Search For:

Displaying 1-25 out of 25 total
Micro Stories and Mega Stories
Found in: IEEE MultiMedia
By Ramesh Jain,Malcolm Slaney
Issue Date:January 2013
pp. 86-90
Given the status of technology today, it is easy to capture experiential data, such as photos, for events and even organize them. That means that one can now easily store experiential data and use it to tell stories. The authors explore the new Internet te...
 
Precision-Recall Is Wrong for Multimedia
Found in: IEEE Multimedia
By Malcolm Slaney
Issue Date:July 2011
pp. 4-7
Editor's Note: I want to open a dialog about issues that are important to our field, and could change the direction of our work. I don't intend to write most of the columns, and I am soliciting ideas. Please send me your suggestions, either for issues you ...
 
Don't Click Here
Found in: IEEE Multimedia
By David A. Shamma,Malcolm Slaney
Issue Date:July 2012
pp. 4-6
One of the most important aspects of multimedia research is mining data about user behavior. In a world with one or fewer clicks per piece of content, one needs a lot of users to get a meaningful signal. A monetization ecosystem now directs multimedia rese...
 
Tell Me a Story
Found in: IEEE Multimedia
By Aisling Kelliher,Malcolm Slaney
Issue Date:January 2012
pp. 4, 6
Multimedia offers researchers developing tools, methods, and frameworks an intuitive and cross-cultural application space with a diverse set of motivated end users. As we progress from shoeboxes of Hi8 tapes to terabyte drives filled with rarely viewed med...
 
Web-Scale Multimedia Analysis: Does Content Matter?
Found in: IEEE Multimedia
By Malcolm Slaney
Issue Date:April 2011
pp. 12-15
<p>Editor's Note</p><p>This is my first column as editor of the Visions and Views column. I hope that with this column I can bring you ideas that are new and interesting. I want to open a dialog about issues that are important to our fiel...
 
Reconciliation of human and machine speech recognition performance
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Misha Pavel, Malcolm Slaney, Hynek Hermansky
Issue Date:April 2009
pp. 1669-1672
This paper focuses on resolving a number of issues that appear when the performance of human speech recognition is compared to that of automatic speech recognition. In particular human experimental data suggest that the resulting error is a product of the ...
 
Being Literate with Large Document Collections: Observational Studies and Cost Structure Tradeoffs
Found in: Hawaii International Conference on System Sciences
By Daniel M. Russell, Malcolm Slaney, Yan Qu, Mave Houston
Issue Date:January 2006
pp. 55
How do people work with large document collections? We studied the effects of different kinds of analysis tools on the behavior of people doing rapid large-volume data assessment, analysis and organization. We analyzed the micro-structure details of using ...
   
Measuring Information Understanding in Large Document Collections
Found in: Hawaii International Conference on System Sciences
By Malcolm Slaney, Daniel M. Russell
Issue Date:January 2005
pp. 105
We present a method for testing subject's performance in a realistic (end-to-end) information understanding task-rapid understanding of large document collections-and discuss lessons learned from our attempts to measure representative information-understan...
   
Temporal Events in All Dimensions and Scales
Found in: Detection and Recognition of Events in Video, IEEE Workshop on
By Malcolm Slaney, Dulce Ponceleon, James Kaufman
Issue Date:July 2001
pp. 83
This paper describes a new representation for the audio and visual information in a video signal. We use reduce the dimensionality of the signals with singular-value decompositions (SVD) or mel-frequency cepstral coefficients (MFCC). We apply these transfo...
 
Academia Meets Industry at the Multimedia Grand Challenge
Found in: IEEE Multimedia
By Cees G.M. Snoek, Malcolm Slaney
Issue Date:January 2011
pp. 4-7
This column is about last year's ACM Multimedia Grand Challenge in Florence, Italy, an event that endeavors to connect (academic) researchers more effectively with the realities of the business world. The authors describe the 10 challenges and present the ...
 
Introduction to the special section on the 20th anniversary of the ACM international conference on multimedia
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Klara Nahrstedt, Malcolm Slaney, Rainer Lienhart
Issue Date:October 2013
pp. 1-3
For over two decades, video streaming over the Internet has received a substantial amount of attention from both academia and industry. Starting from the design of transport protocols for streaming video, research interests have later shifted to the peer-t...
     
Identifying authoritative sources of multimedia content: mining specificity and expertise from large-scale multimedia databases
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Lyndon Kennedy, Malcolm Slaney
Issue Date:November 2011
pp. 1205-1208
We present a framework for identifying authoritative sources (such as web sites or individual users) that are likely to produce high-quality or interesting images. We construct a directed graph across sources based on the propensity of one source to "cite"...
     
Using gaze patterns to study and predict reading struggles due to distraction
Found in: Proceedings of the 2011 annual conference extended abstracts on Human factors in computing systems (CHI EA '11)
By Justin Rao, Malcolm Slaney, Vidhya Navalpakkam
Issue Date:May 2011
pp. 1705-1710
We analyze gaze patterns to study how users in online reading environments cope with visual distraction, and we report gaze markers that identify reading difficulties due to distraction. The amount of visual distraction is varied from none, medium to high ...
     
Processing web-scale multimedia data
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Edward Y. Chang, Malcolm Slaney
Issue Date:October 2010
pp. 1771-1772
The Internet brings us access to multimedia databases with billions of data instances. The massive amount of data available to researchers and application developers brings both opportunities and challenges. In particular, massive amount of data makes data...
     
Image classification using the web graph
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Dhruv Kumar Mahajan, Malcolm Slaney
Issue Date:October 2010
pp. 991-994
Image classification is a well-studied and hard problem in computer vision. We extend a proven solution for classifying web spam to handle images. We exploit the link structure of the web graph: a web page related to a given category is normally linked to ...
     
Multimodal retrieval and ranking: more than waveforms
Found in: Proceedings of the international conference on Multimedia information retrieval (MIR '10)
By Malcolm Slaney
Issue Date:March 2010
pp. 241-242
Those of us that are engineers like to think in terms of pure content-analysis problems: Analyze the waveform to find the most likely chord; Look at rating data to determine what songs our friends will like; Or recognize the genre from a bag-of-features mo...
     
Reliable tags using image similarity: mining specificity and expertise from large-scale multimedia databases
Found in: Proceedings of the 1st workshop on Web-scale multimedia corpus (WSMC '09)
By Kilian Weinberger, Lyndon Kennedy, Malcolm Slaney
Issue Date:October 2009
pp. 17-24
This paper describes an approach for finding image descriptors or tags that are highly reliable and specific. Reliable, in this work, means that the tags are related to the image's visual content, which we verify by finding two or more real people who agre...
     
Unsupervised image ranking
Found in: Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining (LS-MMRM '09)
By Eva Horster, Kilian Weinberger, Malcolm Slaney, Marc'Aurelio Ranzato
Issue Date:October 2009
pp. 81-88
In the paper, we propose and test an unsupervised approach for image ranking. Prior solutions are based on image content and the similarity graph connecting images. We generalize this idea by directly estimating the likelihood of each photo in a feature sp...
     
Resolving tag ambiguity
Found in: Proceeding of the 16th ACM international conference on Multimedia (MM '08)
By Kilian Quirin Weinberger, Malcolm Slaney, Roelof Van Zwol
Issue Date:October 2008
pp. 40-42
Tagging is an important way for users to succinctly describe the content they upload to the Internet. However, most tag-suggestion systems recommend words that are highly correlated with the existing tag set, and thus add little information to a user's con...
     
Continuous visual vocabulary modelsfor pLSA-based scene recognition
Found in: Proceedings of the 2008 international conference on Content-based image and video retrieval (CIVR '08)
By Eva Horster, Malcolm Slaney, Rainer Lienhart
Issue Date:July 2008
pp. 569-570
Topic models such as probabilistic Latent Semantic Analysis (pLSA) and Latent Dirichlet Allocation (LDA) have been shown to perform well in various image content analysis tasks. However, due to the origin of these models from the text domain, almost all pr...
     
Image retrieval on large-scale image databases
Found in: Proceedings of the 6th ACM international conference on Image and video retrieval (CIVR '07)
By Eva Horster, Malcolm Slaney, Rainer Lienhart
Issue Date:July 2007
pp. 17-24
Online image repositories such as Flickr contain hundreds of millions of images and are growing quickly. Along with that the needs for supporting indexing, searching and browsing is becoming more and more pressing. In this work we will employ the image con...
     
Predicting success from music sales data: a statistical and adaptive approach
Found in: Proceedings of the 1st ACM workshop on Audio and music computing multimedia (AMCMM '06)
By Jonathan Berger, Malcolm Slaney, Song Hui Chon
Issue Date:October 2006
pp. 83-88
Musical taste is highly individualized and evolves over time in seemingly unpredictable ways. However popular trends emerge as collective and potentially predictable patterns of preference for genre and style. The goal of this paper is to reveal these patt...
     
Measuring playlist diversity for recommendation systems
Found in: Proceedings of the 1st ACM workshop on Audio and music computing multimedia (AMCMM '06)
By Malcolm Slaney, William White
Issue Date:October 2006
pp. 77-82
We describe a way to measure the diversity of consumer's musical interests and characterize this diversity using published musical playlists. For each song in the playlist we calculate a set of features, which were optimized for genre recognition, and repr...
     
Automatic chord recognition from audio using a supervised HMM trained with audio-from-symbolic data
Found in: Proceedings of the 1st ACM workshop on Audio and music computing multimedia (AMCMM '06)
By Kyogu Lee, Malcolm Slaney
Issue Date:October 2006
pp. 11-20
A novel approach for obtaining labeled training data is presented to directly estimate the model parameters in a supervised learning algorithm for automatic chord recognition from the raw audio. To this end, harmonic analysis is first performed on symbolic...
     
Multimedia edges: finding hierarchy in all dimensions
Found in: Proceedings of the ninth ACM international conference on Multimedia (MULTIMEDIA '01)
By Dulce Ponceleon, James Kaufman, Malcolm Slaney
Issue Date:September 2001
pp. 29-40
This paper describes a new unified representation for the informa┬┐tion in a video. We reduce the dimensionality of the signal with either a singular-value decomposition (on the semantic and image data) or mel-frequency cepstral coefficients (on the audio d...
     
 1