16 Result(s)
within
Conference Paper
Mark Sandler
-
Chapter and Conference Paper
SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Deep learning based object detectors are commonly deployed on mobile devices to solve a variety of tasks. For maximum accuracy, each detector is usually trained to solve one single specific task, and comes wit...
-
Chapter and Conference Paper
Information-Bottleneck Approach to Salient Region Discovery
We propose a new method for learning image attention masks in a semi-supervised setting based on the Information Bottleneck principle. Provided with a set of labeled images, the mask generation model is minimi...
-
Chapter and Conference Paper
SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
As mobile hardware technology advances, on-device computation is becoming more and more affordable.
-
Chapter and Conference Paper
Does k Matter? k-NN Hubness Analysis for Kernel Additive Modelling Vocal Separation
Kernel Additive Modelling (KAM) is a framework for source separation aiming to explicitly model inherent properties of sound sources to help with their identification and separation. KAM separates a given sour...
-
Chapter and Conference Paper
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget. While many existing algorithms simplify networks based o...
-
Chapter and Conference Paper
Ontological Representation of Audio Features
Feature extraction algorithms in Music Informatics aim at deriving statistical and semantic information directly from audio signals. These may be ranging from energies in several frequency bands to musical inf...
-
Chapter and Conference Paper
MusicWeb: Music Discovery with Open Linked Semantic Metadata
This paper presents MusicWeb, a novel platform for music discovery by linking music artists within a web-based application. MusicWeb provides a browsing experience using connections that are either extra-music...
-
Chapter and Conference Paper
Facilitating Music Information Research with Shared Open Vocabularies
There is currently no agreement on common shared representations of audio features in the field of music information retrieval. The Audio Feature Ontology has been developed as part of a harmonised library of ...
-
Chapter and Conference Paper
A Shared Vocabulary for Audio Features
The aim of the Shared Open Vocabulary for Audio Research and Retrieval project is to foster greater agreement on the representation of content-based audio features within music research communities. The Audio ...
-
Chapter and Conference Paper
Music Emotion Recognition: From Content- to Context-Based Models
The striking ability of music to elicit emotions assures its prominent status in human culture and every day life. Music is often enjoyed and sought for its ability to induce or convey emotions, which may mani...
-
Chapter and Conference Paper
Evaluation of the Music Ontology Framework
The Music Ontology provides a framework for publishing structured music-related data on the Web, ranging from editorial data to temporal annotations of audio signals. It has been used extensively, for example ...
-
Chapter and Conference Paper
Interactive Music Applications and Standards
Music is now consumed in interactive applications that allow for the user to directly influence the musical performance. These applications are distributed as games for gaming consoles and applications for mob...
-
Chapter and Conference Paper
Towards the Automatic Generation of a Semantic Web Ontology for Musical Instruments
In this study we present a novel hybrid system by develo** a formal method of automatic ontology generation for web-based audio signal processing applications. An ontology is seen as a knowledge management s...
-
Chapter and Conference Paper
Speech/Music Discrimination in Audio Podcast Using Structural Segmentation and Timbre Recognition
We propose two speech/music discrimination methods using timbre models and measure their performances on a 3 hour long database of radio podcasts from the BBC. In the first method, the machine estimated classi...
-
Chapter and Conference Paper
Musically Meaningful or Just Noise? An Analysis of On-line Artist Networks
A sample of the Myspace social network is examined. Using methods from complex network theory, we show empirically that the structure of the Myspace artist network is related to the concept of musical genre. A...
-
Chapter and Conference Paper
A Scalable Framework for Multimedia Knowledge Management
In this paper, we describe a knowledge management framework that addresses the needs of multimedia analysis projects and provides a basis for information retrieval systems. The framework uses Semantic Web technol...
