FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W36199337> ?p ?o ?g. }

• W36199337 abstract "Video and image retrieval has been an active and challenging research area due to the explosive growth of online video data, personal video recordings, digital photos, and broadcast news videos. In order to effectively manage and use such enormous multimedia resources, users need to be able to access, search, or browse video content at the semantic level. Current solutions primarily rely on text features and do not utilize rich multimodal cues. Works exploring multimodal features often use manually selected features and/or ad hoc models, thus lacking scalability to general applications. To fully exploit the potential of integrating multimodal features and ensure generality of solutions, this thesis presents a novel, rigorous framework and new statistical methods for video structuring, threading, and search in large-scale video databases.We focus on investigation of several fundamental problems for video indexing and retrieval: (1) How to select and fuse a large number of heterogeneous multimodal features from image, speech, audio, arid text? (2) How to automatically discover and model mid-level features for multimedia content? (3) How to model similarity between multimodal documents such as news videos or multimedia web documents? (4) How to exploit unsupervised methods in video search to boost performance in an automatic fashion?To address such challenging problems, our main contributions include the following: First, we extend the Maximum Entropy model to fuse diverse perceptual features from multiple levels and modalities and demonstrate significant performance improvement in broadcast news video segmentation. Secondly, we propose an information-theoretic approach to automatically construct mid-level representations. It is the first work to remove the dependency on the manual and labor-intensive processes in developing mid-level feature representations from low-level features. Thirdly, we introduce new multimodal representations based on visual duplicates, cue word clusters, high-level concepts, etc. to compute similarity between the multimedia documents. Using such new similarity metrics, we demonstrate significant gain in rnulti-lingual cross-domain topic tracking. Lastly, to improve the automatic image and video search performance, we propose two new methods for reranking the initial video search results based on text keywords only. In the image/video level, we apply the information bottleneck principle to discover the image clusters in the initial search results, and then rerank the images based on cluster-level relevance scores and the occurrence frequency of images. Such method is efficient and generic, applicable to reranking of any initial search results using other search approaches, such as content-based image search or semantic concept-based search. In the multimedia document level, building on the multimodal document similarities, we propose a random walk framework for reranking the initial text-based video search results. Significant performance improvement is demonstrated in comparison with text-based reranking methods. In addition, we have studied application and optimal parameter settings of the power method in solving the multi-modal random walk problems. All of our experiments are conducted using the large-scale diverse video data such as the TRECVID benchmark data set, which includes more than 160 hours of broadcast videos from multiple international channels." @default.
• W36199337 created "2016-06-24" @default.
• W36199337 creator A5017855052 @default.
• W36199337 creator A5043898632 @default.
• W36199337 date "2007-01-01" @default.
• W36199337 modified "2023-09-24" @default.
• W36199337 title "An information-theoretic framework towards large-scale video structuring, threading, and retrieval" @default.
• W36199337 cites W112397748 @default.
• W36199337 cites W1482214997 @default.
• W36199337 cites W1491644433 @default.
• W36199337 cites W1528949297 @default.
• W36199337 cites W1540940911 @default.
• W36199337 cites W1557074680 @default.
• W36199337 cites W1578226009 @default.
• W36199337 cites W1589050831 @default.
• W36199337 cites W1592225080 @default.
• W36199337 cites W1679913846 @default.
• W36199337 cites W1854214752 @default.
• W36199337 cites W1967666795 @default.
• W36199337 cites W1972442292 @default.
• W36199337 cites W1983936280 @default.
• W36199337 cites W1992419399 @default.
• W36199337 cites W1998224037 @default.
• W36199337 cites W2004533983 @default.
• W36199337 cites W2009484134 @default.
• W36199337 cites W2010425028 @default.
• W36199337 cites W2016243284 @default.
• W36199337 cites W2031602671 @default.
• W36199337 cites W2042178278 @default.
• W36199337 cites W2046624828 @default.
• W36199337 cites W2048679005 @default.
• W36199337 cites W2052470695 @default.
• W36199337 cites W2058685270 @default.
• W36199337 cites W2060314721 @default.
• W36199337 cites W2066727938 @default.
• W36199337 cites W2079234336 @default.
• W36199337 cites W2080942732 @default.
• W36199337 cites W2086028291 @default.
• W36199337 cites W2089150756 @default.
• W36199337 cites W2096041903 @default.
• W36199337 cites W2096175520 @default.
• W36199337 cites W2099111195 @default.
• W36199337 cites W2103723258 @default.
• W36199337 cites W2105126865 @default.
• W36199337 cites W2109283550 @default.
• W36199337 cites W2109943925 @default.
• W36199337 cites W2110866924 @default.
• W36199337 cites W2112510289 @default.
• W36199337 cites W21165000 @default.
• W36199337 cites W2119484097 @default.
• W36199337 cites W2120477910 @default.
• W36199337 cites W2120887753 @default.
• W36199337 cites W2121947440 @default.
• W36199337 cites W2128594317 @default.
• W36199337 cites W2129193626 @default.
• W36199337 cites W2130395434 @default.
• W36199337 cites W2133455944 @default.
• W36199337 cites W2138775357 @default.
• W36199337 cites W2144080413 @default.
• W36199337 cites W2145541974 @default.
• W36199337 cites W2146558186 @default.
• W36199337 cites W2148603752 @default.
• W36199337 cites W2150753219 @default.
• W36199337 cites W2150938184 @default.
• W36199337 cites W2153635508 @default.
• W36199337 cites W2156598602 @default.
• W36199337 cites W2157391896 @default.
• W36199337 cites W2161118554 @default.
• W36199337 cites W2163288162 @default.
• W36199337 cites W2165874743 @default.
• W36199337 cites W2166541625 @default.
• W36199337 cites W2167247356 @default.
• W36199337 cites W2167725992 @default.
• W36199337 cites W2170344111 @default.
• W36199337 cites W2170512680 @default.
• W36199337 cites W2184848982 @default.
• W36199337 cites W2242334530 @default.
• W36199337 cites W2403632467 @default.
• W36199337 cites W2426479676 @default.
• W36199337 cites W2799004609 @default.
• W36199337 cites W2916209825 @default.
• W36199337 cites W2916453377 @default.
• W36199337 cites W2916567321 @default.
• W36199337 cites W2917011293 @default.
• W36199337 cites W3032163182 @default.
• W36199337 cites W2118736770 @default.
• W36199337 cites W2461406179 @default.
• W36199337 hasPublicationYear "2007" @default.
• W36199337 type Work @default.
• W36199337 sameAs 36199337 @default.
• W36199337 citedByCount "1" @default.
• W36199337 crossrefType "journal-article" @default.
• W36199337 hasAuthorship W36199337A5017855052 @default.
• W36199337 hasAuthorship W36199337A5043898632 @default.
• W36199337 hasConcept C10138342 @default.
• W36199337 hasConcept C136764020 @default.
• W36199337 hasConcept C154945302 @default.
• W36199337 hasConcept C15744967 @default.
• W36199337 hasConcept C162324750 @default.
• W36199337 hasConcept C165696696 @default.

• next