Filters








47,317 Hits in 4.5 sec

A Semantic-Based Approach For Artist Similarity

Sergio Oramas, Mohamed Sordo, Luis Espinosa Anke, Xavier Serra
2015 Zenodo  
"A Semantic-based Approach for Artist Similarity", 16th International Society for Music Information Retrieval Conference, 2015. Figure 1 . 1 Workflow of the proposed method.  ...  Apart from the defined approaches, a pure text-based approach for document similarity is added to act as a reference for the obtained results.  ... 
doi:10.5281/zenodo.1415975 fatcat:xnytigsx4nfdtmm26o42srbu2a

Using Artist Similarity To Propagate Semantic Information

Joon Hee Kim, Brian Tomasik, Douglas Turnbull
2009 Zenodo  
That is, the approach that results in the best transfer of semantic information between artists may be considered a good approach for accessing artist similarity.  ...  In some sense, tag propagation represents a sixth approach because it is based on the notions of artist similarity.  ... 
doi:10.5281/zenodo.1416509 fatcat:3ugls7gkercrfgtibhdzioswm4

How Much Metadata Do We Need In Music Recommendation? A Subjective Evaluation Using Preference Sets

Dmitry Bogdanov, Perfecto Herrera
2011 Zenodo  
Artist Similarity based on Last.fm Tags (M-TAGS) Alternatively, we consider a metadata-based distance working on the artist level.  ...  The conducted evaluation corroborates a similar study presented in [3] , in which similar patterns of no statistically significant difference between a content-based semantic distance and a simple genre-based  ... 
doi:10.5281/zenodo.1415103 fatcat:i3w5zpd6dbcsbenxjriq4q3f4i

Knowledge Extraction And Representation Learning For Music Recommendation And Classification

Sergio Oramas, Xavier Serra
2017 Zenodo  
Then, we show how modeling semantic information may impact musicological studies and helps to outperform purely text-based approaches in music similarity, classification, and recommendation.  ...  We focus on the semantic enrichment of descriptions associated to musical items (e.g., artists biographies, album reviews, metadata), and the exploitation of multimodal data (e.g., text, audio, images)  ...  Apart from the defined approaches, a pure text-based approach for document similarity is added to act as a baseline for the obtained results.  ... 
doi:10.5281/zenodo.1048497 fatcat:kdh5jhvocbh3riwln6n2f756su

Knowledge Extraction And Representation Learning For Music Recommendation And Classification

Sergio Oramas, Xavier Serra
2017 Zenodo  
Then, we show how modeling semantic information may impact musicological studies and helps to outperform purely text-based approaches in music similarity, classification, and recommendation.  ...  We focus on the semantic enrichment of descriptions associated to musical items (e.g., artists biographies, album reviews, metadata), and the exploitation of multimodal data (e.g., text, audio, images)  ...  Apart from the defined approaches, a pure text-based approach for document similarity is added to act as a baseline for the obtained results.  ... 
doi:10.5281/zenodo.1100973 fatcat:yfpmc6qxbbakjp6qzvywyoaoci

A Deep Multimodal Approach for Cold-start Music Recommendation

Sergio Oramas, Oriol Nieto, Mohamed Sordo, Xavier Serra
2017 Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems - DLRS 2017  
., artist metadata and audio track), and merging feature embeddings in a multimodal approach improve the accuracy of the recommendations.  ...  Music streaming services often ingest all available music, but this poses a challenge: how to recommend new artists for which prior knowledge is scarce?  ...  We compare four di erent approaches using the biography texts as input. (1) a pure text-based approach using a VSM and a feedforward network TEXT. (2) similar to (1) but with a semantically enriched version  ... 
doi:10.1145/3125486.3125492 dblp:conf/recsys/OramasNSS17 fatcat:srv74edtavccnp46cqxgjptuxm

MusicWeb: Music Discovery with Open Linked Semantic Metadata [chapter]

Mariano Mora-Mcginity, Alo Allik, György Fazekas, Mark Sandler
2016 Communications in Computer and Information Science  
This paper presents MusicWeb, a novel platform for music discovery by linking music artists within a web-based application.  ...  These connections are further enhanced by thematic analysis of journal articles, blog posts and content-based similarity measures focussing on high level musical categories.  ...  Artist Similarity There are many ways in which artists can be considered related: similarity may be based on a particular style or genre, but it may also mean that artists are followed by people from similar  ... 
doi:10.1007/978-3-319-49157-8_25 fatcat:lzubyrdkjbctfh5m52fnvvdesy

Quantify music artist similarity based on style and mood

Bo Shao, Tao Li, Mitsunori Ogihara
2008 Proceeding of the 10th ACM workshop on Web information and data management - WIDM '08  
In this paper, we propose a new framework for quantifying artist similarity.  ...  Music artist similarity has been an active research topic in music information retrieval for a long time since it is especially useful for music recommendation and organization.  ...  quantify the artist similarities based on the semantic similarities of the style and mood terms.  ... 
doi:10.1145/1458502.1458522 dblp:conf/widm/ShaoLO08 fatcat:jacvfvtppjabhd2snpqu2sa65y

Extensive Classification of Visual Art Paintings for Enhancing Education System using Hybrid SVM-ANN with Sparse Metric Learning based on Kernel Regression

Fei Xu, Tong Wu, Shali Huang, Kuntong Han, Wenwen Lin, Shizhong Wu, Sivaparthipan CB, Samuel R Dinesh Jackson
2021 International Journal of Interactive Multimedia and Artificial Intelligence  
A classification model is developed using hybrid SVM-ANN for semantic-level understanding to predict painting's genre, artist, and style.  ...  For modeling the similarities between the artworks or paintings, it is essential to extract useful features of visual paintings and propose the best approach for learning these similarity metrics.  ...  This provides a computer capable of making semantic decisions relevant to aesthetics, such as an identification of a painting's theme, genre, and artist, and delivering optimized similarity measures based  ... 
doi:10.9781/ijimai.2021.10.001 fatcat:u67rkxp7cvaujg6g42kn4kogqu

A generic semantic-based framework for cross-domain recommendation

Ignacio Fernández-Tobías, Iván Cantador, Marius Kaminskas, Francesco Ricci
2011 Proceedings of the 2nd International Workshop on Information Heterogeneity and Fusion in Recommender Systems - HetRec '11  
In this paper, we present an ongoing research work on the design and development of a generic knowledge-based description framework built upon semantic networks.  ...  This enables to link concepts in the two domains by means of a weighted directed acyclic graph, and to perform weight spreading on such graph to identify items in the target domain (music artists) that  ...  of a generic semantic-based framework for crossdomain recommendation.  ... 
doi:10.1145/2039320.2039324 fatcat:isrpwvl4ozcffb6l6m4er4lk6u

Music Recommendation: A multi-faceted approach

Oscar Celma, Xavier Serra
2006 Zenodo  
As a test–bed example, two prototypes have been developed a music search engine and music discovery based on music similarity, and a hybrid music recommender.  ...  Finally, the descriptions are enclosed into an ontological framework for semantic integration and retrieval of audiovisual metadata.  ...  Artist co-occurrences on web pages was introduced in [SKW05a]. The approach was based on creating special Google queries for every pair of artists.  ... 
doi:10.5281/zenodo.3743108 fatcat:wcfdl34jnzeqtmzjzamjjvdt44

Toward automated discovery of artistic influence

Babak Saleh, Kanako Abe, Ravneet Singh Arora, Ahmed Elgammal
2014 Multimedia tools and applications  
As a result, we provide a visualization of artists (Map of Artists) based on the similarity between their works * The final publication is available at Springer R .  ...  For this purpose, we investigated several painting-similarity and artist-similarity measures.  ...  We also present a tool for visualizing artist similarity through what we call a map of artists.  ... 
doi:10.1007/s11042-014-2193-x fatcat:dejnkywrxjhwleeoz5txuk3yri

From Knowledge Map to Mind Map: Artificial Imagination [article]

Ruixue Liu, Baoyang Chen, Xiaoyu Guo, Yan Dai, Meng Chen, Zhijie Qiu, Xiaodong He
2019 arXiv   pre-print
However, lacking of imagination is still a main problem for AI painting. In this paper, we propose a novel approach to inject rich imagination into a special painting art Mind Map creation.  ...  Imagination is one of the most important factors which makes an artistic painting unique and impressive.  ...  We want to thank both institutions for their support, and additionally CAFA EAST AI Group.  ... 
arXiv:1903.01080v2 fatcat:4zjbvzavlvekjp3qudsal37vpq

Toward Automated Discovery of Artistic Influence [article]

Babak Saleh, Kanako Abe, Ravneet Singh Arora, Ahmed Elgammal
2014 arXiv   pre-print
As a result, we provide a visualization of artists (Map of Artists) based on the similarity between their works  ...  For this purpose, we investigated several painting-similarity and artist-similarity measures.  ...  We also present a tool for visualizing artist similarity through what we call a map of artists.  ... 
arXiv:1408.3218v1 fatcat:t4qs7vbugbac5gciymy3ouvboq

Representation Learning of Music Using Artist Labels [article]

Jiyoung Park, Jongpil Lee, Jangyeon Park, Jung-Woo Ha, Juhan Nam
2018 arXiv   pre-print
One is a plain DCNN trained with the whole artist labels simultaneously, and the other is a Siamese DCNN trained with a subset of the artist labels based on the artist identity.  ...  In this paper, we present a supervised feature learning approach using artist labels annotated in every single track as objective meta data.  ...  FEATURE EVALUATION We apply the learned audio features to genre classification as a target task in two different approaches: feature similarity-based retrieval and transfer learning.  ... 
arXiv:1710.06648v2 fatcat:hgt6s7w4pjarpjz3or2uyota7y
« Previous Showing results 1 — 15 out of 47,317 results