Abstract: Textual information found in scene images provides high level semantic information about the image and its context and it can be leveraged for better scene understanding. In this paper we address the problem of scene text retrieval: given a text query, the system must return all images containing the queried text. The novelty of the proposed model consists in the usage of a single shot CNN architecture that predicts at the same time bounding boxes and a compact text representation of the words in them. In this way, the text based image retrieval task can be casted as a simple nearest neighbor search of the query text representation over the outputs of the CNN over the entire image
database. Our experiments demonstrate that the proposed architecture
outperforms previous state-of-the-art while it offers a significant increase
in processing speed.

Abstract: In large-scale query-by-example retrieval, embedding image signatures in a binary space offers two benefits: data compression and search efficiency. While most embedding algorithms binarize both query and database signatures, it has been noted that this is not strictly a requirement. Indeed, asymmetric schemes which binarize the database signatures but not the query still enjoy the same two benefits but may provide superior accuracy. In this work, we propose two general asymmetric distances which are applicable to a wide variety of embedding techniques including Locality Sensitive Hashing (LSH), Locality Sensitive Binary Codes (LSBC), Spectral Hashing (SH) and Semi-Supervised Hashing (SSH). We experiment on four public benchmarks containing up to 1M images and show that the proposed asymmetric distances consistently lead to large improvements over the symmetric Hamming distance for all binary embedding techniques. We also propose a novel simple binary embedding technique – PCA Embedding (PCAE) – which is shown to yield competitive results with respect to more complex algorithms such as SH and SSH.

Abstract: In this paper we propose a novel approach for writer adaptation in a handwritten word-spotting task. The method exploits the fact that the semi-continuous hidden Markov model separates the word model parameters into (i) a codebook of shapes and (ii) a set of word-specific parameters.
Our main contribution is to employ this property to derive writer-specific word models by statistically adapting an initial universal codebook to each document. This process is unsupervised and does not even require the appearance of the keyword(s) in the searched document. Experimental results show an increase in performance when this adaptation technique is applied. To the best of our knowledge, this is the first work dealing with adaptation for word-spotting. The preliminary version of this paper obtained an IBM Best Student Paper Award at the 19th International Conference on Pattern Recognition.

Abstract: Future video prediction is an ill-posed Computer Vision problem that recently received much attention. Its main challenges are the high variability in video content, the propagation of errors through time, and the non-specificity of the future frames: given a sequence of past frames there is a continuous distribution of possible futures. This work introduces bijective Gated Recurrent Units, a double mapping between the input and output of a GRU layer. This allows for recurrent auto-encoders with state sharing between encoder and decoder, stratifying the sequence representation and helping to prevent capacity problems. We show how with this topology only the encoder or decoder needs to be applied for input encoding and prediction, respectively. This reduces the computational cost and avoids re-encoding the predictions when generating a sequence of frames, mitigating the propagation of errors. Furthermore, it is possible to remove layers from an already trained model, giving an insight to the role performed by each layer and making the model more explainable. We evaluate our approach on three video datasets, outperforming state of the art prediction results on MMNIST and UCF101, and obtaining competitive results on KTH with 2 and 3 times less memory usage and computational cost than the best scored approach.

Abstract: Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiple-scale multiple-image generative model, which jointly estimates the foreground and background appearance distributions from several images, in a non-supervised manner. In contrast to other co-segmentation methods, our approach does not require the images to have similar foregrounds and different backgrounds to function properly. Region matching is applied to exploit inter-image information by establishing correspondences between the common objects that appear in the scene. Moreover, computing many-to-many associations of regions allow further applications, like recognition of object parts across images. We report results on iCoseg, a challenging dataset that presents extreme variability in camera viewpoint, illumination and object deformations and poses. We also show that our method is robust against large intra-class variability in the MSRC database.

Abstract: In this paper we propose a symbol spotting technique in graphical documents. Graphs are used to represent the documents and a (sub)graph matching technique is used to detect the symbols in them. We propose a graph serialization to reduce the usual computational complexity of graph matching. Serialization of graphs is performed by computing acyclic graph paths between each pair of connected nodes. Graph paths are one-dimensional structures of graphs which are less expensive in terms of computation. At the same time they enable robust localization even in the presence of noise and distortion. Indexing in large graph databases involves a computational burden as well. We propose a graph factorization approach to tackle this problem. Factorization is intended to create a unified indexed structure over the database of graphical documents. Once graph paths are extracted, the entire database of graphical documents is indexed in hash tables by locality sensitive hashing (LSH) of shape descriptors of the paths. The hashing data structure aims to execute an approximate k-NN search in a sub-linear time. We have performed detailed experiments with various datasets of line drawings and compared our method with the state-of-the-art works. The results demonstrate the effectiveness and efficiency of our technique.