Search Results - "Jiu, Mingyuan"

Nonlinear Deep Kernel Learning for Image Annotation by Mingyuan Jiu, Sahbi, Hichem

“…Multiple kernel learning (MKL) is a widely used technique for kernel design. Its principle consists in learning, for a given support vector classifier, the…”
Get full text

Laplacian deep kernel learning for image annotation by Mingyuan Jiu, Sahbi, Hichem

“…Semi-supervised learning seeks to build accurate classification machines by taking advantage of both labeled and unlabeled data. This learning scheme is useful…”
Get full text

Deep kernel map networks for image annotation by Mingyuan Jiu, Sahbi, Hichem

“…Deep multiple kernel learning is a powerful technique that selects and deeply combines multiple elementary kernels in order to provide the best performance on…”
Get full text

Semi supervised deep kernel design for image annotation by Mingyuan Jiu, Sahbi, Hichem

“…It is commonly agreed that the success of support vector machines (SVMs), is highly dependent on the choice of particular similarity functions referred to as…”
Get full text

Evaluation of video activity localizations integrating quality and quantity measurements by Wolf, Christian, Lombardi, Eric, Mille, Julien, Celiktutan, Oya, Jiu, Mingyuan, Dogan, Emre, Eren, Gonen, Baccouche, Moez, Dellandréa, Emmanuel, Bichot, Charles-Edmond, Garcia, Christophe, Sankur, Bülent

“…•A new evaluation procedure for action localization is proposed.•We introduce performance graphs showing quantity as a function of quality.•A single…”
Get full text

Detection of Conductive Particles in TFT-LCD Circuit Using Generative Adversarial Networks by Wang, Yuanyuan, Ma, Ling, Jiu, Mingyuan, Jiang, Huiqin

“…The inspection of conductive particles is a crucial step in the Thin Film Transistor Liquid Crystal Display (TFT-LCD) circuit detection process since only…”
Get full text

Sparse Hierarchical Interaction Learning with Epigraphical Projection by Jiu, Mingyuan, Pustelnik, Nelly, Janaqi, Stefan, Chebre, Mériam, Qi, Lin, Ricoux, Philippe

“…This work focuses on learning optimization problems with quadratical interactions between variables, which go beyond the additive models of traditional linear…”
Get full text

Deep representation design from deep kernel networks by Jiu, Mingyuan, Sahbi, Hichem

“…•Deep map network is proposed to efficiently approximate deep kernel network.•Unsupervised fine-tuning algorithm is proposed for deep map network.•The results…”
Get full text

A Deep Primal-Dual Proximal Network for Image Restoration by Jiu, Mingyuan, Pustelnik, Nelly

“…Image restoration remains a challenging task in image processing. Numerous methods tackle this problem, which is often solved by minimizing a nonsmooth…”
Get full text

Context-aware deep kernel networks for image annotation by Jiu, Mingyuan, Sahbi, Hichem

“…•A novel context-aware deep kernel network that learns context is proposed.•The learning algorithms for layerwise, stationary and classwise contexts are…”
Get full text

Alternative Design of DeepPDNet in the Context of Image Restoration by Jiu, Mingyuan, Pustelnik, Nelly

“…This work designs an image restoration deep network relying on unfolded Chambolle-Pock primal-dual iterations. Each layer of our network is built from…”
Get full text

DHCN: Deep Hierarchical Context Networks For Image Annotation by Jiu, Mingyuan, Sahbi, Hichem

“…Context modeling is one of the most fertile sub-fields of visual recognition which aims at designing discriminant image representations while incorporating…”
Get full text

End-to-End Deep Kernel Map Design for Image Annotation by Jiu, Mingyuan, Sahbi, Hichem

“…Deep kernel map networks have shown excellent performances in various classification problems including image annotation. Their general recipe consists in…”
Get full text

Multiclass SVM with graph path coding regularization for face classification by Mingyuan Jiu, Pustelnik, Nelly, Chebre, Meriam, Janaqv, Stefan, Ricoux, Philippe

“…We consider the problem of learning graphs in a sparse multiclass support vector machines framework. For such a problem, sparse graph penalty is useful to…”
Get full text

Human body part estimation from depth images via spatially-constrained deep learning by Jiu, Mingyuan, Wolf, Christian, Taylor, Graham, Baskurt, Atilla

“…•We integrate spatial part layout into supervised learning of the deep ConvNets.•Spatial learning for unsupervised pre-training of the deep ConvNets is…”
Get full text

Deep Context Networks for Image Annotation by Jiu, Mingyuan, Sahbi, Hichem, Qi, Lin

“…Context plays an important role in visual pattern recognition as it provides complementary clues for different learning tasks including image classification…”
Get full text

Supervised Learning and Codebook Optimization for Bag-of-Words Models by Jiu, Mingyuan, Wolf, Christian, Garcia, Christophe, Baskurt, Atilla

“…In this paper, we present a novel approach for supervised codebook learning and optimization for bag-of-words models. This type of models is frequently used in…”
Get full text

Alternative design of DeepPDNet in the context of image restoration by Jiu, Mingyuan, Pustelnik, Nelly

“…IEEE Signal Processing Letters 2022 This work designs an image restoration deep network relying on unfolded Chambolle-Pock primal-dual iterations. Each layer…”
Get full text

Image Annotation based on Deep Hierarchical Context Networks by Jiu, Mingyuan, Sahbi, Hichem

“…Context modeling is one of the most fertile subfields of visual recognition which aims at designing discriminant image representations while incorporating…”
Get full text

A deep primal-dual proximal network for image restoration by Jiu, Mingyuan, Pustelnik, Nelly

“…Image restoration remains a challenging task in image processing. Numerous methods tackle this problem, often solved by minimizing a non-smooth penalized…”
Get full text