FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322741600> ?p ?o ?g. }

• W4322741600 endingPage "501" @default.
• W4322741600 startingPage "485" @default.
• W4322741600 abstract "Self-supervised learning has drawn attention through its effectiveness in learning in-domain representations with no ground-truth annotations; in particular, it is shown that properly designed pretext tasks bring significant performance gains for downstream tasks. Inspired from this, we tackle video scene segmentation, which is a task of temporally localizing scene boundaries in a long video, with a self-supervised learning framework where we mainly focus on designing effective pretext tasks. In our framework, given a long video, we adopt a sliding window scheme; from a sequence of shots in each window, we discover a moment with a maximum semantic transition and leverage it as pseudo-boundary to facilitate the pre-training. Specifically, we introduce three novel boundary-aware pretext tasks: 1) Shot-Scene Matching (SSM), 2) Contextual Group Matching (CGM) and 3) Pseudo-boundary Prediction (PP); SSM and CGM guide the model to maximize intra-scene similarity and inter-scene discrimination by capturing contextual relation between shots while PP encourages the model to identify transitional moments. We perform an extensive analysis to validate effectiveness of our method and achieve the new state-of-the-art on the MovieNet-SSeg benchmark. The code is available at https://github.com/kakaobrain/bassl ." @default.
• W4322741600 created "2023-03-03" @default.
• W4322741600 creator A5008666758 @default.
• W4322741600 creator A5011022538 @default.
• W4322741600 creator A5028292436 @default.
• W4322741600 creator A5041553395 @default.
• W4322741600 creator A5052116704 @default.
• W4322741600 creator A5057225987 @default.
• W4322741600 creator A5067433666 @default.
• W4322741600 date "2023-01-01" @default.
• W4322741600 modified "2023-09-26" @default.
• W4322741600 title "BaSSL: Boundary-aware Self-Supervised Learning for Video Scene Segmentation" @default.
• W4322741600 cites W190821737 @default.
• W4322741600 cites W1963878379 @default.
• W4322741600 cites W2063249218 @default.
• W4322741600 cites W2108598243 @default.
• W4322741600 cites W2151617679 @default.
• W4322741600 cites W2171186743 @default.
• W4322741600 cites W2194775991 @default.
• W4322741600 cites W2487442924 @default.
• W4322741600 cites W2491875666 @default.
• W4322741600 cites W2578494166 @default.
• W4322741600 cites W2645519508 @default.
• W4322741600 cites W2732026016 @default.
• W4322741600 cites W2906270977 @default.
• W4322741600 cites W2948242301 @default.
• W4322741600 cites W2957775769 @default.
• W4322741600 cites W2963426332 @default.
• W4322741600 cites W2963642716 @default.
• W4322741600 cites W2963853051 @default.
• W4322741600 cites W2964037671 @default.
• W4322741600 cites W2981851019 @default.
• W4322741600 cites W2982335217 @default.
• W4322741600 cites W3009622574 @default.
• W4322741600 cites W3034364644 @default.
• W4322741600 cites W3035218028 @default.
• W4322741600 cites W3035524453 @default.
• W4322741600 cites W3035557275 @default.
• W4322741600 cites W3090449556 @default.
• W4322741600 cites W3095481265 @default.
• W4322741600 cites W3099032148 @default.
• W4322741600 cites W3108225446 @default.
• W4322741600 cites W3120214499 @default.
• W4322741600 cites W3123599388 @default.
• W4322741600 cites W3124314487 @default.
• W4322741600 cites W3145385912 @default.
• W4322741600 cites W3170837227 @default.
• W4322741600 cites W3174415835 @default.
• W4322741600 cites W3174587031 @default.
• W4322741600 cites W3177173029 @default.
• W4322741600 cites W3184549588 @default.
• W4322741600 cites W4247996926 @default.
• W4322741600 cites W4313165677 @default.
• W4322741600 doi "https://doi.org/10.1007/978-3-031-26316-3_29" @default.
• W4322741600 hasPublicationYear "2023" @default.
• W4322741600 type Work @default.
• W4322741600 citedByCount "1" @default.
• W4322741600 countsByYear W43227416002023 @default.
• W4322741600 crossrefType "book-chapter" @default.
• W4322741600 hasAuthorship W4322741600A5008666758 @default.
• W4322741600 hasAuthorship W4322741600A5011022538 @default.
• W4322741600 hasAuthorship W4322741600A5028292436 @default.
• W4322741600 hasAuthorship W4322741600A5041553395 @default.
• W4322741600 hasAuthorship W4322741600A5052116704 @default.
• W4322741600 hasAuthorship W4322741600A5057225987 @default.
• W4322741600 hasAuthorship W4322741600A5067433666 @default.
• W4322741600 hasConcept C105795698 @default.
• W4322741600 hasConcept C119857082 @default.
• W4322741600 hasConcept C153083717 @default.
• W4322741600 hasConcept C154945302 @default.
• W4322741600 hasConcept C165064840 @default.
• W4322741600 hasConcept C17744445 @default.
• W4322741600 hasConcept C199539241 @default.
• W4322741600 hasConcept C2779627259 @default.
• W4322741600 hasConcept C31972630 @default.
• W4322741600 hasConcept C33923547 @default.
• W4322741600 hasConcept C41008148 @default.
• W4322741600 hasConcept C89600930 @default.
• W4322741600 hasConcept C94625758 @default.
• W4322741600 hasConceptScore W4322741600C105795698 @default.
• W4322741600 hasConceptScore W4322741600C119857082 @default.
• W4322741600 hasConceptScore W4322741600C153083717 @default.
• W4322741600 hasConceptScore W4322741600C154945302 @default.
• W4322741600 hasConceptScore W4322741600C165064840 @default.
• W4322741600 hasConceptScore W4322741600C17744445 @default.
• W4322741600 hasConceptScore W4322741600C199539241 @default.
• W4322741600 hasConceptScore W4322741600C2779627259 @default.
• W4322741600 hasConceptScore W4322741600C31972630 @default.
• W4322741600 hasConceptScore W4322741600C33923547 @default.
• W4322741600 hasConceptScore W4322741600C41008148 @default.
• W4322741600 hasConceptScore W4322741600C89600930 @default.
• W4322741600 hasConceptScore W4322741600C94625758 @default.
• W4322741600 hasLocation W43227416001 @default.
• W4322741600 hasOpenAccess W4322741600 @default.
• W4322741600 hasPrimaryLocation W43227416001 @default.
• W4322741600 hasRelatedWork W1669643531 @default.
• W4322741600 hasRelatedWork W1982826852 @default.
• W4322741600 hasRelatedWork W2005437358 @default.

• next