Brian McFee

The million song dataset challenge

We introduce the Million Song Dataset Challenge: a large-scale, personalized music recommendation challenge, where the goal is to predict the songs that a user will listen to, given both the users listening history and full information (including meta-data and content analysis) for all songs. We explain the taste profile data, our goals and design choices in creating the challenge, and present baseline results using simple, off-the-shelf recommendation algorithms.

Multi-class object localization by combining local contextual interactions

Recent work in object localization has shown that the use of contextual cues can greatly improve accuracy over models that use appearance features alone. Although many of these models have successfully explored different types of contextual sources, they only consider one type of contextual interaction (e.g., pixel, region or object level interactions), leaving open questions about the true potential contribution of context. Furthermore, contributions across object classes and over appearance features still remain unknown. In this work, we introduce a novel model for multi-class object localization that incorporates different levels of contextual interactions. We study contextual interactions at pixel, region and object level by using three different sources of context: semantic, boundary support and contextual neighborhoods. Our framework learns a single similarity metric from multiple kernels, combining pixel and region interactions with appearance features, and then uses a conditional random field to incorporate object level interactions. We perform experiments on two challenging image databases: MSRC and PASCAL VOC 2007. Experimental results show that our model outperforms current state-of-the-art contextual frameworks and reveals individual contributions for each contextual interaction level, as well as the importance of each type of feature in object localization.

Learning Content Similarity for Music Recommendation

Many tasks in music information retrieval, such as recommendation, and playlist generation for online radio, fall naturally into the query-by-example setting, wherein a user queries the system by providing a song, and the system responds with a list of relevant or similar song recommendations. Such applications ultimately depend on the notion of similarity between items to produce high-quality results. Current state-of-the-art systems employ collaborative filter methods to represent musical items, effectively comparing items in terms of their constituent users. While collaborative filter techniques perform well when historical data is available for each item, their reliance on historical data impedes performance on novel or unpopular items. To combat this problem, practitioners rely on content-based similarity, which naturally extends to novel items, but is typically outperformed by collaborative filter methods. In this paper, we propose a method for optimizing content-based similarity by learning from a sample of collaborative filter data. The optimized content-based similarity metric can then be applied to answer queries on novel and unpopular items, while still maintaining high recommendation accuracy. The proposed system yields accurate and efficient representations of audio content, and experimental results show significant improvements in accuracy over competing content-based recommendation techniques.

Partial order embedding with multiple kernels

We consider the problem of embedding arbitrary objects (e.g., images, audio, documents) into Euclidean space subject to a partial order over pair-wise distances. Partial order constraints arise naturally when modeling human perception of similarity. Our partial order framework enables the use of graph-theoretic tools to more efficiently produce the embedding, and exploit global structure within the constraint set. We present an embedding algorithm based on semidefinite programming, which can be parameterized by multiple kernels to yield a unified space from heterogeneous features.

Contextual Object Localization With Multiple Kernel Nearest Neighbor

Recently, many object localization models have shown that incorporating contextual cues can greatly improve accuracy over using appearance features alone. Therefore, many of these models have explored different types of contextual sources, but only considering one level of contextual interaction at the time. Thus, what context could truly contribute to object localization, through integrating cues from all levels, simultaneously, remains an open question. Moreover, the relative importance of the different contextual levels and appearance features across different object classes remains to be explored. Here we introduce a novel framework for multiple class object localization that incorporates different levels of contextual interactions. We study contextual interactions at the pixel, region and object level based upon three different sources of context: semantic, boundary support, and contextual neighborhoods. Our framework learns a single similarity metric from multiple kernels, combining pixel and region interactions with appearance features, and then applies a conditional random field to incorporate object level interactions. To effectively integrate different types of feature descriptions, we extend the large margin nearest neighbor to a novel algorithm that supports multiple kernels. We perform experiments on three challenging image databases: Graz-02, MSRC and PASCAL VOC 2007. Experimental results show that our model outperforms current state-of-the-art contextual frameworks and reveals individual contributions for each contextual interaction level as well as appearance features, indicating their relative importance for object localization.

Learning to segment songs with ordinal linear discriminant analysis

This paper describes a supervised learning algorithm which optimizes a feature representation for temporally constrained clustering. The proposed method is applied to music segmentation, in which a song is partitioned into functional or locally homogeneous segments (e.g., verse or chorus). To facilitate abstraction over multiple training examples, we develop a latent structural repetition feature, which summarizes the repetitive structure of a song of any length in a fixed-dimensional representation. Experimental results demonstrate that the proposed method efficiently integrates heterogeneous features, and improves segmentation accuracy.

From region similarity to category discovery

The goal of object category discovery is to automatically identify groups of image regions which belong to some new, previously unseen category. This task is typically performed in a purely unsupervised setting, and as a result, performance depends critically upon accurate assessments of similarity between unlabeled image regions. To improve the accuracy of category discovery, we develop a novel multiple kernel learning algorithm based on structural SVM, which optimizes a similarity space for nearest-neighbor prediction. The optimized space is then used to cluster unlabeled data and identify new categories. Experimental results on the MSRC and PASCAL VOC2007 data sets indicate that using an optimized similarity metric can improve clustering for category discovery. Furthermore, we demonstrate that including both labeled and unlabeled training data when optimizing the similarity metric can improve the overall quality of the system.

Iterative Category Discovery via Multiple Kernel Metric Learning

The goal of an object category discovery system is to annotate a pool of unlabeled image data, where the set of labels is initially unknown to the system, and must therefore be discovered over time by querying a human annotator. The annotated data is then used to train object detectors in a standard supervised learning setting, possibly in conjunction with category discovery itself. Category discovery systems can be evaluated in terms of both accuracy of the resulting object detectors, and the efficiency with which they discover categories and annotate the training data. To improve the accuracy and efficiency of category discovery, we propose an iterative framework which alternates between optimizing nearest neighbor classification for known categories with multiple kernel metric learning, and detecting clusters of unlabeled image regions likely to belong to a novel, unknown categories. Experimental results on the MSRC and PASCAL VOC2007 data sets show that the proposed method improves clustering for category discovery, and efficiently annotates image regions belonging to the discovered classes.

Better beat tracking through robust onset aggregation

Onset detection forms the critical first stage of most beat tracking algorithms. While common spectral-difference onset detectors can work well in genres with clear rhythmic structure, they can be sensitive to loud, asynchronous events (e.g., off-beat notes in a jazz solo), which limits their general efficacy. In this paper, we investigate methods to improve the robustness of onset detection for beat tracking. Experimental results indicate that simple modifications to onset detection can produce large improvements in beat tracking accuracy.

WOMRAD: 2nd workshop on music recommendation and discovery

The world of music is changing rapidly. We are now just a few clicks away from being able to listen to nearly any song that has ever been recorded. This easy access to a nearly endless supply of music is changing how we explore, discover, share and experience music