LAMP

Category: Publications

  • 3D color charts for camera spectral sensitivity estimation

    R Deeb, D Muselet, M Hebert, A Tremeau, J van de Weijer, F ETIENNE Read Full Paper → Estimating spectral data such as camera sensor responses or illuminant spectral power distribution from raw RGB camera outputs is crucial in many computer vision applications. Usually, 2D color charts with various patches of known spectral reflectance are used as reference […]

  • LIUM-CVC Submissions for WMT17 Multimodal Translation Task

    Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Marc Masana, Luis Herranz, Joost van de Weijer Read Full Paper → This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. We mainly explored two multimodal architectures where either global visual features or convolutional feature maps are […]

  • Improved Recursive Geodesic Distance Computation for Edge Preserving Filter

    Mikhail G. Mozerov; Joost van de Weijer Read Full Paper → All known recursive filters based on the geodesic distance affinity are realized by two 1D recursions applied in two orthogonal directions of the image plane. The 2D extension of the filter is not valid and has theoretically drawbacks, which lead to known artifacts. In this […]

  • Bandwidth Limited Object Recognition in High Resolution Imagery

    Laura Lopez-Fuentes; Andrew D. Bagdanov; Joost Van De Weijer; Harald Skinnemoen Read Full Paper → This paper proposes a novel method to optimize bandwidth usage for object detection in critical communication scenarios. We develop two operating models of active information seeking. The first model identifies promising regions in low resolution imagery and progressively requests higher resolution regions on […]

  • Ensembles of Generative Adversarial Networks

    Yaxing Wang, Lichao Zhang, Joost van de Weijer Read Full Paper → Ensembles are a popular way to improve results of discriminative CNNs. The combination of several networks trained starting from different initializations improves results significantly. In this paper we investigate the usage of ensembles of GANs. The specific nature of GANs opens up several new ways […]

  • Invertible Conditional GANs for image editing

    Guim Perarnau, Joost van de Weijer, Bogdan Raducanu, Jose M. Álvarez Read Full Paper → Generative Adversarial Networks (GANs) have recently demonstrated to successfully approximate complex data distributions. A relevant extension of this model is conditional GANs (cGANs), where the introduction of external information allows to determine specific representations of the generated images. In this work, we evaluate […]

  • Does Multimodality Help Human and Machine for Translation and Image Captioning?

    Ozan Caglayan, Walid Aransa, Yaxing Wang, Marc Masana, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Joost van de Weijer Read Full Paper → This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge. We explored various comparative methods, namely phrase-based systems and attentional recurrent neural networks models trained using monomodal or multimodal data. We also performed […]

  • On-the-fly Network Pruning for Object Detection

    Marc Masana, Joost van de Weijer, Andrew D. Bagdanov Read Full Paper → Object detection with deep neural networks is often performed by passing a few thousand candidate bounding boxes through a deep neural network for each image. These bounding boxes are highly correlated since they originate from the same image. In this paper we investigate how […]

  • Hierarchical part detection with deep neural networks

    Esteve Cervantes; Long Long Yu; Andrew D. Bagdanov; Marc Masana; Joost van de Weijer Read Full Paper → Part detection is an important aspect of object recognition. Most approaches apply object proposals to generate hundreds of possible part bounding box candidates which are then evaluated by part classifiers. Recently several methods have investigated directly regressing to a limited set […]

  • FitNets: Hints for Thin Deep Nets

    Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, Yoshua Bengio Read Full Paper → While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student […]