Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308456711> ?p ?o ?g. }
- W4308456711 endingPage "549" @default.
- W4308456711 startingPage "531" @default.
- W4308456711 abstract "Abstract We present the first comprehensive video polyp segmentation (VPS) study in the deep learning era. Over the years, developments in VPS are not moving forward with ease due to the lack of a large-scale dataset with fine-grained segmentation annotations. To address this issue, we first introduce a high-quality frame-by-frame annotated VPS dataset, named SUN-SEG, which contains 158 690 colonoscopy video frames from the well-known SUN-database. We provide additional annotation covering diverse types, i.e., attribute, object mask, boundary, scribble, and polygon. Second, we design a simple but efficient baseline, named PNS+, which consists of a global encoder, a local encoder, and normalized self-attention (NS) blocks. The global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations, which are then progressively refined by two NS blocks. Extensive experiments show that PNS+ achieves the best performance and real-time inference speed (170 fps), making it a promising solution for the VPS task. Third, we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based comparisons. Finally, we discuss several open issues and suggest possible research directions for the VPS community. Our project and dataset are publicly available at https://github.com/GewelsJI/VPS ." @default.
- W4308456711 created "2022-11-12" @default.
- W4308456711 creator A5001254143 @default.
- W4308456711 creator A5001285878 @default.
- W4308456711 creator A5050524397 @default.
- W4308456711 creator A5056294284 @default.
- W4308456711 creator A5063072430 @default.
- W4308456711 creator A5078276127 @default.
- W4308456711 creator A5081513423 @default.
- W4308456711 date "2022-11-03" @default.
- W4308456711 modified "2023-10-18" @default.
- W4308456711 title "Video Polyp Segmentation: A Deep Learning Perspective" @default.
- W4308456711 cites W1901129140 @default.
- W4308456711 cites W1994922096 @default.
- W4308456711 cites W2008359794 @default.
- W4308456711 cites W2021088830 @default.
- W4308456711 cites W2034269173 @default.
- W4308456711 cites W2077474654 @default.
- W4308456711 cites W2100470808 @default.
- W4308456711 cites W2155195832 @default.
- W4308456711 cites W2156967881 @default.
- W4308456711 cites W2194775991 @default.
- W4308456711 cites W2285968993 @default.
- W4308456711 cites W2332757643 @default.
- W4308456711 cites W2560328367 @default.
- W4308456711 cites W2560770519 @default.
- W4308456711 cites W2593488799 @default.
- W4308456711 cites W2620841913 @default.
- W4308456711 cites W2623808523 @default.
- W4308456711 cites W2803469628 @default.
- W4308456711 cites W2806175674 @default.
- W4308456711 cites W2928165649 @default.
- W4308456711 cites W2955084925 @default.
- W4308456711 cites W2957414648 @default.
- W4308456711 cites W2963091558 @default.
- W4308456711 cites W2963529609 @default.
- W4308456711 cites W2963604034 @default.
- W4308456711 cites W2963868681 @default.
- W4308456711 cites W2979600871 @default.
- W4308456711 cites W2996290406 @default.
- W4308456711 cites W2997217064 @default.
- W4308456711 cites W2997286550 @default.
- W4308456711 cites W2999580839 @default.
- W4308456711 cites W3008258421 @default.
- W4308456711 cites W3023282579 @default.
- W4308456711 cites W3034684132 @default.
- W4308456711 cites W3044711955 @default.
- W4308456711 cites W3046240927 @default.
- W4308456711 cites W3049318984 @default.
- W4308456711 cites W3082604781 @default.
- W4308456711 cites W3082624664 @default.
- W4308456711 cites W3090492687 @default.
- W4308456711 cites W3091342696 @default.
- W4308456711 cites W3091630951 @default.
- W4308456711 cites W3092344722 @default.
- W4308456711 cites W3104061658 @default.
- W4308456711 cites W3104979525 @default.
- W4308456711 cites W3106168076 @default.
- W4308456711 cites W3108718921 @default.
- W4308456711 cites W3161727022 @default.
- W4308456711 cites W3164098653 @default.
- W4308456711 cites W3164631742 @default.
- W4308456711 cites W3174565742 @default.
- W4308456711 cites W3175515048 @default.
- W4308456711 cites W3177004386 @default.
- W4308456711 cites W3187378100 @default.
- W4308456711 cites W3195814479 @default.
- W4308456711 cites W3199502724 @default.
- W4308456711 cites W3199543531 @default.
- W4308456711 cites W3199914841 @default.
- W4308456711 cites W3200027277 @default.
- W4308456711 cites W3202263958 @default.
- W4308456711 cites W3203497085 @default.
- W4308456711 cites W3203507611 @default.
- W4308456711 cites W3204166336 @default.
- W4308456711 cites W3204372962 @default.
- W4308456711 cites W3204643350 @default.
- W4308456711 cites W3204995672 @default.
- W4308456711 cites W3209182117 @default.
- W4308456711 cites W3210073375 @default.
- W4308456711 cites W3210532697 @default.
- W4308456711 cites W4214542306 @default.
- W4308456711 cites W4220963330 @default.
- W4308456711 cites W4315490105 @default.
- W4308456711 cites W4362603432 @default.
- W4308456711 doi "https://doi.org/10.1007/s11633-022-1371-y" @default.
- W4308456711 hasPublicationYear "2022" @default.
- W4308456711 type Work @default.
- W4308456711 citedByCount "13" @default.
- W4308456711 countsByYear W43084567112022 @default.
- W4308456711 countsByYear W43084567112023 @default.
- W4308456711 crossrefType "journal-article" @default.
- W4308456711 hasAuthorship W4308456711A5001254143 @default.
- W4308456711 hasAuthorship W4308456711A5001285878 @default.
- W4308456711 hasAuthorship W4308456711A5050524397 @default.
- W4308456711 hasAuthorship W4308456711A5056294284 @default.
- W4308456711 hasAuthorship W4308456711A5063072430 @default.
- W4308456711 hasAuthorship W4308456711A5078276127 @default.