- SyMIL: MinMax Latent SVM for Weakly Labeled Data. [pdf]
IEEE Transactions on Neural Networks and Learning Systems (IF: 4.6), to appear, 2018.
- Exploiting Negative Evidence for Deep Latent Structured Models. [pdf] IEEE Transactions on Pattern Analysis and Machine Intelligence (IF: 8.3), January 2018.
- Gaze Latent Support Vector Machine for Image Classification Improved by Weakly Supervised Region Selection. [pdf] Pattern Recognition (PR) (5-year IF: 4.991), to appear, 2017.
- Learning a Distance Metric from Relative Comparisons between
Quadruplets of Images. [pdf]
International Journal of Computer Vision (IJCV) (5-year IF: 4.65), Volume 121, Issue 1, pp 65-94, January 2017 (online June 2016).
- Perceptual principles for video classification with Slow Feature Analysis. [Project Page]
IEEE Journal of Selected Topics in Signal Processing (IF: 3.6), p. 428-437, vol 8, April 2014.
- Learning Deep Hierarchical Visual Feature Coding. [pdf]
, IEEE Transactions on Neural Networks and Learning Systems (IF: 4.6), p. 2212-2225, vol 12, December 2014.
- SnooperText: A Text Detection System for Automatic Indexing of Urban Scenes. [Project Page] [pdf]
Computer Vision and Image Understanding (CVIU), p. 92-104, vol 122, May 2014.
- JKernelMachines: A simple framework for Kernel Machines. [mloss page] [pdf]
Journal of Machine Learning Research (JMLR), track for Machine Learning Open Source Software, p. 1417-1421, vol 14, May 2013.
- Extended Coding and Pooling in the HMAX Model. [Project Page] [pdf]
IEEE Transactions on Image Processing, vol 22, num 2, p. 764-777, Feb 2013.
- Pooling in Image Representation: the Visual Codeword Point of View. [Project Page]
Computer Vision and Image Understanding (CVIU), Special Issue on Visual Concept Detection, vol 117, num 5, p. 453-465, May 2013.
- T-HOG: an Effective Gradient-Based Descriptor for Single Line Text Regions. [Project Page] [pdf]
Pattern Recognition (PR), vol 46, num 3, p. 1078-1090, March 2013.
- A Cognitive and Video-based Approach for Multinational License Plate Recognition.
Machine Vision and Applications (5-year-IF: 1.324),
vol 22, num 2, p. 389-407, March 2011.
- A Real-Time, MultiView Fall Detection System: a LHMM-Based Approach. [pdf]
IEEE Transactions on Circuits and Systems for Video Technology
(5-year-IF: 3.102) , Special Issue on Event
Analysis in Videos, vol 18, Issue 11, p.1522-1532, November 2008.
- Learning Articulated Appearance Models for Tracking Humans: a Spectral Graph Matching Approach. [pdf]
- Manifold Learning in Quotient Spaces. [pdf]
- Cross-modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings. [pdf]
- MUTAN: Multimodal Tucker Fusion for Visual Question Answering. [pdf]
- Deformable Part-based Fully Convolutional
Network for Object Detection. [pdf]
BMCV 2017 (oral). BMVC'17 Best Science Paper Award
- WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation. [pdf]
- WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks. [pdf]
- Gaze Latent Support Vector Machine for Image Classification. [pdf]
- Max-Min convolutional neural networks for image classification. [pdf]
- Deep Neural Netwrks Under Stress. [pdf]
- MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking. [pdf] - [supplementary material]- [Project Page]
- LR-CNN For Fine-grained Classification with Varying Resolution. [pdf].
- Exemplar Based Metric Learning For Robust Visual Localization. [pdf].
- Incremental Learning of Latent Structural SVM for Weakly Supervised Image Classification. [pdf].
ICIP 2014, Paris, France, 27-30 Oct 2014.
- Semantic Pooling for Image Categorization using Multiple Kernel Learning. [pdf]
ICIP 2014, Paris, France, 27-30 Oct 2014.
- Fantope Regularization in Metric Learning. [pdf]- [Project Page]
CVPR 2014, Columbus, Ohio, USA, 24-27 June 2014.
- Sequentially Generated Instance-Dependent Image Representations for Classification. [pdf]
ICLR 2014, Banff, Canada, 14-16 April 2014.
- Top-Down Regularization of Deep Belief Networks. [pdf]
NIPS 2013, p 1878-1886, Lake Tahoe, Nevada, USA, 5-8 December 2013.
- Quadruplet-wise Image Similarity Learning. [pdf]
ICCV 2013, Sydney, Australia, 3-6 December 2013.
- Image Classification using Object Detectors. [pdf]
ICIP 2013, p. 4340-4344, Melbourne, Australia, 15-18 Sep 2013.
- Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis. [pdf]
CVPR 2013, p 2603-2610, Portland, OR, USA, 23-28 June 2013.
- Unsupervised and Supervised Visual Codes with Restricted Boltzmann Machines. [pdf]
ECCV 2012, p 298-311, Firenze, Italy, 7-13 Oct 2012.
- Structural and visual comparisons for Web page archiving. [pdf]
DocEng 2012. To appear.
- Contextual Detection of drawn Symbols in old Maps. [pdf]
ICIP 2012, p 837-840, Orlando, USA, 2012.
- BossaNova at ImageCLEF 2012 Flickr Photo Annotation Task. [pdf]
Working Notes of the Conference and Labs of the Evaluation Forum (CLEF). To appear.
- Learning geometric combinations of Gaussian kernels with alternating Quasi-Newton algorithm [pdf]
- Classification of Urban Scenes from Georeferenced Images in Urban Street-View Context
International Conference on Machine Learning and Applications (ICMLA 2012).
- HMAX-S: Deep scale representation for biologically inspired image categorization. [pdf]
ICIP 2011, p 1261-1264, ISBN: 978-1-4577-1304-0, Brussels, 11-14 Sep 2011.
- BOSSA: extended BoW formalism for image classification. [pdf]
ICIP 2011, p 2909-2912, ISBN: 978-1-4673-0062-9, Brussels, 11-14 Sep 2011.
- SnooperTrack: Text Detection and Tracking for Outdoor Videos. [pdf]
ICIP 2011, p 505-508, ISBN: 978-1-4577-1304-0, Brussels, 11-14 Sep 2011.
- Learning Invariant Color Features with Sparse Topographic RBM. [pdf]
ICIP 2011., p 1241-1244, Brussels, 11-14 Sep 2011.
- Efficient Bag-of-Feature kernel representation for image similarity search. [pdf]
ICIP 2011.p 109-112, Brussels, 11-14 Sep 2011.
- Pedestrian head detection and tracking using graph skeleton for people counting in crowded environments.
Conference on Machine Vision Applications (MVA2011).
- People counting using skeleton graph and tracking.
The IASTED International Conference on Signal and Image Processing and Applications, SIPA 2011, Crete, Greece, 2011.
- An efficient System for combining complementary kernels in complex visual categorization tasks.
International Conference on Image Processing (ICIP 2010) , p 3877-3880,
ISBN: 978-1-4244-7992-4, Hong-Kong, 26-29 Sep 2010.
- SnooperText: A Multiresolution System for Text Detection in Complex Visual Scenes. [pdf]
International Conference on Image Processing (ICIP 2010), p 3861-3864, ISBN: 978-1-4244-7992-4 , Hong-Kong, 26-29 Sep 2010.
- Fast People Counting using Head Detection from Skeleton Graph. [pdf]
International Conference on Advanced Video and Signal based
Surveillance (IEEE AVSS), pp.233-240, Boston, 29 august-1 september 2010.
- A Bottom/Up, View Point Invariant Human Detector. [pdf]
19th International Conference on Pattern Recognition (ICPR), p. 1-4,
Tampa, Florida, December 8-11 2008.
- A Combined Statistical-Structural Strategy for Alphanumeric Recognition. [pdf]
3rd International Symposium on Visual Computing (ISVC), p. 529-538
Lake Tahoe, Nevada, California, November 26--28 2007.
- A HHMM-Based Approach for Robust Fall Detection. [pdf]
- Recipe Recognition with Large Multimodal Food Dataset
Workshop on Cooking and Eating Activities, ICME 2015.
- Absolute geo-localization thanks to Hidden Markov Model and exemplar-based
metric learning [pdf]
Workshop on Computer Vision in Vehicle Technology, CVPR 2015.
- Hybrid Pooling Fusion in the BoW Pipeline
Workshop on Information fusion in computer vision for concept recognition, ECCV 2012.
- Structural and Visual Similarity Learning for Web Page Archiving [pdf]
10th workshop on Content-Based Multimedia Indexing,
Content-Based Multimedia Indexing, 2012.
- Text Detection and Recognition in Urban Scenes. [pdf]
CVRS workshop - ICCV 2011, p 227-234, ISBN: 978-1-4673-0062-9, 6-13 Nov 2011.
- Combining complementary kernels in complex visual categorization [poster][abstract]
KDCV workshop - ICCV 2011, Barcelona, 6-13 Nov 2011.
- Biasing Restricted Boltzmann Machines to Manipulate Latent Selectivity and Sparsity. [pdf] [Supplementary]
NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning, p 1-8, Vancouver, Canada, 2010.
Habilitation to Drive Research (HDR)
Representations & Learning for Semantic Annotation of
Visual Data [manuscript] - [slides]
, 1st July 2015.
Hierarchical Representations for Shape Recognition,
People Identification and Motion Analysis in Image Sequences, 11 July 2007.