1.1k citations · 3.1k across the 34 of their papers we have counts for
7 papers · 1 filter
FastText.zip: Compressing text classification models
Armand Joulin, Edouard Grave, Piotr Bojanowski +3
We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutio…
Interferences in match kernels
Naila Murray, Hervé Jégou, Florent Perronnin +1
We consider the design of an image representation that embeds and aggregates a set of local descriptors into a single vector. Popular representations of this kind include the bag-o…
Polysemous codes
Matthijs Douze, Hervé Jégou, Florent Perronnin
This paper considers the problem of approximate nearest neighbor search in the compressed domain. We introduce polysemous codes, which offer both the distance estimation quality of…
How should we evaluate supervised hashing?
Alexandre Sablayrolles, Matthijs Douze, Hervé Jégou +1
Hashing produces compact representations for documents, to perform tasks like classification or retrieval based on these short codes. When hashing is supervised, the codes are trai…
Efficient softmax approximation for GPUs
Edouard Grave, Armand Joulin, Moustapha Cissé +2
We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the li…
Approximate search with quantized sparse representations
Himalaya Jain, Patrick Pérez, Rémi Gribonval +2
This paper tackles the task of storing a large collection of vectors, such as visual descriptors, and of searching in it. To this end, we propose to approximate database vectors by…
Tubelets: Unsupervised action proposals from spatiotemporal super-voxels
Mihir Jain, Jan van Gemert, Hervé Jégou +2
This paper considers the problem of localizing actions in videos as a sequences of bounding boxes. The objective is to generate action proposals that are likely to include the acti…