|
|
Souhail Bakkali, Zuheng Ming, Mickael Coustaty, Marçal Rusiñol, & Oriol Ramos Terrades. (2023). VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification. PR - Pattern Recognition, 139, 109419.
Abstract: Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream approach. In this paper, we approach the document classification problem by learning cross-modal representations through language and vision cues, considering intra- and inter-modality relationships. Instead of merging features from different modalities into a common representation space, the proposed method exploits high-level interactions and learns relevant semantic information from effective attention flows within and across modalities. The proposed learning objective is devised between intra- and inter-modality alignment tasks, where the similarity distribution per task is computed by contracting positive sample pairs while simultaneously contrasting negative ones in the common feature representation space}. Extensive experiments on public document classification datasets demonstrate the effectiveness and the generalization capacity of our model on both low-scale and large-scale datasets.
|
|
|
|
Ruben Tito, Dimosthenis Karatzas, & Ernest Valveny. (2023). Hierarchical multimodal transformers for Multipage DocVQA. PR - Pattern Recognition, 144(109834).
Abstract: Existing work on DocVQA only considers single-page documents. However, in real applications documents are mostly composed of multiple pages that should be processed altogether. In this work, we propose a new multimodal hierarchical method Hi-VT5, that overcomes the limitations of current methods to process long multipage documents. In contrast to previous hierarchical methods that focus on different semantic granularity (He et al., 2021) or different subtasks (Zhou et al., 2022) used in image classification. Our method is a hierarchical transformer architecture where the encoder learns to summarize the most relevant information of every page and then, the decoder uses this summarized representation to generate the final answer, following a bottom-up approach. Moreover, due to the lack of multipage DocVQA datasets, we also introduce MP-DocVQA, an extension of SP-DocVQA where questions are posed over multipage documents instead of single pages. Through extensive experimentation, we demonstrate that Hi-VT5 is able, in a single stage, to answer the questions and provide the page that contains the answer, which can be used as a kind of explainability measure.
|
|
|
|
Gemma Sanchez, Josep Llados, & K. Tombre. (2002). A mean string algorithm to compute the average among a set of 2D shapes. PRL - Pattern Recognition Letters, 23(1-3), 203–214.
|
|
|
|
Oriol Ramos Terrades, & Ernest Valveny. (2006). A new use of the ridgelets transform for describing linear singularities in images. PRL - Pattern Recognition Letters, 27(6), 587–596.
|
|
|
|
Miquel Ferrer, Ernest Valveny, & F. Serratosa. (2009). Median graph: A new exact algorithm using a distance based on the maximum common subgraph. PRL - Pattern Recognition Letters, 30(5), 579–588.
Abstract: Median graphs have been presented as a useful tool for capturing the essential information of a set of graphs. Nevertheless, computation of optimal solutions is a very hard problem. In this work we present a new and more efficient optimal algorithm for the median graph computation. With the use of a particular cost function that permits the definition of the graph edit distance in terms of the maximum common subgraph, and a prediction function in the backtracking algorithm, we reduce the size of the search space, avoiding the evaluation of a great amount of states and still obtaining the exact median. We present a set of experiments comparing our new algorithm against the previous existing exact algorithm using synthetic data. In addition, we present the first application of the exact median graph computation to real data and we compare the results against an approximate algorithm based on genetic search. These experimental results show that our algorithm outperforms the previous existing exact algorithm and in addition show the potential applicability of the exact solutions to real problems.
|
|
