR), 2019 Paper / Code

Preprints (* equal contribution, ^† corresponding author)

	Multi-Level Contrastive Learning for Dense Prediction Task Qiushan Guo, Yizhou Yu, Yi Jiang, Jiannan Wu, Zehuan Yuan, and Ping Luo. arXiv, 2023 arXiv / Code
	Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders Haosen Yang, Deng Huang, Bin Wen, Jiannan Wu, Hongxun Yao, Yi Jiang^†, Xiatian Zhu, Zehuan Yuan arXiv, 2022 arXiv / Code
	MetaFormer: A Unified Meta Framework for Fine-Grained Recognition Qishuai Diao, Yi Jiang^†, Bin Wen, Jia Sun, Zehuan Yuan arXiv, 2022 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, 2020 arXiv / Code

Awards

Winner of CVPR 2022 Large-scale Video Object Segmentation Challenge: Video Instance Segmentation
Runner up of CVPR 2021 FGVC8 iNaturalist Challenge
Runner up of ICCV 2019 WIDER Face and Person Challenge: Face Detection
Excellent Mentor Award, ByteDance 2021
Outstanding Staff Award, Bytedance 2020
Competition Master in kaggle 2018

Professional activities

Main Organizer for ECCV 2022 Workshop: Multiple Object Tracking and Segmentation in Complex Environments
Reviewer for CVPR, ICCV, ECCV, NIPS, MM
Reviewer for Trans. on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Trans. on Image Processing (TIP), Pattern Recognition

Design and source code from Jon Barron.