547 research outputs found
Architecture and challenges of maintaining a large-scale, context-aware human digital memory
No full textRecent advances in digital multimedia capture, transmission and storage has led us close to realising the MEMEX vision, in which much of an individual's personal information can be stored for retrieval at a later stage. These personal archives (Human Digital Memories (HDMs)) are constructed from a wide range of data sources across various media types. In this paper we examine the challenges of building, organising, browsing, searching and recommending from large (multi-million item per annum) visual HDMs. We present our findings based on an extensive period of HDM generation (2 years and 2 million images), illustrating the challenges of and architectural requirements for managing such archives
MindTheGap 2014 Beyond Single-Shot Text Queries: Bridging the Gap(s) between Research Communities
No full textHFE C282Y homozygosity is associated with an increased risk of total hip replacement for osteoarthritis
No full textAbstract not availableYuanyuan Wang, Lyle C. Gurrin, Anita E. Wluka, Nadine A. Bertalli, Nicholas J. Osborne, Martin B. Delatycki, Graham G. Giles, Dallas R. English, John L. Hopper, Julie A. Simpson, Stephen Graves, Katrina J. Allen, Flavia M. Cicuttin
Image retrieval using multi-scale CNN features pooling
No full textIn this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on NetVLAD and a triplet mining procedure based on samples difficulty to obtain an effective image representation. Extensive experiments show that our approach is able to reach state-of-the-art results on three standard datasets
Use of content analysis tools for visual interaction design
No full textAutomatic media content analysis in multimedia is a very promising field of research bringing in various possibilities for enhancing visual informatics. By computationally analysing the quantitative data contained in text, audio, image and video media, more semantically meaningful and useful information on the media contents can be derived, extracted and visualised, informing human users those facts and patterns initially hidden in the bit streams of data. Insights into how to transform the emerging technological possibilities from these media analysis tools into usable visual interfaces to help people see visual information in novel ways will be an important contribution to visual informatics. In this paper, we outline some of the more promising content analysis techniques currently being researched in multimedia and computer vision and discuss how these could be used to develop visually-oriented end-user interfaces that support searching, browsing and summarization of the media contents in various usage contexts. We illustrate this with a few example applications that we have developed over the years, all of which designed in such a way as to take advantage of the automatic content analysis and to discover and create novel usage scenarios of consuming visually-oriented media contents
Cohort Profile: Melbourne Atopy Cohort study (MACS)
No full textAdvance Access Publication Date: 21 April 2016Adrian J Lowe, Caroline J Lodge, Katrina J Allen, Michael J Abramson, Melanie C Matheson, Paul S Thomas, Christopher A Barton, Catherine M Bennett, Bircan Erbas, Cecilie Svanes, Mathias Wjst, Francisco G, omez Real, Jennifer L Perret, Melissa A Russell, Melissa C Southey, John L Hopper, Lyle C Gurrin, Christine J Axelrad, David J Hill and Shyamali C Dharmag
Towards developing a collaborative video platform for learning
No full textThe work presented in this paper outlines issues relating to the development of a collaborative video platform for learning. Student adoption of collaborative and video technology is increasing dramatically, becoming part of their everyday lives. The aim of this paper is to propose a system and framework for the successful integration of these technologies into teaching and learning. At the outset we assess current trends and previous research, using these findings to inform the development of a new platform. System specifications are then presented with specific needs identified for students and educators. Finally our tentative framework for a integrating a collaborative video platform for learning is presented
The design of an intergenerational lifelog browser to support sharing within family groups
No full textImproving the evaluation of web search systems
No full textLinkage analysis as an aid to web search has been assumed to be of significant benefit and we know that it is being implemented by many major Search Engines. Why then have few TREC participants been able to scientifically prove the benefits of linkage analysis over the past three years? In this paper we put forward reasons why disappointing results have been found and we identify the linkage density requirements of a dataset to faithfully support experiments into linkage analysis. We also report a series of linkage-based retrieval experiments on a more densely linked dataset culled from the TREC web documents
Collaborative searching for video using the Físchlár system and a DiamondTouch table
No full textFischlar DT is one of a family of systems which support interactive searching and browsing through an archive of digital video information. Previous Fischlar systems have used a conventional screen, keyboard and mouse interface, but Fischlar-DT operates with using a horizontal, multiuser, touch sensitive tabletop known as a DiamondTouch. We present the Fischlar-DT system partly from a systems perspective, but mostly in terms of how its design and functionality supports collaborative searching. The contribution of the paper is thus the introduction of Fischlar-DT and a description of how design concerns for supporting collaborative search can be realised on a tabletop interface
- …
