Abstract: In this paper we propose to learn a multimodal image and text embedding from Web and Social Media data, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the pipeline can learn from images with associated text without supervision and perform a thourough analysis of five different text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text based image retrieval task, and we clearly outperform state of the art in the MIRFlickr dataset when training in the target data. Further we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.

Abstract: Transfer learning aims at adapting a model learned from source dataset to target dataset. It is a beneficial approach especially when annotating on the target dataset is expensive or infeasible. Transfer learning has demonstrated its powerful learning capabilities in various vision tasks. Despite transfer learning being a promising approach, it is still an open question how to adapt the model learned from the source dataset to the target dataset. One big challenge is to prevent the impact of category bias on classification performance. Dataset bias exists when two images from the same category, but from different datasets, are not classified as the same. To address this problem, a transfer learning algorithm has been proposed, called negative back-dropout transfer learning (NB-TL), which utilizes images that have been misclassified and further performs back-dropout strategy on them to penalize errors. Experimental results demonstrate the effectiveness of the proposed algorithm. In particular, the authors evaluate the performance of the proposed NB-TL algorithm on UCF 101 action recognition dataset, achieving 88.9% recognition rate.

Abstract: This paper proposes Convolve, Attend and Spell, an attention based sequence-to-sequence model for handwritten word recognition. The proposed architecture has three main parts: an encoder, consisting of a CNN and a bi-directional GRU, an attention mechanism devoted to focus on the pertinent features and a decoder formed by a one-directional GRU, able to spell the corresponding word, character by character. Compared with the recent state-of-the-art, our model achieves competitive results on the IAM dataset without needing any pre-processing step, predefined lexicon nor language model. Code and additional results are available in https://github.com/omni-us/research-seq2seq-HTR.

Abstract: When extracting information from handwritten documents, text transcription and named entity recognition are usually faced as separate subsequent tasks. This has the disadvantage that errors in the first module affect heavily the
performance of the second module. In this work we propose to do both tasks jointly, using a single neural network with a common architecture used for plain text recognition. Experimentally, the work has been tested on a collection of historical marriage records. Results of experiments are presented to show the effect on the performance for different
configurations: different ways of encoding the information, doing or not transfer learning and processing at text line or multi-line region level. The results are comparable to state of the art reported in the ICDAR 2017 Information Extraction competition, even though the proposed technique does not use any dictionaries, language modeling or post processing.

Abstract: In this work, we introduce the Global Planar Convolution module as a building-block for fully-convolutional networks that aggregates global information and, therefore, enhances the context perception capabilities of segmentation networks in the context of brain tumor segmentation. We implement two baseline architectures (3D UNet and a residual version of 3D UNet, ResUNet) and present a novel architecture based on these two architectures, ContextNet, that includes the proposed Global Planar Convolution module. We show that the addition of such module eliminates the need of building networks with several representation levels, which tend to be over-parametrized and to showcase slow rates of convergence. Furthermore, we provide a visual demonstration of the behavior of GPC modules via visualization of intermediate representations. We finally participate in the 2018 edition of the BraTS challenge with our best performing models, that are based on ContextNet, and report the evaluation scores on the validation and the test sets of the challenge.

Abstract: Major advances have recently been made in merging language and vision representations. Most tasks considered so far have confined themselves to the processing of objects and lexicalised relations amongst objects (content words). We know, however, that humans (even pre-school children) can abstract over raw multimodal data to perform certain types of higher level reasoning, expressed in natural language by function words. A case in point is given by their ability to learn quantifiers, i.e. expressions like few, some and all. From formal semantics and cognitive linguistics, we know that quantifiers are relations over sets which, as a simplification, we can see as proportions. For instance, in most fish are red, most encodes the proportion of fish which are red fish. In this paper, we study how well current neural network strategies model such relations. We propose a task where, given an image and a query expressed by an object–property pair, the system must return a quantifier expressing which proportions of the queried object have the queried property. Our contributions are twofold. First, we show that the best performance on this task involves coupling state-of-the-art attention mechanisms with a network architecture mirroring the logical structure assigned to quantifiers by classic linguistic formalisation. Second, we introduce a new balanced dataset of image scenarios associated with quantification queries, which we hope will foster further research in this area.

Abstract: We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature activations without requiring part annotations and uses these activations to update and rectify the output likelihood distribution. In contrast to other approaches, the proposed mechanism is modular, architecture-independent and efficient both in terms of parameters and computation required. Experiments show that networks augmented with our approach systematically improve their classification accuracy and become more robust to clutter. As a result, Wide Residual Networks augmented with our proposal surpasses the state of the art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford dogs, and UEC Food-100.