Imperial College London


Faculty of EngineeringDepartment of Computing

Senior Lecturer



+44 (0)20 7594 7123s.leutenegger Website




360ACE ExtensionSouth Kensington Campus






BibTex format

author = {Johns, E and Leutenegger, S and Davison, AJ},
doi = {10.1109/CVPR.2016.414},
publisher = {Computer Vision Foundation (CVF)},
title = {Pairwise Decomposition of Image Sequences for Active Multi-View Recognition},
url = {},
year = {2016}

RIS format (EndNote, RefMan)

AB - A multi-view image sequence provides a much richercapacity for object recognition than from a single image.However, most existing solutions to multi-view recognitiontypically adopt hand-crafted, model-based geometric methods,which do not readily embrace recent trends in deeplearning. We propose to bring Convolutional Neural Networksto generic multi-view recognition, by decomposingan image sequence into a set of image pairs, classifyingeach pair independently, and then learning an object classi-fier by weighting the contribution of each pair. This allowsfor recognition over arbitrary camera trajectories, withoutrequiring explicit training over the potentially infinite numberof camera paths and lengths. Building these pairwiserelationships then naturally extends to the next-best-viewproblem in an active recognition framework. To achievethis, we train a second Convolutional Neural Network tomap directly from an observed image to next viewpoint.Finally, we incorporate this into a trajectory optimisationtask, whereby the best recognition confidence is sought fora given trajectory length. We present state-of-the-art resultsin both guided and unguided multi-view recognition on theModelNet dataset, and show how our method can be usedwith depth images, greyscale images, or both.
AU - Johns,E
AU - Leutenegger,S
AU - Davison,AJ
DO - 10.1109/CVPR.2016.414
PB - Computer Vision Foundation (CVF)
PY - 2016///
SN - 1063-6919
TI - Pairwise Decomposition of Image Sequences for Active Multi-View Recognition
UR -
UR -
ER -