Matches in ScholarlyData for { ?s ?p ?o. }
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasLastItem item-5.
- item-1 type ListItem.
- item-1 hasContent gengxin-miao.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent junichi-tatemura.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent wang-pin-hsiung.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent arsany-sawires.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent louise-e-moser.
- item-5 previous item-4.
- 100 creator chi-young-oh.
- 100 creator gary-marchionini.
- 100 creator yaxiao-song.
- 100 type InProceedings.
- 100 label "What are the most eye-catching and ear-catching features in the video? Implications for video summarization.".
- 100 sameAs 100.
- 100 abstract "With the rapid growth in computing technology and explosive proliferation of digital videos online, it is imperative to give web users effective summarization and skimming tools to facilitate finding and browsing of videos. Video summarization, a mechanism for generating short summaries of videos, has become a common approach for aiding users in browsing and retrieving relevant videos from large video collections. To produce reliable automatic video summarization algorithms, it is essential to first understand how human beings create video summaries with manual efforts. This paper examines a set of video summaries created by multiple human assessors for instructional documentary videos, and identifies the most eye-catching and ear-catching features in these manually generated video summaries. The paper provides insights into what features automatic algorithms should be looking for when performing automatic video summarization.".
- 100 hasAuthorList authorList.
- 100 isPartOf proceedings.
- 100 keyword "Indexing".
- 100 keyword "retrieval of Web rich-media content".
- 100 title "What are the most eye-catching and ear-catching features in the video? Implications for video summarization.".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent yaxiao-song.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent gary-marchionini.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent chi-young-oh.
- item-3 previous item-2.
- 1000 creator jennifer-neville.
- 1000 creator monica-rogati.
- 1000 creator rongjing-xiang.
- 1000 type InProceedings.
- 1000 label "Modeling Relationship Strength in Online Social Network".
- 1000 sameAs 1000.
- 1000 abstract "Previous work analyzing social networks has mainly focused on binary friendship relations. However, in online social networks the low cost of link formation can lead to networks with heterogeneous relationship strengths (e.g., acquaintances and best friends mixed together). In this case, the binary friendship indicator provides only a coarse representation of relationship information. In this work, we develop an unsupervised model to estimate relationship strength from interaction activity (e.g., communication, tagging) and user similarity. More specifically, we formulate a link-based latent variable model, along with a coordinate ascent optimization procedure for the inference. We evaluate our approach on real-world data from Facebook and LinkedIn, showing that the estimated link weights result in higher autocorrelation and lead to improved classification accuracy.".
- 1000 hasAuthorList authorList.
- 1000 isPartOf proceedings.
- 1000 keyword "Models for social networks".
- 1000 keyword "their evolution".
- 1000 title "Modeling Relationship Strength in Online Social Network".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent rongjing-xiang.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent jennifer-neville.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent monica-rogati.
- item-3 previous item-2.
- 1010 creator duncan-watts.
- 1010 creator jake-hofman.
- 1010 creator munmun-de-choudhury.
- 1010 creator winter-mason.
- 1010 type InProceedings.
- 1010 label "Inferring Relevant Social Networks from Interpersonal Communication".
- 1010 sameAs 1010.
- 1010 abstract "Researchers increasingly use electronic communication data to construct and study large social networks, effectively inferring unobserved ties (e.g. i is connected to j) from observed communication events (e.g. i emails j). Often overlooked, however, is the impact of tie definition on the corresponding network, and in turn the relevance of the inferred network to the research question of interest. Here we study the problem of network inference and relevance for two email data sets of different size and origin. In each case, we generate a family of networks parameterized by a threshold condition on the frequency of emails exchanged between pairs of individuals. After demonstrating that different choices of the threshold correspond to dramatically different network structures, we then formulate the relevance of these networks in terms of a series of prediction tasks that depend on various network features. In general, we find: a) that prediction accuracy is maximized over a non-trivial range of thresholds corresponding to 5--10 reciprocated emails per year; b) that for any prediction task, choosing the optimal value of the threshold yields a sizable (~30%) boost in accuracy over naive choices; and c) that the optimal threshold value appears to be (somewhat surprisingly) consistent across data sets and prediction tasks. We emphasize the practical utility in defining ties via their relevance to the prediction task(s) at hand and discuss implications of our empirical results.".
- 1010 hasAuthorList authorList.
- 1010 isPartOf proceedings.
- 1010 keyword "Measuring".
- 1010 keyword "explaining properties of social networks".
- 1010 title "Inferring Relevant Social Networks from Interpersonal Communication".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.