Search Results for author: Amaia Salvador

Found 19 papers, 11 papers with code

Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning

1 code implementation CVPR 2021 Amaia Salvador, Erhan Gundogdu, Loris Bazzani, Michael Donoser

Cross-modal recipe retrieval has recently gained substantial attention due to the importance of food in people's lives, as well as the availability of vast amounts of digital cooking recipes and food images to train machine learning models.

Self-Supervised Learning

Mask-guided sample selection for Semi-Supervised Instance Segmentation

no code implementations25 Aug 2020 Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto

Our method consists in first predicting pseudo-masks for the unlabeled pool of samples, together with a score predicting the quality of the mask.

Active Learning Instance Segmentation +2

WiCV 2019: The Sixth Women In Computer Vision Workshop

no code implementations23 Sep 2019 Irene Amerini, Elena Balashova, Sayna Ebrahimi, Kathryn Leonard, Arsha Nagrani, Amaia Salvador

In this paper we present the Women in Computer Vision Workshop - WiCV 2019, organized in conjunction with CVPR 2019.

Budget-aware Semi-Supervised Semantic and Instance Segmentation

no code implementations14 May 2019 Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto

Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention.

Instance Segmentation Semantic Segmentation

Elucidating image-to-set prediction: An analysis of models, losses and datasets

1 code implementation11 Apr 2019 Luis Pineda, Amaia Salvador, Michal Drozdzal, Adriana Romero

In this paper, we identify an important reproducibility challenge in the image-to-set prediction literature that impedes proper comparisons among published methods, namely, researchers use different evaluation protocols to assess their contributions.

Multi-Label Classification

RVOS: End-to-End Recurrent Network for Video Object Segmentation

1 code implementation CVPR 2019 Carles Ventura, Miriam Bellver, Andreu Girbau, Amaia Salvador, Ferran Marques, Xavier Giro-i-Nieto

Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence.

One-shot visual object segmentation Unsupervised Video Object Segmentation +1

Inverse Cooking: Recipe Generation from Food Images

4 code implementations CVPR 2019 Amaia Salvador, Michal Drozdzal, Xavier Giro-i-Nieto, Adriana Romero

Our system predicts ingredients as sets by means of a novel architecture, modeling their dependencies without imposing any order, and then generates cooking instructions by attending to both image and its inferred ingredients simultaneously.

Recipe Generation

Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images

no code implementations14 Oct 2018 Javier Marin, Aritro Biswas, Ferda Ofli, Nicholas Hynes, Amaia Salvador, Yusuf Aytar, Ingmar Weber, Antonio Torralba

In this paper, we introduce Recipe1M+, a new large-scale, structured corpus of over one million cooking recipes and 13 million food images.

General Classification

Cross-modal Embeddings for Video and Audio Retrieval

1 code implementation7 Jan 2018 Didac Surís, Amanda Duarte, Amaia Salvador, Jordi Torres, Xavier Giró-i-Nieto

The increasing amount of online videos brings several opportunities for training self-supervised neural networks.

Recurrent Neural Networks for Semantic Instance Segmentation

1 code implementation2 Dec 2017 Amaia Salvador, Miriam Bellver, Victor Campos, Manel Baradad, Ferran Marques, Jordi Torres, Xavier Giro-i-Nieto

We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image.

Instance Segmentation Semantic Segmentation

Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks

3 code implementations29 Aug 2016 Alberto Montes, Amaia Salvador, Santiago Pascual, Xavier Giro-i-Nieto

This thesis explore different approaches using Convolutional and Recurrent Neural Networks to classify and temporally localize activities on videos, furthermore an implementation to achieve it has been proposed.

Action Detection Activity Detection

Faster R-CNN Features for Instance Search

3 code implementations29 Apr 2016 Amaia Salvador, Xavier Giro-i-Nieto, Ferran Marques, Shin'ichi Satoh

This work explores the suitability for instance retrieval of image- and region-wise representations pooled from an object detection CNN such as Faster R-CNN.

Instance Search Object Detection +1

Bags of Local Convolutional Features for Scalable Instance Search

2 code implementations15 Apr 2016 Eva Mohedano, Amaia Salvador, Kevin McGuinness, Ferran Marques, Noel E. O'Connor, Xavier Giro-i-Nieto

This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW).

Instance Search

Cultural Event Recognition with Visual ConvNets and Temporal Models

no code implementations24 Apr 2015 Amaia Salvador, Matthias Zeppelzauer, Daniel Manchon-Vizuete, Andrea Calafell, Xavier Giro-i-Nieto

Our solution is based on the combination of visual features extracted from convolutional neural networks with temporal information using a hierarchical classifier scheme.

Classification General Classification

Exploring EEG for Object Detection and Retrieval

no code implementations9 Apr 2015 Eva Mohedano, Amaia Salvador, Sergi Porta, Xavier Giró-i-Nieto, Graham Healy, Kevin McGuinness, Noel O'Connor, Alan F. Smeaton

We show that it is indeed possible to detect such objects in complex images and, also, that users with previous knowledge on the dataset or experience with the RSVP outperform others.

Content-Based Image Retrieval EEG +1

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