FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W68733909> ?p ?o ?g. }

• W68733909 endingPage "899" @default.
• W68733909 startingPage "853" @default.
• W68733909 abstract "The ability to associate images with natural language sentences that describe what is depicted in them is a hallmark of image understanding, and a prerequisite for applications such as sentence-based image search. In analogy to image search, we propose to frame sentence-based image annotation as the task of ranking a given pool of captions. We introduce a new benchmark collection for sentence-based image description and search, consisting of 8,000 images that are each paired with five different captions which provide clear descriptions of the salient entities and events. We introduce a number of systems that perform quite well on this task, even though they are only based on features that can be obtained with minimal supervision. Our results clearly indicate the importance of training on multiple captions per image, and of capturing syntactic (word order-based) and semantic features of these captions. We also perform an in-depth comparison of human and automatic evaluation metrics for this task, and propose strategies for collecting human judgments cheaply and on a very large scale, allowing us to augment our collection with additional relevance judgments of which captions describe which image. Our analysis shows that metrics that consider the ranked list of results for each query image or sentence are significantly more robust than metrics that are based on a single response per query. Moreover, our study suggests that the evaluation of ranking-based image description systems may be fully automated." @default.
• W68733909 created "2016-06-24" @default.
• W68733909 creator A5042661827 @default.
• W68733909 creator A5045060643 @default.
• W68733909 creator A5048989024 @default.
• W68733909 date "2013-08-30" @default.
• W68733909 modified "2023-10-14" @default.
• W68733909 title "Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics" @default.
• W68733909 cites W114341944 @default.
• W68733909 cites W1489525520 @default.
• W68733909 cites W1510073064 @default.
• W68733909 cites W1515242458 @default.
• W68733909 cites W151785663 @default.
• W68733909 cites W1527575280 @default.
• W68733909 cites W1532325895 @default.
• W68733909 cites W1545305210 @default.
• W68733909 cites W1647729745 @default.
• W68733909 cites W1687846465 @default.
• W68733909 cites W1711703781 @default.
• W68733909 cites W1858383477 @default.
• W68733909 cites W1861492603 @default.
• W68733909 cites W1895577753 @default.
• W68733909 cites W1897761818 @default.
• W68733909 cites W1977531404 @default.
• W68733909 cites W1982897610 @default.
• W68733909 cites W1983988843 @default.
• W68733909 cites W1987486061 @default.
• W68733909 cites W1990190154 @default.
• W68733909 cites W1995689975 @default.
• W68733909 cites W2006969979 @default.
• W68733909 cites W2020842694 @default.
• W68733909 cites W2025341678 @default.
• W68733909 cites W2029163572 @default.
• W68733909 cites W2038721957 @default.
• W68733909 cites W2053154970 @default.
• W68733909 cites W2062955551 @default.
• W68733909 cites W2066134726 @default.
• W68733909 cites W2066941820 @default.
• W68733909 cites W2098162425 @default.
• W68733909 cites W2100235303 @default.
• W68733909 cites W2101105183 @default.
• W68733909 cites W2102765684 @default.
• W68733909 cites W2106277773 @default.
• W68733909 cites W2108082645 @default.
• W68733909 cites W2109586012 @default.
• W68733909 cites W2109710679 @default.
• W68733909 cites W2110485445 @default.
• W68733909 cites W2111993661 @default.
• W68733909 cites W2119775030 @default.
• W68733909 cites W2120419212 @default.
• W68733909 cites W2124101779 @default.
• W68733909 cites W2126384256 @default.
• W68733909 cites W2127411609 @default.
• W68733909 cites W2128856065 @default.
• W68733909 cites W2133459682 @default.
• W68733909 cites W2137471889 @default.
• W68733909 cites W2141000440 @default.
• W68733909 cites W2141766660 @default.
• W68733909 cites W2142468277 @default.
• W68733909 cites W2144600658 @default.
• W68733909 cites W2149172860 @default.
• W68733909 cites W2150824314 @default.
• W68733909 cites W2151103935 @default.
• W68733909 cites W2153222072 @default.
• W68733909 cites W2154652894 @default.
• W68733909 cites W2156985047 @default.
• W68733909 cites W2162867699 @default.
• W68733909 cites W2167277498 @default.
• W68733909 cites W2167693926 @default.
• W68733909 cites W2168186441 @default.
• W68733909 cites W2185175083 @default.
• W68733909 cites W2264742718 @default.
• W68733909 cites W2951805548 @default.
• W68733909 cites W2962706528 @default.
• W68733909 cites W2962835968 @default.
• W68733909 cites W3000226596 @default.
• W68733909 cites W8316075 @default.
• W68733909 cites W92662927 @default.
• W68733909 cites W956551720 @default.
• W68733909 doi "https://doi.org/10.1613/jair.3994" @default.
• W68733909 hasPublicationYear "2013" @default.
• W68733909 type Work @default.
• W68733909 sameAs 68733909 @default.
• W68733909 citedByCount "924" @default.
• W68733909 countsByYear W687339092012 @default.
• W68733909 countsByYear W687339092014 @default.
• W68733909 countsByYear W687339092015 @default.
• W68733909 countsByYear W687339092016 @default.
• W68733909 countsByYear W687339092017 @default.
• W68733909 countsByYear W687339092018 @default.
• W68733909 countsByYear W687339092019 @default.
• W68733909 countsByYear W687339092020 @default.
• W68733909 countsByYear W687339092021 @default.
• W68733909 countsByYear W687339092022 @default.
• W68733909 countsByYear W687339092023 @default.
• W68733909 crossrefType "journal-article" @default.
• W68733909 hasAuthorship W68733909A5042661827 @default.
• W68733909 hasAuthorship W68733909A5045060643 @default.

• next