No abstract

No abstract

Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guiding content that should be employed to tackle a diversity of computer vision tasks such as image retrieval, finegrained classification, and visual question answering. In this paper, we address the problem of fine-grained classification and image retrieval by leveraging textual information along with visual cues to comprehend the existing intrinsic relation between the two modalities. The novelty of the proposed model consists of the usage of a PHOC descriptor to construct a bag of textual words along with a Fisher Vector Encoding that captures the morphology of text. This approach provides a stronger multimodal representation for this task and as our experiments demonstrate, it achieves state-of-the-art results on two different tasks, fine-grained classification and image retrieval. The code of this model will be publicly available at 1 .

Many sets of human facial photographs produced in Western cultures are available for scientific research. We report here on the development of a face database of Turkish undergraduate student targets. High-resolution standardized photographs were taken and supported by the following materials: (a) basic demographic and appearance-related information, (b) two types of landmark configurations (for Webmorph and geometric morphometrics (GM)), (c) facial width-to-height ratio (fWHR) measurement, (d) information on photography parameters, (e) perceptual norms provided by raters. We also provide various analyses and visualizations of facial variation based on rating norms using GM. Finally, we found that there is sexual dimorphism in fWHR in our sample but that this is accounted for by body mass index. We present the pattern of associations between rating norms, GM and fWHR measurements. The database and supporting materials are freely available for scientific research purposes.

No abstract