toggle visibility Search & Display Options
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
  Records Links
Author Lluis Gomez; Ali Furkan Biten; Ruben Tito; Andres Mafla; Marçal Rusiñol; Ernest Valveny; Dimosthenis Karatzas edit   pdf
url  openurl
  Title Multimodal grid features and cell pointers for scene text visual question answering Type Journal Article
  Year 2021 Publication Pattern Recognition Letters Abbreviated Journal PRL  
  Volume (down) 150 Issue Pages 242-249  
  Keywords  
  Abstract This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this is that it makes difficult for the model to reason jointly about both modalities. To fix this problem we propose a new model that is based on an single attention mechanism that attends to multi-modal features conditioned to the question. The output weights of this attention module over a grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text to the given question. Our experiments demonstrate competitive performance in two standard datasets with a model that is faster than previous methods at inference time. Furthermore, we also provide a novel analysis of the ST-VQA dataset based on a human performance study. Supplementary material, code, and data is made available through this link.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.084; 600.121 Approved no  
  Call Number Admin @ si @ GBT2021 Serial 3620  
Permanent link to this record
 
 
Author Arka Ujjal Dey; Suman Ghosh; Ernest Valveny; Gaurav Harit edit   pdf
url  doi
openurl 
  Title Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding Type Journal Article
  Year 2021 Publication Pattern Recognition Letters Abbreviated Journal PRL  
  Volume (down) 149 Issue Pages 164-171  
  Keywords  
  Abstract Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we propose to jointly use scene text and visual channels for robust semantic interpretation of images. We do not only extract and encode visual and scene text cues, but also model their interplay to generate a contextual joint embedding with richer semantics. The contextual embedding thus generated is applied to retrieval and classification tasks on multimedia images, with scene text content, to demonstrate its effectiveness. In the retrieval framework, we augment our learned text-visual semantic representation with scene text cues, to mitigate vocabulary misses that may have occurred during the semantic embedding. To deal with irrelevant or erroneous recognition of scene text, we also apply query-based attention to our text channel. We show how the multi-channel approach, involving visual semantics and scene text, improves upon state of the art.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ DGV2021 Serial 3364  
Permanent link to this record
 
 
Author Ruben Tito; Dimosthenis Karatzas; Ernest Valveny edit   pdf
doi  openurl
  Title Hierarchical multimodal transformers for Multi-Page DocVQA Type Journal Article
  Year 2023 Publication Pattern Recognition Abbreviated Journal PR  
  Volume (down) 144 Issue Pages 109834  
  Keywords  
  Abstract Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISSN 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.155; 600.121 Approved no  
  Call Number Admin @ si @ TKV2023 Serial 3825  
Permanent link to this record
 
 
Author Ruben Tito; Dimosthenis Karatzas; Ernest Valveny edit   pdf
url  openurl
  Title Hierarchical multimodal transformers for Multipage DocVQA Type Journal Article
  Year 2023 Publication Pattern Recognition Abbreviated Journal PR  
  Volume (down) 144 Issue 109834 Pages  
  Keywords  
  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.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number Admin @ si @ TKV2023 Serial 3836  
Permanent link to this record
 
 
Author Souhail Bakkali; Zuheng Ming; Mickael Coustaty; Marçal Rusiñol; Oriol Ramos Terrades edit   pdf
doi  openurl
  Title VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification Type Journal Article
  Year 2023 Publication Pattern Recognition Abbreviated Journal PR  
  Volume (down) 139 Issue Pages 109419  
  Keywords  
  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.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISSN 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.140; 600.121 Approved no  
  Call Number Admin @ si @ BMC2023 Serial 3826  
Permanent link to this record
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: