R
Relja Arandjelovic
Researcher at École Normale Supérieure
Publications - 57
Citations - 9416
Relja Arandjelovic is an academic researcher from École Normale Supérieure. The author has contributed to research in topics: Convolutional neural network & Image retrieval. The author has an hindex of 30, co-authored 51 publications receiving 6787 citations. Previous affiliations of Relja Arandjelovic include University of Oxford & PSL Research University.
Papers
More filters
Proceedings ArticleDOI
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
TL;DR: A convolutional neural network architecture that is trainable in an end-to-end manner directly for the place recognition task and an efficient training procedure which can be applied on very large-scale weakly labelled tasks are developed.
Proceedings ArticleDOI
Three things everyone should know to improve object retrieval
TL;DR: A new method to compare SIFT descriptors (RootSIFT) which yields superior performance without increasing processing or storage requirements, and a novel method for query expansion where a richer model for the query is learnt discriminatively in a form suited to immediate retrieval through efficient use of the inverted index.
Proceedings ArticleDOI
All About VLAD
TL;DR: It is shown that a simple change to the normalization method significantly improves retrieval performance and vocabulary adaptation can substantially alleviate problems caused when images are added to the dataset after initial vocabulary learning.
Proceedings ArticleDOI
Look, Listen and Learn
TL;DR: There is a valuable, but so far untapped, source of information contained in the video itself – the correspondence between the visual and the audio streams, and a novel “Audio-Visual Correspondence” learning task that makes use of this.
Journal ArticleDOI
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
TL;DR: A convolutional neural network architecture that is trainable in an end-to-end manner directly for the place recognition task, and significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks.