Search Results for author: Ferran Diego

Found 9 papers, 3 papers with code

Efficient Keyword Spotting by capturing long-range interactions with Temporal Lambda Networks

1 code implementation16 Apr 2021 Biel Tura, Santiago Escuder, Ferran Diego, Carlos Segura, Jordi Luque

This work explores the application of Lambda networks, an alternative framework for capturing long-range interactions without attention, for the keyword spotting task.

Keyword Spotting speech-recognition +1

Transcription-Enriched Joint Embeddings for Spoken Descriptions of Images and Videos

no code implementations1 Jun 2020 Benet Oriol, Jordi Luque, Ferran Diego, Xavier Giro-i-Nieto

In this work, we propose an effective approach for training unique embedding representations by combining three simultaneous modalities: image and spoken and textual narratives.

Retrieval

Unsupervised Representation Learning by Discovering Reliable Image Relations

no code implementations18 Nov 2019 Timo Milbich, Omair Ghori, Ferran Diego, Björn Ommer

To nevertheless find those relations which can be reliably utilized for learning, we follow a divide-and-conquer strategy: We find reliable similarities by extracting compact groups of images and reliable dissimilarities by partitioning these groups into subsets, converting the complicated overall problem into few reliable local subproblems.

Representation Learning Transfer Learning

CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation

no code implementations23 Oct 2018 Radek Mackowiak, Philip Lenz, Omair Ghori, Ferran Diego, Oliver Lange, Carsten Rother

State of the art methods for semantic image segmentation are trained in a supervised fashion using a large corpus of fully labeled training images.

Active Learning Image Segmentation +1

Sparse convolutional coding for neuronal assembly detection

1 code implementation NeurIPS 2017 Sven Peter, Elke Kirschbaum, Martin Both, Lee Campbell, Brandon Harvey, Conor Heins, Daniel Durstewitz, Ferran Diego, Fred A. Hamprecht

Cell assemblies, originally proposed by Donald Hebb (1949), are subsets of neurons firing in a temporally coordinated way that gives rise to repeated motifs supposed to underly neural representations and information processing.

Cost efficient gradient boosting

1 code implementation NeurIPS 2017 Sven Peter, Ferran Diego, Fred A. Hamprecht, Boaz Nadler

In contrast to previous approaches to learning with cost penalties, our method can grow very deep trees that on average are nonetheless cheap to compute.

Road Detection via On--line Label Transfer

no code implementations10 Dec 2014 José M. Álvarez, Ferran Diego, Joan Serrat, Antonio M. López

The major challenges of road detection are dealing with shadows and lighting variations and the presence of other objects in the scene.

Pedestrian Detection Video Alignment

Tracking Indistinguishable Translucent Objects over Time using Weakly Supervised Structured Learning

no code implementations CVPR 2014 Luca Fiaschi, Ferran Diego, Konstantin Gregor, Martin Schiegg, Ullrich Koethe, Marta Zlatic, Fred A. Hamprecht

We use weakly supervised structured learning to track and disambiguate the identity of multiple indistinguishable, translucent and deformable objects that can overlap for many frames.

Cannot find the paper you are looking for? You can Submit a new open access paper.