| CARVIEW |
Select Language
HTTP/2 200
last-modified: Tue, 29 Aug 2023 08:48:37 GMT
accept-ranges: bytes
vary: Accept-Encoding
content-encoding: gzip
host-header: c2hhcmVkLmJsdWVob3N0LmNvbQ==
content-type: text/html
date: Mon, 29 Dec 2025 02:52:12 GMT
server: Apache
Véronique Prinet
Véronique PrinetAssociate ProfessorChinese Academy of Sciences, Institute of AutomationEmail / Google Scholar / Linkedin / Github Research interests: vision, perception, machine learning, image and video understanding My recent research is mainly concerned with deep generative and predictive models from image and video using self-supervised techniques, ie, learning approaches that do not require manual data labelling. In the past, I worked extensively on low-level vision tasks, specifically physics-based models for vision, and graph representation in images. |
|
 |
Multi-modal spatio-temporal meteorological forecasting with deep neural network
Xinbang Zhang, Qizhao Jin, Tingzhao Yu, Shiming Xiang, Qiuming Kuang, Véronique Prinet and Chunhong Pan ISPRS Journal of Photogrammetry and Remote Sensing 2022, 188, 380-393 Abstract Meteorological forecasting is a typical and fundamental problem in the remote sensing field. Although many brilliant forecasting methods have been developed, long-term (a few days ahead) meteorological prediction still relies on traditional Numerical Weather Prediction (NWP) that is not competent for the oncoming flood of meteorological data. To improve the forecasting ability faced with meteorological big data, this article adopts the Automated Machine Learning (AutoML) technique and proposes a deep learning framework to model the dynamics of multi-modal meteorological data along spatial and temporal dimensions. Spatially, a convolution based network is developed to extract the spatial context of multi-modal meteorological data. Considering the complex relationship between different modalities, the Neural Architecture Search (NAS) method is introduced to automate the designing procedure of the fusion network in a purely data-driven manner. As for the temporal dimension, an encoder-decoder structure is built to exhaustively model the temporal dynamics of the embedding sequence. Specializing for the numerical sequence representation transformation, the multi-head attention module endows the proposed model with the ability to forecast future data. Generally speaking, the whole framework could be optimized with the standard back-propagation, yielding an end-to-end learning mechanism. To investigate its feasibility, the proposed model is evaluated with four typical meteorological modalities including temperature, relative humidity, and two components of wind, which are all restricted under the region whose latitude and longitude range from 0 to 55 degree N and 70 to 140 degree E, respectively. Experiments on two datasets with different resolutions verify that deep learning is effective as an operational technique for the meteorological forecasting task.
|
 |
Urban Scene Based Semantical Modulation for Pedestrian Detection
Hangzhi Jiang, Shengcai Liao, Jinpeng Li, Véronique Prinet, Shiming Xiang and Chunhong Pan Neurocomputing 2022, 474, 1-12 Abstract Despite recent progress, pedestrian detection still suffers from the troublesome problems of small objects, occlusions, and numerous false positives. Intuitively, the rich context information available from urban scenes could help determine the presence and location of pedestrians. For example, roads and sidewalks are good cues for potential pedestrians, while detections on buildings and trees are often false positives. However, most existing pedestrian detectors ignore or inadequately utilize semantic context. In this paper, in order to make full use of the urban-scene semantics to facilitate pedestrian detection, we propose a new method called Semantical Modulation based Pedestrian Detector (SMPD). First, for efficiency, a semantic prediction module is jointly learned with a baseline detector for semantic predictions. Second, a semantic integration module is designed to exploit the urban-scene semantic context for detection. Specifically, we force it to be an independent detection branch based solely on semantic information. In this way, together with the baseline detector, the fused detection results explicitly depend on both the learned appearance features and the scene context around pedestrians. In addition, while existing methods cannot be applied to the datasets where semantic annotations are not available for training, we introduce a semi-supervised transfer learning approach to make our methodsuitable for more scenarios. We demonstrate experimentally that, thanks to the integration of semantic context from urban scenes, SMPD can accurately detect small and occluded pedestrians, as well as effectively remove false positives. As a result, SMPD achieves the new state of the art on the Citypersons and Caltech datasets.
|
 |
Enhanced Boundary Learning for Glass-like Object Segmentation
Hao He, Xiangtai Li, Guangliang Cheng, Jianping Shi, Yunhai Tong, Gaofeng Meng, Véronique Prinet, Lubin Weng, Shiming Xiang and Chunhong Pan ICCV 2021 Abstract Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping. However, this task is very challenging due to the arbitrary scenes behind glass-like objects. This paper aims to solve the glass-like object segmentation problem via enhanced boundary learning. In particular, we first propose a novel refined differential module that outputs finer boundary cues. We then introduce an edge-aware point-based graph convolution network module to model the global shape along the boundary. We use these two modules to design a decoder that generates accurate and clean segmentation results, especially on the object contours. Both modules are lightweight and effective: they can be embedded into various segmentation models. In extensive experiments on three recent glass-like object segmentation datasets, including Trans10k, MSD, and GDD, our approach establishes new state-of-the-art results. We also illustrate the strong generalization properties of our method on three generic segmentation datasets, including Cityscapes, BDD, and COCO Stuff.
|
 |
MS-Net: Multi-Source Spatio-Temporal Network for Traffic Flow Prediction
Shen Fang, Véronique Prinet, Jianlong Chang, Michael Werman, Shiming Xiang and Chunhong Pan IEEE Transactions on Intelligent Transportation Systems (T-ITS) 2021 Abstract Predicting urban traffic flow is a challenging task, due to the complicated spatio-temporal dependencies on traffic networks. Urban traffic flow usually has both short-term neighboring and long-term periodic temporal dependencies. It is also noticed that the spatial correlations over different traffic nodes are both local and non-local. What's more, the traffic flow is affected by various external factors. To capture the non-local spatial correlations, we propose a Dilated Attentional Graph Convolution (DAGC). The DAGC utilizes a dilated graph convolution kernel to expand the nodes' receptive field and exploit multi-order neighborhood. Technically, the lower-order neighborhood corresponds to local spatial dependencies, while the higher-order neighborhood corresponds to non-local spatial dependencies between nodes. Based on DAGC, a Multi-Source Spatio-Temporal Network (MS-Net) is designed, which suffices to integrate long-range historical traffic data as well as multi-modal external information. MS-Net consists of four components: a spatial feature extraction module, a temporal feature fusion module, an external factors embedding module, and a multi-source data fusion module. Extensive experiments on three real traffic datasets demonstrates that the proposed model performs well on both the public transportation networks, road networks, and can handle large-scale traffic networks in particular the Beijing bus network which has more than 4,000 traffic nodes.
|
 |
Decoupled Representation Learning for Skeleton-Based Gesture Recognition
Jianbo Liu, Yongcheng Liu, Ying Wang, Véronique Prinet, Shiming Xiang and Chunhong Pan Computer Vision and Pattern Recognition (CVPR) 2020 Abstract Skeleton-based gesture recognition is very challenging, as the high-level information in gesture is expressed by a sequence of complexly composite motions. Previous works often learn all the motions with a single model. In this paper, we propose to decouple the gesture into hand posture variations and hand movements, which are then modeled separately. For the former, the skeleton sequence is embedded into a 3D hand posture evolution volume (HPEV) to represent fine-grained posture variations. For the latter, the shifts of hand center and fingertips are arranged as a 2D hand movement map (HMM) to capture holistic movements. To learn from the two inhomogeneous representations for gesture recognition, we propose an end-to-end two-stream net-work. The HPEV stream integrates both spatial layout and temporal evolution information of hand postures by a dedicated 3D CNN, while the HMM stream develops an efficient2D CNN to extract hand movement features. Eventually, the predictions of the two streams are aggregated with high efficiency. Extensive experiments on SHREC’17 Track, DHG-14/28 and FPHA datasets demonstrate that our method iscompetitive with the state-of-the-art.
|
 |
Progressive Sparse Local Attention for Video Object Detection
Chaoxu Guo, Bin Fan, Jie Gu, Qian Zhang, Shiming Xiang, Véronique Prinet and Chunhong Pan International Conference in Computer Vision (ICCV) 2019 Abstract Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and efficiency. However, introducing an extra model to estimate optical flow can significantly increase the overall model size. The gap between optical flow and high-level features can also hinder it from establishing spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense Feature Transforming (DenseFT) are proposed to model temporal appearance and enrich feature representation respectively in a novel video object detection framework. Experiments on ImageNet VID show that our method achieves the best accuracy compared to existing methods with smaller model size and acceptable runtime speed.
|
 |
Road Curb Detection and Localization With Monocular Forward-View Vehicle Camera
Stanislav Panev, Francisco Vicente, Fernando De la Torre and Véronique Prinet IEEE Transactions on Intelligent Transportation Systems (IEEE TITS), 20(9), Sept. 2019 Abstract
We propose a robust method for estimating road curb 3D parameters (size, location, orientation) using a calibrated camera equiped with a fish-eye lens. Automatic curb detection and localization is particularly important in the context of Advanced Driver Assistance System (ADAS), ie to prevent possible collision and damage of the vehicle's bumper during perpendicular parking automatic manoeuvre.
Combining 3D geometric reasoning with advanced visual detection methods, our approach is able to estimate the vehicle to curb distance with 90% accuracy in real time, as well as its orientation, height and depth.
Our approach consists of two distinct components -- curb detection in each individual video frame and temporal analysis. The first part comprises of sophisticated curb edges extraction and parametrized 3D curb template fitting. Using a few assumptions regarding the real world geometry, we can thus retrieve the curb's heigh and its relative position wrt the moving vehicle on which the camera is mounted. Support Vector Machine (SVM) classifier feeded with Histograms of Oriented Gradients (HOG) is used for filtering out outliers. In the second part, the detected curb regions are tracked in the
temporal domain, so as to perform a second pass of false positives rejection.
We have validated our approach on a newly collected a database of 11 videos under different conditions. We have used using point-wise LIDAR measurements and manual exhaustive labels as ground-truth.
|
 |
Motion Selective Prediction for Video Frame Synthesis
Véronique Prinet arxiv:1812.10157, 2018 appeared also in International Conference in Image Processing (ICIP) 2019 (short version) under the title: Domain-Agnostic Video Prediction from Motion Selective Kernels Project page |
 |
3D Road Curb Extraction from Image Sequence for Automobile Parking Assist System
Véronique Prinet, Jinsong Wang, Jongho Lee, David Wettergreen International Conference in Image Processing (ICIP) 2016 |
 |
Illuminant Chromaticity from Image Sequences
Véronique Prinet, Dani Lischinski and Michael Werman International Conference in Computer Vision (ICCV) 2013 Project page |
 |
Specular Highlight Enhancement from Video Sequences
Véronique Prinet, Michael Werman and Dani Lischinski International Conference in Image Processing (ICIP) 2013 |
 |
Mid-level Features and Spatio-Temporal Context for Activity Recognition
Fei Yuan, Hicchem Sahbi, Véronique Prinet and JinSong Yuan Pattern Recognition (PR) 2012, 45(12), pp.4182--4191 |
 |
Subgrid Formulation of Optical Flow for the Study of Turbulent Flow
Cyril Cassisa, Serge Simoens, Véronique Prinet and Liang Shao Experiments in Fluids (ExpFlu) 2011, 51(6), pp.1739--1754 |
 |
Spatio-Temporal Interest Points Chain (STIPC) for activity recognition
Fei Yuan, Gui-Song Xia, Hichem Sahbi and Véronique Prinet Asian Conference on Pattern Recognition (ACPR) 2011 |
 |
Spatio-temporal Context Kernel for Activity Recognition
Fei Yuan, Hichem Sahbi and Véronique Prinet Asian Conference on Pattern Recognition (ACPR) 2011 |
 |
Extended Phase Field Higher-Order Active Contour Models for Networks:
Its Application to Road Network Extraction from VHR Satellite Image
Ting Peng, Ian H. Jermyn, Véronique Prinet and Joziane Zerubia International Journal of Computer Vision (IJCV) 2010, 88(1), pp.111--128 Project page |
 |
Towards Optimal Naive Bayes Nearest Neighbour
Régis Behmo, Paul Marcombes, Arnak Dalalyan and Véronique Prinet European Conference on Computer Vision (ECCV) 2010 Project page |
 |
Middle-Level Representation for Human Activities Recognition: the Role of Spatio-temporal Relationships
Fei Yuan, Véronique Prinet and Junsong Yuan European Computer Vision - Workshop on Human Motion (ECCVW) 2010 |
 |
Sub-grid physical optical flow for remote sensing of sandstorm
Cyril Cassisa, Serge Simoens and Véronique Prinet, Shao Liang International Geoscience and Remote Sensing Symposium (IGARSS) 2010 |
 |
A Robust Framework Based on Phase Field Modeling for Road Network Extraction from VHR Satellite Images
Ting Peng, Ian H. Jermyn, Véronique Prinet and Joziane Zerubia Chinese Journal of Computers (CJC), 2009 |
|
Conditional Mixed-state Model for Structural Change Analysis from VHR Optical Images
Benjamin Belmudez, Véronique Prinet, JianFeng Yao, Patrick Bouthemy and Xavier Descombes International Geoscience and Remote Sensing Symposium (IGARSS), 2009 |
 |
Two-frames Optical Flow Formulation in an Unwarped Multiresolution scheme
Cyril Cassisa, Serge Simoens and Véronique Prinet Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications (CIARP) 2009 Best Paper Honorable Mention |
 |
Formulation Physique du Flot Optique pour l'étude de Mouvements Turbulents
Cyril Cassisa, Serge Simoens, Véronique Prinet and Shao Liang Congrès Francais de Visualisation et de Traitement d'Images en Méanique des Fluides (FLUVISU) 2009 |
 |
Robust Change Detection in Dense Urban Areas via SVM Classifier
LiangLiang He and Ivan Laptev Workshop on Urban Remote Sensing (URBAN) 2009 |
 |
Graph Commute Times for Image Representation
Régis Behmo, Nikos Paragios and Véronique Prinet Computer Vision and Pattern Recognition (CVPR) 2008 |
 |
Mixture distributions for weakly supervised classification in remote sensing images
Jean-Baptiste Bordes and Véronique Prinet British Machine Vision Conference (BMVC) 2008 |
 |
An extended phase field higher-order active contour model for networks and
its application to road network extraction from VHR satellite images
Ting Peng, Ian H. Jermyn, Véronique Prinet, and Joziane Zerubia European Conference on Computer Vision (ECCV) 2008 |
 |
Incorporating generic and specific prior knowledge in a multi-scale phase field model for road extraction from VHR images
Ting Peng, Ian H. Jermyn, Véronique Prinet, and Joziane Zerubia IEEE Trans. Geoscience and Remote Sensing Special Issue: Selected Topics in Applied Earth Observations and Remote Sensing , 1(2):139-146, 2008 |
 |
Extraction of main and secondary roads in VHR images using a higher-order phase field model
Ting Peng, Ian H. Jermyn, Véronique Prinet, and Joziane Zerubia In Proc. XXI ISPRS Congress, Commission III, 2008 |
 |
An Application of Graph Commute Times to Image Indexing
Régis Behmo, Nikos Paragios and Véronique Prinet IEEE International Geoscience Remote Sensing Symposium (IGARSS) 2008 |
|
Optical flow estimation in a hybrid multi-resolution MRF framework
Cyril Cassisa, Véronique Prinet, Serge Simoens, Liang Shao and ChengLin Liu International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2008 |
Automatic change detection from sar images based on fuzzy entropy principle
CH Pan, V. Prinet, Q. Yang and SD Ma
Chinese Journal of Electronics, 16(1):176-81, 2007
A Phase Field Model Incorporating Generic and Specific Prior Knowledge Applied to Road Network
Extraction from VHR Satellite Image
T. Peng, I. Jermyn, V. Prinet, J. Zerubia and BG Hu
In Proc. British Machine Vision Conference (BMVC) 2007, Warwick, UK
Urban Road Extraction from VHR Images Using a Multiscale Approach and a Phase Field Model of Network Geometry
T. Peng, I. Jermyn, V. Prinet, J. Zerubia and BG Hu
In Proc. 4th IEEE GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas (URBAN) 2007,
Paris, France
Computing Invariants for Structural Change Detection in Urban areas
FF Tang and V. Prinet
In Proc. 4th IEEE GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas (URBAN) 2007,
Paris, France
Probabilistic Modeling for Structural Change Inference
W. Liu and V. Prinet
In Proc. Asian Conference on Computer Vision (ACCV) 2006, India,
and Lecture Notes in Computer Science vol. 3851
MRF Modeling for Optical Flow Computation From Multistructure Objects
V. Prinet, C. Cassisa and FF Tang
In Proc. International Conference on Image Processing (ICIP) 2006, Atlanta, USA
PS InSAR Technique and its Application in Beijing Area
J. Bai and V. Prinet
In Proc. IEEE International GeoscienceRemote Sensing Symposium (IGARSS) 2005 Seoul, Korea
Spatio-temporal prior shape constraint for level set segmentation
T. Bailloeul, V. Prinet, B. Serra, P. Marthon
Proc. Energy Minimisation Methods in Computer Vision and Pattern Recognition (EMMCVPR) 2005, and
Lecture Notes in Computer Science (LNCS) 3757 Springer-Verlag Berlin Heidelberg, pp. 503-519
Project page
Urban building land use change mapping from high resolution satellite imagery, active contours and Hough voting
T. Bailloeul, V. Prinet, B. Serra, P. Marthon, P. Chen and H. Zhang
In Proc. International Symposium on Physical Measurements and Signature in Remote Sensing (ISPMSRS) 2005
Digital building map refinement from knowledge-driven active contours and very high resolution optical imagery
T. Bailloeul, V. Prinet, B. Serra, P. Marthon, P. Chen and Haitai Zhang
Geo-information, 6:511-522, 2005
first published
In Proc. ISPRS High- Resolution Earth Imaging for Geospatial Information Workshop, 2005, Hannover, Germany
Building change analysis between GIS Data and satellite image
J.H. Duan, V. Prinet and H.Q. Lu
In Proc. IEEE International Geoscience And Remote Sensing Symposium (IGARSS) 2005, Seoul, Korea
Building Detection from High-resolution Satellite Image Using Probability Modeling
W. Liu and V. Prinet
In Proc. IEEE International Geoscience & Remote Sensing Symposium (IGARSS) 2005, Seoul, Korea
A Band-Weighted Landuse Classification Method for Multi-spectral Images
C.H. Pan, G. Wu and V. Prinet
In Proc. International Conference on Computer Vision and Pattern Recognition (CVPR) 2005, SanDiego, USA
Multi-Block PCA Method for Image Change Detection
B. Qiu, V. Prinet, E. Perrier and O. Monga
In Proc. International Conference on Image Analysis and Processing (ICIAP), 2003
Topography retrieval using interferometric synthetic aperture radar technique
F. Wang, V. Prinet and SD Ma
Acta Automatica Sinica, 28(4):527-534, 2002
Stolen from Jon Barron
Short Bio
I am currently a visiting Professor at the Institute of Automation of the Chinese Academy of Sciences. I was an Associate Professor in this same institute from 2000 to 2010, period during which I lead a research team on Image Understanding (RSIU). From 2011 to 2018, I spent eight wonderful years in Israel, at first in the CS departement of the Hebrew University of Jerusalem (HUJI), then at General Motors for a short adventure into the industrial world. I received my B.Sc. in Physics from University Jussieu Paris-VII, M.Sc.A. in Biomedical Engineering from University of Montreal, and Ph.D. in Computer Science from INRIA.
Full CV
pdfFormer Ph.D Students
- Fei YUAN (co-advised with Prof. Songde Ma, CASIA and Prof. Hichem Sahbi, ENST), May 2012
PhD thesis: Action retrieval for video summarization
CAS international students Fellowship - Régis BEHMO (co-advised with Prof. Nikos Paragios, Ecole Centrale ParisTech), Sept. 2010
PhD thesis: Visual Feature Graphs and Image Recognition (see also the slides)
INRIA Fellowship - Ting PENG (co-advised with Prof. Josiane Zerubia, INRIA-UNSA and Baogang Hu, CASIA), Nov 2008
PhD thesis: New higher-order active contour models, shape priors, and multiscale analysis: their application to road network extraction from very high resolution satellite images (also
in Chinese 
)
Recipient of the 2008 European Best IEEE Geoscience and Remote Sensing Society PhD Thesis Award
Alcatel Alenia Space Fellowship
French Ministry of Foreign Affairs Fellowship - Timothée BAILLOEUL (co-advised with Prof. Philippe Marthon, ENSEEITH and BaoGang Hu, CASIA), Dec 2005
PhD thesis: Active contours and prior knowledge for change analysis: application to digital urban building map updating from optical high resolution remote sensing images
(en francais
)
(egalement accessible sur le site de l'Institut National Polytechnique de Toulouse)
Alcatel Aliena Space Fellowship - Gang WU (co-advised with SongDe Ma and Chunhong Pan, CASIA), 2004
PhD thesis: Classification from remote sensing images - YanJie ZHANG (co-advised with Prof. ZhanYi Hu, CASIA), 2004
PhD thesis: Methods and applications on interferometry image processing - Feng WANG (co-advised with Prof. SongDe Ma, CASIA), 2003
PhD thesis: SAR image unwrapping techniques - ZhaoHui ZHANG (co-advised with Prof. SongDe Ma, CASIA), 2003
PhD thesis: Study on automatic registration from multi-sensor satellite images
Former M.Sc Students
- Cui ZHANG, May 2011
Shape Description for Image Matching - Xing GONG, May 2011
Change detection with structural and textural analysis of images - DongMin MA, May 2010
Segmentation and motion estimation in image sequences - LiangLiang HE (co-advised with Prof. Ivan Laptev, INRIA), May 2009.
Change Detection in Very High Resolution Satellite Images with Local Features and Statistical Classifier - Fengfeng TANG, May 2007.
Structural Change Detection in Very High Resolution Satellite Images - Jun BAI, 2005
Research and Application of PS InSAR and cross-interferometry - Wei LIU, 2005
Building Recognition and Change Inference Based on Very High Resolution Satellite Images Using Probabilistic Model - WenHui PENG, 2004
Unsupervised change detection from SAR images - ZhanWu YU, 2004
Multi-source data registration using fourier transform
Former Post-doctoral Fellows
- Bo QIU (CASIA), 2003
Former Interns
- Paul MARCOMBES (with Renaud Keriven, Ecole des Ponts ParisTech), 2010
- Pascal ZILLE (INSA Rouen), 2010
- Yves PIRIOU (Supaero), 2008
- Benjamin BELMUDEZ (with Patrick Bouthemy and Jianfeng Yao, INRIA), 2007
- Cyril CASSISA (with Shao Liang, INSA and Ecole Centrale Lyon), 2008-2010
- Jean-Baptiste BORDES (with Henri Maitre, ENST), 2008
Scientific talks
- 2021.4.29. Towards intelligent transportation systems: Urban traffic forecasting and autonomous parking
- 2019.6.25. Domain Agnostic Video Prediction from Motion Selective Kernels, @Tencent AI & Robotics X Labs, Shenzhen (Prof. ZhengYou Zhang)
- 2015.6.11. A Surface Reflectance Model and Applications in Video Sequences, @Brown University, Providence (Prof. Thomas Serre)
- 2013.10.3. Illuminant Estimation from Video Sequences, @Australian National University (Prof. Richard Hartley)
- 2011.12.4. Towards Optimal Naive Bayes Nearest Neighbour Classification, @The Hebrew University of Jerusalem, Israel (Prof. Shmuel Peleg)
- 2010.2.15. PhaseFields Higher-Order Active Contours Model with Shape Priors, @The Hebrew University of Jerusalem Israel (Prof. Schmuel Peleg).
- 2006.12.8. Contrainte de forme robuste pour la segmentation par contours actifs, Invited Speaker, Workshop Day @INRIA-Rennes ( Prof. Renaud Keriven)
- 2007.11.12. Change detection from VHR remote sensing images, @INRIA Sophia-Antipolis (Prof. Josiane Zerubia)
All publics talks
- Invited Speaker, TCI21 Forum, Climate change and Natural disaster: the role of ICT , Valenciennes France (October 30, 2008)
- Invited Speaker, TCI21 Forum, ICT and sustainable development: Green cities of China , Valenciennes France (October 30, 2008)
Regular courses
|
Image Processing and Computer Vision Spring 2001/2002/2003 University of the Chinese Academy of Sciences |
Summer Schools - teaching
- CIMPA Summer School "Partial Differential Equations and Computer Vision", @Beijing, 1999
- Summer School "Mathematical Methods for Multi-Channel Image Processing (MULT-IM)" @Beijing, July 2006
Summer Schools - Organisation committee
- "Machine Learning, Statistics and Computer Vision'', @Ezhou, Hubei, China, June 30-July 11 2008. Co-organised with Prof. Zhu SongChun (UCLA).
- ''Mathematical Methods for Multi-Channel Image Processing (MULT-IM)'', @Beijing, China, 3-8 July 2006. Co-organised with Prof. P.L. Combettes (Univ. Paris 6)