Matches in SemOpenAlex for { <https://semopenalex.org/work/W80459767> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W80459767 abstract "We are interested in content-based tasks for visual media, especially video. Automatic assignment of semantic tags representing visual or multimodal concepts (“high-level features”) to video segments is a fundamental technology for filtering, categorization, browsing, search, and other video exploitation activities. Approaches based on using metadata, automatically recognised speech, image-image similarity, and object detection and matching all have their contributions but using semantic concepts is the one which is most scalable and has an interesting intersection with language. TRECVid is an annual benchmarking activity which has been on-going for 10 years [1]. It has focused on many tasks such as shot boundary detection, summarisation, and various forms of search. The 2012 running of TRECVid addressed 6 tasks, including Semantic INdexing (SIN) of video. The rationale for the SIN task is as follows. Given a test collection of video, a master shot reference, and a set of concept definitions, return for each concept a list of at most 2,000 shot IDs from the test collection ranked according to their likelihood of containing the concept. The data set is 291 hours of short videos with durations between 10 seconds and 3.5 minutes where there exists at least 4 positive samples of each concept. Of the 346 test concepts, a subset of 50, not known by participants at submission time, are manually judged. This task has run since the start of TRECVid and in 2012, the task is similar to previous years, except in scale. Previously, for the majority of participants the approach was to build independent concept detectors based on training a machine learning toolkit on a set of positive and negative example shots, using low-level features from the images, as described in [2]. To cater for this, a collaborative annotation of the concepts is carried out each year to build a concept bank on which to train classifiers. The TRECVid organizers also provide a set of relations between the concepts of two types: A implies B and A excludes B. Relations that can be derived by transitivity are not included. Participants are free to use the relations or not and submissions are not required to comply with them. Some of the more advanced methods from participants use the annotations of non-evaluated concepts and the ontology relations to improve the detection of the evaluated concepts." @default.
- W80459767 created "2016-06-24" @default.
- W80459767 creator A5008334059 @default.
- W80459767 creator A5008973400 @default.
- W80459767 creator A5049624750 @default.
- W80459767 date "2012-12-13" @default.
- W80459767 modified "2023-09-27" @default.
- W80459767 title "A decade of work on semantic concept detection from video: TRECVid’s contribution" @default.
- W80459767 cites W1605811577 @default.
- W80459767 cites W2013970786 @default.
- W80459767 cites W2062903088 @default.
- W80459767 hasPublicationYear "2012" @default.
- W80459767 type Work @default.
- W80459767 sameAs 80459767 @default.
- W80459767 citedByCount "0" @default.
- W80459767 crossrefType "journal-article" @default.
- W80459767 hasAuthorship W80459767A5008334059 @default.
- W80459767 hasAuthorship W80459767A5008973400 @default.
- W80459767 hasAuthorship W80459767A5049624750 @default.
- W80459767 hasConcept C127413603 @default.
- W80459767 hasConcept C136764020 @default.
- W80459767 hasConcept C146978453 @default.
- W80459767 hasConcept C154945302 @default.
- W80459767 hasConcept C162324750 @default.
- W80459767 hasConcept C177264268 @default.
- W80459767 hasConcept C178790620 @default.
- W80459767 hasConcept C184337299 @default.
- W80459767 hasConcept C185592680 @default.
- W80459767 hasConcept C187736073 @default.
- W80459767 hasConcept C199360897 @default.
- W80459767 hasConcept C204321447 @default.
- W80459767 hasConcept C23123220 @default.
- W80459767 hasConcept C2778344882 @default.
- W80459767 hasConcept C2780451532 @default.
- W80459767 hasConcept C2781238097 @default.
- W80459767 hasConcept C41008148 @default.
- W80459767 hasConcept C64543145 @default.
- W80459767 hasConcept C75165309 @default.
- W80459767 hasConcept C93518851 @default.
- W80459767 hasConcept C94124525 @default.
- W80459767 hasConceptScore W80459767C127413603 @default.
- W80459767 hasConceptScore W80459767C136764020 @default.
- W80459767 hasConceptScore W80459767C146978453 @default.
- W80459767 hasConceptScore W80459767C154945302 @default.
- W80459767 hasConceptScore W80459767C162324750 @default.
- W80459767 hasConceptScore W80459767C177264268 @default.
- W80459767 hasConceptScore W80459767C178790620 @default.
- W80459767 hasConceptScore W80459767C184337299 @default.
- W80459767 hasConceptScore W80459767C185592680 @default.
- W80459767 hasConceptScore W80459767C187736073 @default.
- W80459767 hasConceptScore W80459767C199360897 @default.
- W80459767 hasConceptScore W80459767C204321447 @default.
- W80459767 hasConceptScore W80459767C23123220 @default.
- W80459767 hasConceptScore W80459767C2778344882 @default.
- W80459767 hasConceptScore W80459767C2780451532 @default.
- W80459767 hasConceptScore W80459767C2781238097 @default.
- W80459767 hasConceptScore W80459767C41008148 @default.
- W80459767 hasConceptScore W80459767C64543145 @default.
- W80459767 hasConceptScore W80459767C75165309 @default.
- W80459767 hasConceptScore W80459767C93518851 @default.
- W80459767 hasConceptScore W80459767C94124525 @default.
- W80459767 hasLocation W804597671 @default.
- W80459767 hasOpenAccess W80459767 @default.
- W80459767 hasPrimaryLocation W804597671 @default.
- W80459767 hasRelatedWork W1771558772 @default.
- W80459767 hasRelatedWork W1973581457 @default.
- W80459767 hasRelatedWork W1982795953 @default.
- W80459767 hasRelatedWork W2048261712 @default.
- W80459767 hasRelatedWork W2072136734 @default.
- W80459767 hasRelatedWork W2097830588 @default.
- W80459767 hasRelatedWork W2103556603 @default.
- W80459767 hasRelatedWork W2110935080 @default.
- W80459767 hasRelatedWork W2139882085 @default.
- W80459767 hasRelatedWork W2155015210 @default.
- W80459767 hasRelatedWork W2163174791 @default.
- W80459767 hasRelatedWork W2184848982 @default.
- W80459767 hasRelatedWork W2548993058 @default.
- W80459767 hasRelatedWork W2732761615 @default.
- W80459767 hasRelatedWork W2895639515 @default.
- W80459767 hasRelatedWork W2964134286 @default.
- W80459767 hasRelatedWork W3008050599 @default.
- W80459767 hasRelatedWork W3036846062 @default.
- W80459767 hasRelatedWork W3154360660 @default.
- W80459767 hasRelatedWork W620452028 @default.
- W80459767 isParatext "false" @default.
- W80459767 isRetracted "false" @default.
- W80459767 magId "80459767" @default.
- W80459767 workType "article" @default.