Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891549171> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2891549171 abstract "Recently, researches are emerging to extend CNN-based segmentation approaches from still image to video. Directly applying per-frame based image segmentation networks on video is not efficient. To address this issue, a promising direction is to explore the video continuity. A state-of-the-art approach called Deep Feature Flow (DFF) runs the segmentation network only on sparse key frames and propagates feature maps to other frames via cross-frame motion. However, such approach does not work well for hand segmentation in a video as it is not robust to hand posture change. In this paper, we propose to incorporate a light-weight detail enhancement network (DEN) into the DFF framework to achieve robustness against cross-frame motion and hand posture change. Experimental results on a public depth video dataset, FingerPaint, demonstrate that our approach achieves higher segmentation accuracy than the DFF-based approach with similar speedups against the per-frame based video hand segmentation approach." @default.
- W2891549171 created "2018-09-27" @default.
- W2891549171 creator A5039662070 @default.
- W2891549171 creator A5077092506 @default.
- W2891549171 creator A5088623594 @default.
- W2891549171 date "2018-10-01" @default.
- W2891549171 modified "2023-10-16" @default.
- W2891549171 title "DFF-DEN: Deep Feature Flow with Detail Enhancement Network for Hand Segmentation in Depth Video" @default.
- W2891549171 cites W1568156700 @default.
- W2891549171 cites W1903029394 @default.
- W2891549171 cites W1969595749 @default.
- W2891549171 cites W1975694442 @default.
- W2891549171 cites W2005255079 @default.
- W2891549171 cites W2023633446 @default.
- W2891549171 cites W2075156252 @default.
- W2891549171 cites W2155893237 @default.
- W2891549171 cites W2169374518 @default.
- W2891549171 cites W2194775991 @default.
- W2891549171 cites W2204609240 @default.
- W2891549171 cites W2293778192 @default.
- W2891549171 cites W2412782625 @default.
- W2891549171 cites W2469784314 @default.
- W2891549171 cites W2520346623 @default.
- W2891549171 cites W2552900565 @default.
- W2891549171 cites W2560023338 @default.
- W2891549171 cites W2608508975 @default.
- W2891549171 cites W2609077090 @default.
- W2891549171 cites W2962811204 @default.
- W2891549171 cites W2962835968 @default.
- W2891549171 cites W2963866581 @default.
- W2891549171 cites W2963881378 @default.
- W2891549171 cites W3098312772 @default.
- W2891549171 cites W764651262 @default.
- W2891549171 doi "https://doi.org/10.1109/icip.2018.8451687" @default.
- W2891549171 hasPublicationYear "2018" @default.
- W2891549171 type Work @default.
- W2891549171 sameAs 2891549171 @default.
- W2891549171 citedByCount "0" @default.
- W2891549171 crossrefType "proceedings-article" @default.
- W2891549171 hasAuthorship W2891549171A5039662070 @default.
- W2891549171 hasAuthorship W2891549171A5077092506 @default.
- W2891549171 hasAuthorship W2891549171A5088623594 @default.
- W2891549171 hasConcept C104317684 @default.
- W2891549171 hasConcept C115961682 @default.
- W2891549171 hasConcept C124504099 @default.
- W2891549171 hasConcept C126042441 @default.
- W2891549171 hasConcept C138885662 @default.
- W2891549171 hasConcept C154945302 @default.
- W2891549171 hasConcept C155542232 @default.
- W2891549171 hasConcept C185592680 @default.
- W2891549171 hasConcept C25694479 @default.
- W2891549171 hasConcept C2776401178 @default.
- W2891549171 hasConcept C31972630 @default.
- W2891549171 hasConcept C41008148 @default.
- W2891549171 hasConcept C41895202 @default.
- W2891549171 hasConcept C55493867 @default.
- W2891549171 hasConcept C63479239 @default.
- W2891549171 hasConcept C65885262 @default.
- W2891549171 hasConcept C76155785 @default.
- W2891549171 hasConcept C89600930 @default.
- W2891549171 hasConceptScore W2891549171C104317684 @default.
- W2891549171 hasConceptScore W2891549171C115961682 @default.
- W2891549171 hasConceptScore W2891549171C124504099 @default.
- W2891549171 hasConceptScore W2891549171C126042441 @default.
- W2891549171 hasConceptScore W2891549171C138885662 @default.
- W2891549171 hasConceptScore W2891549171C154945302 @default.
- W2891549171 hasConceptScore W2891549171C155542232 @default.
- W2891549171 hasConceptScore W2891549171C185592680 @default.
- W2891549171 hasConceptScore W2891549171C25694479 @default.
- W2891549171 hasConceptScore W2891549171C2776401178 @default.
- W2891549171 hasConceptScore W2891549171C31972630 @default.
- W2891549171 hasConceptScore W2891549171C41008148 @default.
- W2891549171 hasConceptScore W2891549171C41895202 @default.
- W2891549171 hasConceptScore W2891549171C55493867 @default.
- W2891549171 hasConceptScore W2891549171C63479239 @default.
- W2891549171 hasConceptScore W2891549171C65885262 @default.
- W2891549171 hasConceptScore W2891549171C76155785 @default.
- W2891549171 hasConceptScore W2891549171C89600930 @default.
- W2891549171 hasLocation W28915491711 @default.
- W2891549171 hasOpenAccess W2891549171 @default.
- W2891549171 hasPrimaryLocation W28915491711 @default.
- W2891549171 hasRelatedWork W1601487386 @default.
- W2891549171 hasRelatedWork W1631910785 @default.
- W2891549171 hasRelatedWork W2027450165 @default.
- W2891549171 hasRelatedWork W2064520362 @default.
- W2891549171 hasRelatedWork W2152920139 @default.
- W2891549171 hasRelatedWork W2154333700 @default.
- W2891549171 hasRelatedWork W2157087525 @default.
- W2891549171 hasRelatedWork W2170302272 @default.
- W2891549171 hasRelatedWork W2546232368 @default.
- W2891549171 hasRelatedWork W2182382398 @default.
- W2891549171 isParatext "false" @default.
- W2891549171 isRetracted "false" @default.
- W2891549171 magId "2891549171" @default.
- W2891549171 workType "article" @default.