FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140935183> ?p ?o ?g. }

• W3140935183 abstract "We describe an unsupervised method to detect and segment portions of images of live scenes that, at some point in time, are seen moving as a coherent whole, which we refer to as objects. Our method first partitions the motion field by minimizing the mutual information between segments. Then, it uses the segments to learn object models that can be used for detection in a static image. Static and dynamic models are represented by deep neural networks trained jointly in a bootstrapping strategy, which enables extrapolation to previously unseen objects. While the training process requires motion, the resulting object segmentation network can be used on either static images or videos at inference time. As the volume of seen videos grows, more and more objects are seen moving, priming their detection, which then serves as a regularizer for new objects, turning our method into unsupervised continual learning to segment objects. Our models are compared to the state of the art in both video object segmentation and salient object detection. In the six benchmark datasets tested, our models compare favorably even to those using pixel-level supervision, despite requiring no manual annotation." @default.
• W3140935183 created "2021-04-13" @default.
• W3140935183 creator A5013913342 @default.
• W3140935183 creator A5038328783 @default.
• W3140935183 creator A5058789012 @default.
• W3140935183 date "2020-08-16" @default.
• W3140935183 modified "2023-09-26" @default.
• W3140935183 title "DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping" @default.
• W3140935183 cites W1496571393 @default.
• W3140935183 cites W1497599070 @default.
• W3140935183 cites W1861492603 @default.
• W3140935183 cites W1907877624 @default.
• W3140935183 cites W1941318923 @default.
• W3140935183 cites W1950703464 @default.
• W3140935183 cites W1965301399 @default.
• W3140935183 cites W1977427797 @default.
• W3140935183 cites W1995129256 @default.
• W3140935183 cites W1996326832 @default.
• W3140935183 cites W1999478155 @default.
• W3140935183 cites W2002103521 @default.
• W3140935183 cites W2002574940 @default.
• W3140935183 cites W2002781701 @default.
• W3140935183 cites W2037954058 @default.
• W3140935183 cites W2039313011 @default.
• W3140935183 cites W2047670868 @default.
• W3140935183 cites W2065985528 @default.
• W3140935183 cites W2067191022 @default.
• W3140935183 cites W2076756823 @default.
• W3140935183 cites W2078132377 @default.
• W3140935183 cites W2082869876 @default.
• W3140935183 cites W2086791339 @default.
• W3140935183 cites W2089597841 @default.
• W3140935183 cites W2097099938 @default.
• W3140935183 cites W2100470808 @default.
• W3140935183 cites W2111918405 @default.
• W3140935183 cites W2113708607 @default.
• W3140935183 cites W2118143383 @default.
• W3140935183 cites W2119531662 @default.
• W3140935183 cites W2122423951 @default.
• W3140935183 cites W2123081785 @default.
• W3140935183 cites W2128272608 @default.
• W3140935183 cites W2128340050 @default.
• W3140935183 cites W2131958583 @default.
• W3140935183 cites W2138682569 @default.
• W3140935183 cites W2146103513 @default.
• W3140935183 cites W2161185676 @default.
• W3140935183 cites W2170140722 @default.
• W3140935183 cites W2197046994 @default.
• W3140935183 cites W2201368473 @default.
• W3140935183 cites W2294182682 @default.
• W3140935183 cites W2412782625 @default.
• W3140935183 cites W2470139095 @default.
• W3140935183 cites W2536706996 @default.
• W3140935183 cites W2566030665 @default.
• W3140935183 cites W2737008123 @default.
• W3140935183 cites W2744613561 @default.
• W3140935183 cites W2780708736 @default.
• W3140935183 cites W2789523586 @default.
• W3140935183 cites W2798441772 @default.
• W3140935183 cites W2798823518 @default.
• W3140935183 cites W2890250492 @default.
• W3140935183 cites W2890447039 @default.
• W3140935183 cites W2890707244 @default.
• W3140935183 cites W2895293811 @default.
• W3140935183 cites W2895340898 @default.
• W3140935183 cites W2916743882 @default.
• W3140935183 cites W2943695751 @default.
• W3140935183 cites W2955084925 @default.
• W3140935183 cites W2963032190 @default.
• W3140935183 cites W2963299740 @default.
• W3140935183 cites W2963685207 @default.
• W3140935183 cites W2963782415 @default.
• W3140935183 cites W2963878474 @default.
• W3140935183 cites W2963983744 @default.
• W3140935183 cites W2964352379 @default.
• W3140935183 cites W2964665981 @default.
• W3140935183 cites W2967622921 @default.
• W3140935183 cites W2970275033 @default.
• W3140935183 cites W2970642899 @default.
• W3140935183 cites W2970653639 @default.
• W3140935183 cites W2976230581 @default.
• W3140935183 cites W2981342784 @default.
• W3140935183 cites W3001586682 @default.
• W3140935183 cites W3015218297 @default.
• W3140935183 cites W3046208551 @default.
• W3140935183 cites W3140400178 @default.
• W3140935183 doi "https://doi.org/10.48550/arxiv.2008.07012" @default.
• W3140935183 hasPublicationYear "2020" @default.
• W3140935183 type Work @default.
• W3140935183 sameAs 3140935183 @default.
• W3140935183 citedByCount "0" @default.
• W3140935183 crossrefType "posted-content" @default.
• W3140935183 hasAuthorship W3140935183A5013913342 @default.
• W3140935183 hasAuthorship W3140935183A5038328783 @default.
• W3140935183 hasAuthorship W3140935183A5058789012 @default.
• W3140935183 hasBestOaLocation W31409351831 @default.
• W3140935183 hasConcept C124504099 @default.
• W3140935183 hasConcept C13280743 @default.
• W3140935183 hasConcept C149782125 @default.
• W3140935183 hasConcept C153180895 @default.

• next