Learn More
The success of kernel methods including support vector networks (SVMs) strongly depends on the design of appropriate kernels. While initially kernels were designed in order to handle fixed-length data, their extension to unordered, variable-length data became more than necessary for real pattern recognition problems such as object recognition and(More)
The success of kernel methods including support vector machines (SVMs) strongly depends on the design of appropriate kernels. While initially kernels were designed in order to handle fixed-length data, their extension to unordered, variable-length data became more than necessary for real pattern recognition problems such as object recognition and(More)
The success of kernel methods including support vector machines (SVMs) strongly depends on the design of appropriate kernels. While initially kernels were designed in order to handle fixed-length data, their extension to unordered, variable-length data became more than necessary for real pattern recognition problems such as object recognition and(More)
In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for simultaneous vehicle detection, part local-ization, visibility characterization and 3D dimension estimation. Its architecture is based on a new coarse-to-fine object proposal(More)
Given an untextured 3D car models dataset, are we able to learn a robust make and model classifier which will be applied on real color images? One solution consists in finding a common representation between synthetic edge images and real color images. To address this issue, we introduce novel edge-color invariant features for 2D/3D car fine-grained(More)
We propose a new approach for accurate car pose estimation in images using only a dataset of 3D untextured models. Our algorithm detects both a car and its 3D pose. It is based on the matching of 3D models with the car in the image. With a part detector based on Convolutional Neural Networks, interest points corresponding to predefined 3D parts are(More)
Building large video datasets is a crucial task for many applications but is also very expensive in practice. In order to avoid annotating all the frames, the annotations from the labeled frames can be propagated using an offline tracker for each object. Following methods based on dynamic programming and eventually distance transforms, we introduce a new(More)
  • 1