Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318829343> ?p ?o ?g. }
- W4318829343 endingPage "365" @default.
- W4318829343 startingPage "348" @default.
- W4318829343 abstract "Video Object Segmentation is a fundamental task in computer vision that aims at pixel-wise tracking of one or multiple foreground objects within a video sequence. This task is challenging due to real-world requirements such as handling unconstrained object and camera motion, occlusion, fast motion, and motion blur. Recently, methods utilizing RNNs have been successful in accurately and efficiently segmenting the target objects as RNNs can effectively memorize the object of interest and compute the spatiotemporal features which are useful in processing the visual sequential data. However, they have limitations such as lower segmentation accuracy in longer sequences. In this paper, we expand our previous work to develop a hybrid architecture that successfully eliminates some of these challenges by employing additional correspondence matching information, followed by extensively exploring the impact of various architectural designs. Our experiment results on YouTubeVOS dataset confirm the efficacy of our proposed architecture by obtaining an improvement of about 12pp on YoutTubeVOS compared to RNN-based baselines without a considerable increase in the computational costs." @default.
- W4318829343 created "2023-02-02" @default.
- W4318829343 creator A5019899855 @default.
- W4318829343 creator A5029509133 @default.
- W4318829343 creator A5073903451 @default.
- W4318829343 creator A5088285773 @default.
- W4318829343 date "2023-01-01" @default.
- W4318829343 modified "2023-10-16" @default.
- W4318829343 title "Rethinking RNN-Based Video Object Segmentation" @default.
- W4318829343 cites W1496571393 @default.
- W4318829343 cites W1566256432 @default.
- W4318829343 cites W1901129140 @default.
- W4318829343 cites W1955404912 @default.
- W4318829343 cites W1966136723 @default.
- W4318829343 cites W2108598243 @default.
- W4318829343 cites W2113708607 @default.
- W4318829343 cites W2131774270 @default.
- W4318829343 cites W2136016850 @default.
- W4318829343 cites W2194775991 @default.
- W4318829343 cites W2322739735 @default.
- W4318829343 cites W2470139095 @default.
- W4318829343 cites W2564998703 @default.
- W4318829343 cites W2598666589 @default.
- W4318829343 cites W2610147486 @default.
- W4318829343 cites W2799157347 @default.
- W4318829343 cites W2889986507 @default.
- W4318829343 cites W2916797271 @default.
- W4318829343 cites W2921536280 @default.
- W4318829343 cites W2962825871 @default.
- W4318829343 cites W2963091558 @default.
- W4318829343 cites W2963230407 @default.
- W4318829343 cites W2963253279 @default.
- W4318829343 cites W2963503215 @default.
- W4318829343 cites W2963732700 @default.
- W4318829343 cites W2964343881 @default.
- W4318829343 cites W2990205821 @default.
- W4318829343 cites W3035042565 @default.
- W4318829343 cites W3094664776 @default.
- W4318829343 cites W3097065222 @default.
- W4318829343 cites W3098547059 @default.
- W4318829343 cites W3106773277 @default.
- W4318829343 cites W3108086282 @default.
- W4318829343 cites W3109908659 @default.
- W4318829343 cites W3132765014 @default.
- W4318829343 cites W3162231969 @default.
- W4318829343 cites W4212977191 @default.
- W4318829343 cites W589665618 @default.
- W4318829343 doi "https://doi.org/10.1007/978-3-031-25477-2_16" @default.
- W4318829343 hasPublicationYear "2023" @default.
- W4318829343 type Work @default.
- W4318829343 citedByCount "0" @default.
- W4318829343 crossrefType "book-chapter" @default.
- W4318829343 hasAuthorship W4318829343A5019899855 @default.
- W4318829343 hasAuthorship W4318829343A5029509133 @default.
- W4318829343 hasAuthorship W4318829343A5073903451 @default.
- W4318829343 hasAuthorship W4318829343A5088285773 @default.
- W4318829343 hasConcept C104114177 @default.
- W4318829343 hasConcept C105795698 @default.
- W4318829343 hasConcept C127413603 @default.
- W4318829343 hasConcept C147168706 @default.
- W4318829343 hasConcept C154945302 @default.
- W4318829343 hasConcept C165064840 @default.
- W4318829343 hasConcept C201995342 @default.
- W4318829343 hasConcept C202474056 @default.
- W4318829343 hasConcept C2780451532 @default.
- W4318829343 hasConcept C2781238097 @default.
- W4318829343 hasConcept C31972630 @default.
- W4318829343 hasConcept C33923547 @default.
- W4318829343 hasConcept C41008148 @default.
- W4318829343 hasConcept C50644808 @default.
- W4318829343 hasConcept C89600930 @default.
- W4318829343 hasConceptScore W4318829343C104114177 @default.
- W4318829343 hasConceptScore W4318829343C105795698 @default.
- W4318829343 hasConceptScore W4318829343C127413603 @default.
- W4318829343 hasConceptScore W4318829343C147168706 @default.
- W4318829343 hasConceptScore W4318829343C154945302 @default.
- W4318829343 hasConceptScore W4318829343C165064840 @default.
- W4318829343 hasConceptScore W4318829343C201995342 @default.
- W4318829343 hasConceptScore W4318829343C202474056 @default.
- W4318829343 hasConceptScore W4318829343C2780451532 @default.
- W4318829343 hasConceptScore W4318829343C2781238097 @default.
- W4318829343 hasConceptScore W4318829343C31972630 @default.
- W4318829343 hasConceptScore W4318829343C33923547 @default.
- W4318829343 hasConceptScore W4318829343C41008148 @default.
- W4318829343 hasConceptScore W4318829343C50644808 @default.
- W4318829343 hasConceptScore W4318829343C89600930 @default.
- W4318829343 hasLocation W43188293431 @default.
- W4318829343 hasOpenAccess W4318829343 @default.
- W4318829343 hasPrimaryLocation W43188293431 @default.
- W4318829343 hasRelatedWork W1487175407 @default.
- W4318829343 hasRelatedWork W2019566805 @default.
- W4318829343 hasRelatedWork W2343908003 @default.
- W4318829343 hasRelatedWork W2375636617 @default.
- W4318829343 hasRelatedWork W2383464976 @default.
- W4318829343 hasRelatedWork W2385949326 @default.
- W4318829343 hasRelatedWork W2534746541 @default.
- W4318829343 hasRelatedWork W2789220062 @default.
- W4318829343 hasRelatedWork W1967061043 @default.