FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2938698191> ?p ?o ?g. }

• W2938698191 abstract "While many action recognition datasets consist of collections of brief, trimmed videos each containing a relevant action, videos in the real-world (e.g., on YouTube) exhibit very different properties: they are often several minutes long, where brief relevant clips are often interleaved with segments of extended duration containing little change. Applying densely an action recognition system to every temporal clip within such videos is prohibitively expensive. Furthermore, as we show in our experiments, this results in suboptimal recognition accuracy as informative predictions from relevant clips are outnumbered by meaningless classification outputs over long uninformative sections of the video. In this paper we introduce a lightweight clip-sampling model that can efficiently identify the most salient temporal clips within a long video. We demonstrate that the computational cost of action recognition on untrimmed videos can be dramatically reduced by invoking recognition only on these most salient clips. Furthermore, we show that this yields significant gains in recognition accuracy compared to analysis of all clips or randomly/uniformly selected clips. On Sports1M, our clip sampling scheme elevates the accuracy of an already state-of-the-art action classifier by 7% and reduces by more than 15 times its computational cost." @default.
• W2938698191 created "2019-04-25" @default.
• W2938698191 creator A5016319243 @default.
• W2938698191 creator A5070413665 @default.
• W2938698191 creator A5082736347 @default.
• W2938698191 date "2019-04-08" @default.
• W2938698191 modified "2023-10-01" @default.
• W2938698191 title "SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition." @default.
• W2938698191 cites W1522734439 @default.
• W2938698191 cites W1904325426 @default.
• W2938698191 cites W1923404803 @default.
• W2938698191 cites W1988650444 @default.
• W2938698191 cites W2016053056 @default.
• W2938698191 cites W2018068650 @default.
• W2938698191 cites W2084341401 @default.
• W2938698191 cites W2115857089 @default.
• W2938698191 cites W2117539524 @default.
• W2938698191 cites W2133728753 @default.
• W2938698191 cites W2139009685 @default.
• W2938698191 cites W2175640409 @default.
• W2938698191 cites W2194775991 @default.
• W2938698191 cites W2235034809 @default.
• W2938698191 cites W2308045930 @default.
• W2938698191 cites W2342776425 @default.
• W2938698191 cites W2471143248 @default.
• W2938698191 cites W2507009361 @default.
• W2938698191 cites W2511428026 @default.
• W2938698191 cites W2519328139 @default.
• W2938698191 cites W2553594924 @default.
• W2938698191 cites W2563717578 @default.
• W2938698191 cites W2593116425 @default.
• W2938698191 cites W2593722617 @default.
• W2938698191 cites W2597958930 @default.
• W2938698191 cites W2604379605 @default.
• W2938698191 cites W2608988379 @default.
• W2938698191 cites W2619697695 @default.
• W2938698191 cites W2619947201 @default.
• W2938698191 cites W2706729717 @default.
• W2938698191 cites W2737666777 @default.
• W2938698191 cites W2737677090 @default.
• W2938698191 cites W2738167012 @default.
• W2938698191 cites W2755876276 @default.
• W2938698191 cites W2770804203 @default.
• W2938698191 cites W2795478783 @default.
• W2938698191 cites W2807968599 @default.
• W2938698191 cites W2884002012 @default.
• W2938698191 cites W2884883933 @default.
• W2938698191 cites W2897230578 @default.
• W2938698191 cites W2902670099 @default.
• W2938698191 cites W2904080086 @default.
• W2938698191 cites W2904419413 @default.
• W2938698191 cites W2934628279 @default.
• W2938698191 cites W2952186347 @default.
• W2938698191 cites W2962677524 @default.
• W2938698191 cites W2962756039 @default.
• W2938698191 cites W2962835968 @default.
• W2938698191 cites W2962865004 @default.
• W2938698191 cites W2962960500 @default.
• W2938698191 cites W2963091558 @default.
• W2938698191 cites W2963115079 @default.
• W2938698191 cites W2963125010 @default.
• W2938698191 cites W2963155035 @default.
• W2938698191 cites W2963220254 @default.
• W2938698191 cites W2963247196 @default.
• W2938698191 cites W2963321993 @default.
• W2938698191 cites W2963370182 @default.
• W2938698191 cites W2963524571 @default.
• W2938698191 cites W2963526497 @default.
• W2938698191 cites W2963919999 @default.
• W2938698191 cites W2964048159 @default.
• W2938698191 cites W2964214371 @default.
• W2938698191 cites W2964216549 @default.
• W2938698191 cites W2984287396 @default.
• W2938698191 hasPublicationYear "2019" @default.
• W2938698191 type Work @default.
• W2938698191 sameAs 2938698191 @default.
• W2938698191 citedByCount "3" @default.
• W2938698191 countsByYear W29386981912019 @default.
• W2938698191 countsByYear W29386981912021 @default.
• W2938698191 crossrefType "posted-content" @default.
• W2938698191 hasAuthorship W2938698191A5016319243 @default.
• W2938698191 hasAuthorship W2938698191A5070413665 @default.
• W2938698191 hasAuthorship W2938698191A5082736347 @default.
• W2938698191 hasConcept C106131492 @default.
• W2938698191 hasConcept C119857082 @default.
• W2938698191 hasConcept C121332964 @default.
• W2938698191 hasConcept C140779682 @default.
• W2938698191 hasConcept C153180895 @default.
• W2938698191 hasConcept C154945302 @default.
• W2938698191 hasConcept C2777212361 @default.
• W2938698191 hasConcept C2778739407 @default.
• W2938698191 hasConcept C2780719617 @default.
• W2938698191 hasConcept C2780791683 @default.
• W2938698191 hasConcept C28490314 @default.
• W2938698191 hasConcept C2987834672 @default.
• W2938698191 hasConcept C31972630 @default.
• W2938698191 hasConcept C41008148 @default.
• W2938698191 hasConcept C62520636 @default.
• W2938698191 hasConcept C95623464 @default.
• W2938698191 hasConceptScore W2938698191C106131492 @default.

• next