Aggregating local descriptors into a compact image representation
- H. Jégou, Matthijs Douze, C. Schmid, P. Pérez
- Computer ScienceIEEE Computer Society Conference on Computer…
- 13 June 2010
This work proposes a simple yet efficient way of aggregating local image descriptors into a vector of limited dimension, which can be viewed as a simplification of the Fisher kernel representation, and shows how to jointly optimize the dimension reduction and the indexing algorithm.
Region filling and object removal by exemplar-based image inpainting
- A. Criminisi, P. Pérez, K. Toyama
- Computer ScienceIEEE Transactions on Image Processing
- 1 September 2004
The simultaneous propagation of texture and structure information is achieved by a single, efficient algorithm that combines the advantages of two approaches: exemplar-based texture synthesis and block-based sampling process.
Aggregating Local Image Descriptors into Compact Codes
- H. Jégou, F. Perronnin, Matthijs Douze, Jorge Sánchez, P. Pérez, C. Schmid
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 September 2012
This paper first presents and evaluates different ways of aggregating local image descriptors into a vector and shows that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension.
Poisson image editing
- P. Pérez, M. Gangnet, A. Blake
- ArtACM Transactions on Graphics
- 1 July 2003
Using generic interpolation machinery based on solving Poisson equations, a variety of novel tools are introduced for seamless editing of image regions. The first set of tools permits the seamless…
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
- Tuan-Hung Vu, Himalaya Jain, Max Bucher, M. Cord, P. Pérez
- Computer ScienceComputer Vision and Pattern Recognition
- 30 November 2018
This work proposes two novel, complementary methods using (i) entropy loss and (ii) adversarial loss respectively for unsupervised domain adaptation in semantic segmentation with losses based on the entropy of the pixel-wise predictions.
Color-Based Probabilistic Tracking
- P. Pérez, C. Hue, J. Vermaak, M. Gangnet
- Computer ScienceEuropean Conference on Computer Vision
- 28 May 2002
This work introduces a new Monte Carlo tracking technique based on the same principle of color histogram distance, but within a probabilistic framework, and introduces the following ingredients: multi-part color modeling to capture a rough spatial layout ignored by global histograms, incorporation of a background color model when relevant, and extension to multiple objects.
Object removal by exemplar-based inpainting
- A. Criminisi, P. Pérez, K. Toyama
- Computer ScienceIEEE Computer Society Conference on Computer…
- 18 June 2003
A best-first algorithm in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting, which demonstrates the effectiveness of the algorithm in removing large occluding objects as well as thin scratches.
MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction
- Ayush Tewari, M. Zollhöfer, C. Theobalt
- Computer ScienceIEEE International Conference on Computer Vision…
- 30 March 2017
A novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image and can be trained end-to-end in an unsupervised manner, which renders training on very large real world data feasible.
Interactive Image Segmentation Using an Adaptive GMMRF Model
- A. Blake, C. Rother, Matthew A. Brown, P. Pérez, Philip H. S. Torr
- Computer ScienceEuropean Conference on Computer Vision
- 11 May 2004
Estimation is performed by solving a graph cut problem for which very efficient algorithms have recently been developed, however the model depends on parameters which must be set by hand and the aim of this work is for those constants to be learned from image data.
Retrieving actions in movies
A new annotated human action dataset is introduced and a new "keyframe priming" that combines discriminative models of human motion and shape within an action is shown to significantly improve the performance of action detection.
...
...