Label embedding for text recognition

By José A. Rodríguez-Serrano, Florent Perronnin. 2013

90 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Deep Structured Output Learning for Unconstrained Text Recognition (2014, methodology): “In contrast to these approaches based on character classiﬁcation, the work by Almaz´an et al. (2014); Gordo (2014); Goel et al. (2013); Rodriguez-Serrano et al. (2013); Novikova et al. (2012); Mishra et al. (2012) instead uses the notion of holistic word recognition.”
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014, methodology): “In contrast to these approaches based on character classification, the work by [7, 17, 21, 24] instead uses the notion of holistic word recognition.”
Joint Embedding of Words and Labels for Text Classification (2018, background): “, 2014), and text recognition in images (Rodriguez-Serrano et al., 2013).”
Reading Text in the Wild with Convolutional Neural Networks (2014, methodology): “To compute recall and precision in a detection scenario, a bounding box is said to be a true-positive detection if it has overlap with a groundtruth bounding box above a defined threshold.”
Im2Text and Text2Im: Associating Images and Texts for Cross-Modal Retrieval (2014, methodology): “Our work also closely relates with [27], in which images of text and text strings are first embedded into a vector space, and then a compatibility function is learned using Structural SVM that allows to perform both image retrieval as well as recognition.”
Supervised mid-level features for word image representation (2014, methodology): “HOG [8], or SIFT [17] features aggregated with bags of words [7] or Fisher vector [24] encodings) and apply different frameworks and machine learning techniques (such as using attribute representations, metric learning, or exemplar SVMs) on top of these global representations to learn models to perf”
Scene text detection and recognition: recent advances and future trends (2015, background): “[64] 2013 • can recognize words in complex natural images • retrieval based word recognition • efficient • require a lexicon for each image”
Scene Text Detection and Recognition: The Deep Learning Era (2018, background): “Rodriguez-Serrano et al. (2013), Rodriguez-Serrano et al. (2015), Gordo (2015), Almazán et al. (2014) utilize label embedding to directly performmatching between strings and images.”