E
Emmanuel Dellandréa
Researcher at École centrale de Lyon
Publications - 106
Citations - 2332
Emmanuel Dellandréa is an academic researcher from École centrale de Lyon. The author has contributed to research in topics: Object detection & Audio signal. The author has an hindex of 25, co-authored 103 publications receiving 1864 citations. Previous affiliations of Emmanuel Dellandréa include University of Lyon & François Rabelais University.
Papers
More filters
Proceedings ArticleDOI
Reconstructive and Discriminative Sparse Representation for Visual Object Categorization
TL;DR: The results have shown that the approach is more efficient than a sparse representation being only reconstructive, which indicates that adding a discriminative term for constructing the sparse representation is more suitable for the categorization purpose.
Proceedings Article
Multimodal search for graphic designers
Sandra Skaff,David Rouquet,Emmanuel Dellandréa,Achille Falaise,Valérie Bellynck,Hervé Blanchon,Christian Boitet,Didier Schwab,Liming Chen,Alexandre Saidi,Gabriela Csurka,Luca Marchesotti +11 more
TL;DR: It is shown how OMNIA can be used for simple, efficient, and intuitive asset search in the context of graphic design applications.
Journal Article
Visual object categorization based on the fusion of region and local features.
TL;DR: Experimental results demonstrate that the region-based features can be combined with SIFT features to reinforce performance, suggesting that the features managed to extract information which is complementary to the one of SFT features.
Posted Content
Bicameral Structuring and Synthetic Imagery for Jointly Predicting Instance Boundaries and Nearby Occlusions from a Single Image.
TL;DR: A fully convolutional bicameral structuring, composed of two cascaded decoders sharing one deep encoder, linked altogether by skip connections to combine local and global features, for jointly predicting instance boundaries and their unoccluded side is proposed.
Proceedings ArticleDOI
Image modeling using statistical measures for visual object categorization
TL;DR: The results show that merging the region based features and SIFT which are from different sources using an early fusion can actually improve classification performance, suggesting that these features managed to extract information which is complementary to each other.