Xi Shen

Email: shenxiluc at gmail dot com

Bio: I am the Chief Scientist at Intellindust. My team aims at developping simple and effective computer vision algorimths on low-cost edge devices. Tech transfer can be found here.

I did my Ph.D. in the IMAGINE team, École des Ponts ParisTech, advised by Prof. Mathieu Aubry. I also work closely with Prof. Alexei A. Efros. Previously, I was a Senior Researcher at Tencent AI Lab, Shenzhen, China.

I graduated from the Master Vision et Apprentissage (MVA, ENS Paris-Saclay) and Engineering Program at Ecole des Ponts ParisTech. Before that, I received dual B.S. degrees in Mechanics from Université Claude Bernard Lyon and Physics from Wuhan University.

GitHub

Google Scholar

News

01 / 08 / 2023 "TokenCut" is accepted by TPAMI.
01 / 07 / 2023 "LivelySpeaker" is accepted by ICCV 2023.
01 / 03 / 2023 Three papers are accepted by CVPR 2023, thanks to all my co-authors!
15 / 01 / 2023 Our paper T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations is available on arXiv.
22 / 11 / 2022 Our paper SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation is available on arXiv.
30 / 08 / 2022 Our paper Back to MLP: A Simple Baseline for Human Motion Prediction (siMLPe) is accepted to WACV 2023.
14 / 07 / 2022 I am honoured to be acknowledged as Outstanding Reviewer for ICML 2022.
27 / 06 / 2022 Our paper Compressing Features for Learning with Noisy Labels is accepted to TNNLS 2022.
19 / 06 / 2022 CVPR 2022 workshop presentations: "TokenCut" in "L3D"; "SegSwap" in "Image Matching" and "Transformer".
02 / 03 / 2022 "TokenCut" is accepted to CVPR 2022. Check Gradio Demo here.
25 / 02 / 2022 Our paper "Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut" (TokenCut) is published on arXiv.
13 / 01 / 2022 Our paper "Spatially-consistent Feature Matching and Learning for Heritage Image Analysis" is accepted to IJCV.

28 / 12 / 2021 I join Tencent AI Lab as a Senior Researcher, I will work with Dr. Jue Wang on Computer Vision.

03 / 12 / 2021 I am defending my Ph.D. today! [Slides] [Thesis]

29 / 10 / 2021 Our paper "Learning Co-segmentation by Segment Swapping for Retrieval and Discovery" is published on arXiv.

29 / 09 / 2021 Our paper "Re-ranking for image retrieval and transductive few-shot classification" is accepted to Neurips 2021.

18 / 04 / 2021 Our paper " Image Collation: Matching illustrations in manuscripts" is accepted to ICDAR 2021.

15 / 07 / 2020 Our paper " RANSAC-Flow: generic two-stage image alignment" is accepted to ECCV 2020. Watch the demo.

07 / 03 / 2020 The web application of historical watermark recognition is online!! Check the paper and the web application .

12 / 12 / 2019 Our paper " Empirical Bayes Transductive Meta-Learning with Synthetic Gradients" accepted to ICLR 2020.

06 / 08 / 2019 Our paper " Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach" is published on arXiv.

Research

I am interested in Computer Vision and Deep Learning. My research mainly focuses on finding solutions to vision tasks without annotations (unsupervised learning) or with easy accessible annotations (weakly supervised learning).
^* indicates equal contribution.
⁺ indicates corresponding author.
Representative papers are highlighted.

	TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut Yangtao Wang, Xi Shen⁺, Yuan Yuan, Yuming Du, Maomao Li, Xu Hu, James Crowley, Dominique Vaufreydaz IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 [Project page] [PDF] [Code (GitHub)] Star
	LivelySpeaker: Towards Semantic-aware Co-speech Gesture Generation Yihao Zhi^, Xiaodong Cun^, Xuelin Chen, Xi Shen, Wen Guo, Shaoli Huang, Shenghua Gao ICCV, 2023 [Project page] [PDF] [Code (GitHub)] Star
	Explicit Visual Prompting for Low-Level Structure Segmentations Weihuang Liu, Xi Shen, Chi-Man Pun⁺, Xiaodong Cun⁺ CVPR, 2023 [Project page] [PDF] [Code (GitHub)] Star
	T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations Jianrong Zhang^, Yangsong Zhang^, Xiaodong Cun, Shaoli Huang, Yong Zhang, Hongwei Zhao, Hongtao Lu, Xi Shen⁺ CVPR, 2023 [Project page] [PDF] [Code (GitHub)] [Online demo (Colab)] Star
	SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation Wenxuan Zhang^, Xiaodong Cun^, Xuan Wang, Yong Zhang, Xi Shen, Guo Yu, Ying Shan, Fei Wang CVPR, 2023 Top 10 you won't miss papers of CVPR 2023 (Voxel51). [Project page] [PDF] [Code (GitHub)] Star
	Back to MLP: A Simple Baseline for Human Motion Prediction (siMLPe) Wen Guo^, Yuming Du^, Xi Shen⁺, Vincent Lepetit, Xavier Alameda-Pineda, Francesc Moreno-Noguer WACV, 2023 [Project page] [PDF] [siMLPe Code (GitHub)] Star
	Compressing Features for Learning with Noisy Labels Yingyi Chen, Xu Hu, Xi Shen⁺, Chunrong Ai, Johan A.K. Suykens TNNLS, 2022 [Project page] [PDF] [Code (GitHub)] [Workshop Video (7 mins)] Star
	Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut Yangtao Wang, Xi Shen⁺, Xu Hu, Yuan Yuan, James Crowley, Dominique Vaufreydaz CVPR, 2022 [Project page] [PDF] [Code (GitHub)] [Colab] [Gradio Demo] [Code (GitLab)] Star
	Spatially-consistent Feature Matching and Learning for Heritage Image Analysis Xi Shen, Robin Champenois, Shiry Ginosar, Ilaria Pastrolin, Morgane Rousselot, Oumayma Bounou, Tom Monnier, Spyros Gidaris, François Bougard, Pierre-Guillaume Raverdy, Marie-Françoise Limon, Christine Bénévent, Marc Smith, Olivier Poncet, K. Bender, Béatrice Joyeux-Prunel, Elizabeth Honig, Alexei A. Efros, Mathieu Aubry IJCV, 2022 [Project page] [PDF (Springer)] [PDF (HAL)]
	Learning Co-segmentation by Segment Swapping for Retrieval and Discovery Xi Shen, Alexei A. Efros, Armand Joulin, Mathieu Aubry CVPR Image Matching workshop and Transformer workshop, 2022 [Project page] [PDF] [Code] [Youtube Video] [Slides] Star
	Re-ranking for image retrieval and transductive few-shot classification Xi Shen, Yang Xiao, Shell Xu Hu, Othman Sbai, Mathieu Aubry NeurIPS, 2021 [Project page] [PDF] [Code] [Video] Star
	Image Collation: Matching illustrations in manuscripts Ryad Kaoua, Xi Shen, Stavros Lazaris, David Picard, Mathieu Aubry ICDAR, 2021 [Project page] [PDF] [Code] [Dataset] [Video] [Slides] [Poster] Star
	RANSAC-Flow: generic two-stage image alignment Xi Shen, François Darmon, Alexei A. Efros, Mathieu Aubry ECCV, 2020 [Project page] [PDF] [Code] [Demo] [Video] [Slides] Star
	Empirical Bayes Transductive Meta-Learning with Synthetic Gradients Shell Xu Hu, Pablo Moreno, Yang Xiao, Xi Shen, Guillaume Obozinski, Neil D. Lawrence Andreas Damianou ICLR, 2020 [PDF] [Code] Star
	Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach Xi Shen, Ilaria Pastrolin, Oumayma Bounou, Spyros Gidaris, Marc Smith, Olivier Poncet, Mathieu Aubry ICPR, 2020 [Project page] [PDF] [Code] [Dataset] [Video] [Slides] [Web App] [Paper on Web App] Star
	Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning Xi Shen, Alexei A. Efros, Mathieu Aubry CVPR, 2019 Covered by Nature [Project page] [PDF] [Code] [Dataset] [Slides] Star
	Marginalized Average Attentional Network For Weakly-Supervised Learning Yuan Yuan, Yueming Lyu, Xi Shen, Ivor Tsang, Dit-Yan Yeung ICLR, 2019 [PDF] [Code] Star

Misc.

Academic Services

ICML 2022 (Outstanding Reviewer), CVPR 2022 - 2023, ECCV 2022, NeurIPS 2021 - 2022, ICLR 2020 - 2023, BMVC 2019 - 2022, WACV 2023.

Teacher Assistant

03 / 2021 - 04 / 2021 Université PSL (Paris Sciences & Lettres) Digital Humanities Meet Artificial Intelligence (M1).
02 / 2021 - 06 / 2021 Ecole des Ponts ParisTech Computer Vision for Mechanics of materials (L3).
02 / 2019 - 06 / 2019 Ecole des Ponts ParisTech Traitement de l'information et vision artificielle (M1).