Abstract: Many scene text understanding methods approach the endtoend recognition problem from a word-spotting perspective and take huge benet from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed.
In this paper we propose a method that generates contextualized lexicons
for scene images using only visual information. For this, we exploit
the correlation between visual and textual information in a dataset consisting
of images and textual content associated with them. Using the topic modeling framework to discover a set of latent topics in such a dataset allows us to re-rank a xed dictionary in a way that prioritizes the words that are more likely to appear in a given image. Moreover, we train a CNN that is able to reproduce those word rankings but using only the image raw pixels as input. We demonstrate that the quality of the automatically obtained custom lexicons is superior to a generic frequency-based baseline.

Abstract: In this paper, we investigate the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-SBIR scenario that represents a firm step forward in its practical application. The new setting uniquely recognizes two important yet often neglected challenges of practical ZS-SBIR, (i) the large domain gap between amateur sketch and photo, and (ii) the necessity for moving towards large-scale retrieval. We first contribute to the community a novel ZS-SBIR dataset, QuickDraw-Extended, that consists of 330,000 sketches and 204,000 photos spanning across 110 categories. Highly abstract amateur human sketches are purposefully sourced to maximize the domain gap, instead of ones included in existing datasets that can often be semi-photorealistic. We then formulate a ZS-SBIR framework to jointly model sketches and photos into a common embedding space. A novel strategy to mine the mutual information among domains is specifically engineered to alleviate the domain gap. External semantic knowledge is further embedded to aid semantic transfer. We show that, rather surprisingly, retrieval performance significantly outperforms that of state-of-the-art on existing datasets that can already be achieved using a reduced version of our model. We further demonstrate the superior performance of our full model by comparing with a number of alternatives on the newly proposed dataset. The new dataset, plus all training and testing code of our model, will be publicly released to facilitate future research.

Abstract: We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. Detailed analysis of the dataset in comparison with similar datasets for VQA and reading comprehension is presented. We report several baseline results by adopting existing VQA and reading comprehension models. Although the existing models perform reasonably well on certain types of questions, there is large performance gap compared to human performance (94.36% accuracy). The models need to improve specifically on questions where understanding structure of the document is crucial. The dataset, code and leaderboard are available at docvqa. org

Abstract: We call on the Document AI (DocAI) community to re-evaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research progress in understanding visually-rich documents (VRDs). We present a new dataset with novelties related to types of questions, answers, and document layouts based on multi-industry, multi-domain, and multi-page VRDs of various origins and dates. Moreover, we are pushing the boundaries of current methods by creating multi-task and multi-domain evaluation setups that more accurately simulate real-world situations where powerful generalization and adaptation under low-resource settings are desired. DUDE aims to set a new standard as a more practical, long-standing benchmark for the community, and we hope that it will lead to future extensions and contributions that address real-world challenges. Finally, our work illustrates the importance of finding more efficient ways to model language, images, and layout in DocAI.

Abstract: This paper deals with automatic detection of seal (stamp) from documents with cluttered background. Seal detection involves a difficult challenge due to its multi-oriented nature, arbitrary shape, overlapping of its part with signature, noise, etc. Here, a seal object is characterized by scale and rotation invariant spatial feature descriptors computed from recognition result of individual connected components (characters). Scale and rotation invariant features are used in a Support Vector Machine (SVM) classifier to recognize multi-scale and multi-oriented text characters. The concept of generalized Hough transform (GHT) is used to detect the seal and a voting scheme is designed for finding possible location of the seal in a document based on the spatial feature descriptor of neighboring component pairs. The peak of votes in GHT accumulator validates the hypothesis to locate the seal in a document. Experiment is performed in an archive of historical documents of handwritten/printed English text. Experimental results show that the method is robust in locating seal instances of arbitrary shape and orientation in documents, and also efficient in indexing a collection of documents for retrieval purposes.