Exploring "Artist Image" Using Content-Based Analysis Of Promotional Photos
نویسندگان
چکیده
We are interested in automatically calculating music similarity based on the visual appearance of artists. By collecting a large set of promotional photographs featuring artists and using a state-of-the-art image annotation system, we show that we can successfully annotate artists with a large set of (genre) tags. This suggests that we can learn some notion of artist similarity based on visual appearance. Such a similarity measure provides us with a novel query-by-image retrieval paradigm for music discovery.
منابع مشابه
How Iranian Women Express Themselves through Social Media Photos: A Case Study of Instagram
In this study, the issue of using Instagram social network by different groups of Iranian women and their interests and desires in publication of photos is investigated. The purpose of the study is to identify the common aspects and differences in women’s lives reflected in their self-expression efforts based on their social characteristics. Therefore, the women were classified into eight...
متن کاملGrouping Photos by Face
Image organizers such as imgSeek and GIFT allow query by image content (QBIC). QBIC help users find duplicate and similar photos. However, the similarity is measured based on color, texture and shape, not in terms of people. We implemented a “query by face” feature for organizing personal digital photos, using face detection and recognition techniques. We used the OpenCV library to extract face...
متن کاملUsing Context and Similarity for Face and Location Identification
This paper describes a new approach to the automatic detection of human faces and places depicted in photographs taken on cameraphones. Cameraphones offer a unique opportunity to pursue new approaches to media analysis and management: namely to combine the analysis of automatically gathered contextual metadata with media content analysis to fundamentally improve image content recognition and re...
متن کاملA Music Video Information Retrieval Approach to Artist Identification
We propose a cross-modal approach based on separate audio and image data-sets to identify the artist of a given music video. The identification process is based on an ensemble of two separate classifiers. Audio content classification is based on audio features derived from the Million Song Dataset (MSD). Face recognition is based on Local Binary Patterns (LBP) using a training-set of artist por...
متن کاملLearning Consumer Photo Categories for Semantic Retrieval
Research on image categorization has received more attention lately. In particular, the efforts to classify photos based on contents have been devoted to: indoor versus outdoor [Bradshaw, 2000], natural versus man-made [Bradshaw, 2000; Vailaya et al., 2001], and categories of natural scenes [Vailaya et al., 2001]. In general, the classifications were made based on low-level features such as col...
متن کامل