Matches in SemOpenAlex for { <https://semopenalex.org/work/W2739384021> ?p ?o ?g. }
- W2739384021 abstract "With recent innovations in dense image captioning, it is now possible to describe every object of the scene with a caption while objects are determined by bounding boxes. However, interpretation of such an output is not trivial due to the existence of many overlapping bounding boxes. Furthermore, in current captioning frameworks, the user is not able to involve personal preferences to exclude out of interest areas. In this paper, we propose a novel hybrid deep learning architecture for interactive region segmentation and captioning where the user is able to specify an arbitrary region of the image that should be processed. To this end, a dedicated Fully Convolutional Network (FCN) named Lyncean FCN (LFCN) is trained using our special training data to isolate the User Intention Region (UIR) as the output of an efficient segmentation. In parallel, a dense image captioning model is utilized to provide a wide variety of captions for that region. Then, the UIR will be explained with the caption of the best match bounding box. To the best of our knowledge, this is the first work that provides such a comprehensive output. Our experiments show the superiority of the proposed approach over state-of-the-art interactive segmentation methods on several well-known datasets. In addition, replacement of the bounding boxes with the result of the interactive segmentation leads to a better understanding of the dense image captioning output as well as accuracy enhancement for the object detection in terms of Intersection over Union (IoU)." @default.
- W2739384021 created "2017-07-31" @default.
- W2739384021 creator A5013677971 @default.
- W2739384021 creator A5075931354 @default.
- W2739384021 creator A5086192148 @default.
- W2739384021 date "2017-07-26" @default.
- W2739384021 modified "2023-09-27" @default.
- W2739384021 title "Deep Interactive Region Segmentation and Captioning" @default.
- W2739384021 cites W1514535095 @default.
- W2739384021 cites W1527575280 @default.
- W2739384021 cites W1613438798 @default.
- W2739384021 cites W179875071 @default.
- W2739384021 cites W1849277567 @default.
- W2739384021 cites W1850742715 @default.
- W2739384021 cites W1895577753 @default.
- W2739384021 cites W1895989618 @default.
- W2739384021 cites W1903029394 @default.
- W2739384021 cites W1905829557 @default.
- W2739384021 cites W1905882502 @default.
- W2739384021 cites W1931639407 @default.
- W2739384021 cites W1947481528 @default.
- W2739384021 cites W1967268147 @default.
- W2739384021 cites W1971129545 @default.
- W2739384021 cites W2031489346 @default.
- W2739384021 cites W2055224458 @default.
- W2739384021 cites W2062955551 @default.
- W2739384021 cites W2064675550 @default.
- W2739384021 cites W2088049833 @default.
- W2739384021 cites W2097117768 @default.
- W2739384021 cites W2099109083 @default.
- W2739384021 cites W2102605133 @default.
- W2739384021 cites W2109815552 @default.
- W2739384021 cites W2111077768 @default.
- W2739384021 cites W2112796928 @default.
- W2739384021 cites W2121927366 @default.
- W2739384021 cites W2121947440 @default.
- W2739384021 cites W2124351162 @default.
- W2739384021 cites W2125378844 @default.
- W2739384021 cites W2125637308 @default.
- W2739384021 cites W2137918516 @default.
- W2739384021 cites W2143449221 @default.
- W2739384021 cites W2159243025 @default.
- W2739384021 cites W2161969291 @default.
- W2739384021 cites W2163096274 @default.
- W2739384021 cites W2168356304 @default.
- W2739384021 cites W2168555635 @default.
- W2739384021 cites W2169551590 @default.
- W2739384021 cites W2194775991 @default.
- W2739384021 cites W2210744894 @default.
- W2739384021 cites W2251583212 @default.
- W2739384021 cites W2277195237 @default.
- W2739384021 cites W2294819727 @default.
- W2739384021 cites W2337429362 @default.
- W2739384021 cites W2950577311 @default.
- W2739384021 cites W2951548327 @default.
- W2739384021 cites W2952723517 @default.
- W2739384021 cites W2953022248 @default.
- W2739384021 cites W2953106684 @default.
- W2739384021 cites W2962706528 @default.
- W2739384021 cites W2963542991 @default.
- W2739384021 cites W2963758027 @default.
- W2739384021 cites W2964288706 @default.
- W2739384021 cites W603908379 @default.
- W2739384021 cites W62621907 @default.
- W2739384021 cites W68733909 @default.
- W2739384021 cites W8316075 @default.
- W2739384021 hasPublicationYear "2017" @default.
- W2739384021 type Work @default.
- W2739384021 sameAs 2739384021 @default.
- W2739384021 citedByCount "1" @default.
- W2739384021 countsByYear W27393840212018 @default.
- W2739384021 crossrefType "posted-content" @default.
- W2739384021 hasAuthorship W2739384021A5013677971 @default.
- W2739384021 hasAuthorship W2739384021A5075931354 @default.
- W2739384021 hasAuthorship W2739384021A5086192148 @default.
- W2739384021 hasConcept C108583219 @default.
- W2739384021 hasConcept C115961682 @default.
- W2739384021 hasConcept C124504099 @default.
- W2739384021 hasConcept C127413603 @default.
- W2739384021 hasConcept C146978453 @default.
- W2739384021 hasConcept C147037132 @default.
- W2739384021 hasConcept C154945302 @default.
- W2739384021 hasConcept C157657479 @default.
- W2739384021 hasConcept C2781238097 @default.
- W2739384021 hasConcept C31972630 @default.
- W2739384021 hasConcept C41008148 @default.
- W2739384021 hasConcept C63584917 @default.
- W2739384021 hasConcept C64543145 @default.
- W2739384021 hasConcept C81363708 @default.
- W2739384021 hasConcept C89600930 @default.
- W2739384021 hasConceptScore W2739384021C108583219 @default.
- W2739384021 hasConceptScore W2739384021C115961682 @default.
- W2739384021 hasConceptScore W2739384021C124504099 @default.
- W2739384021 hasConceptScore W2739384021C127413603 @default.
- W2739384021 hasConceptScore W2739384021C146978453 @default.
- W2739384021 hasConceptScore W2739384021C147037132 @default.
- W2739384021 hasConceptScore W2739384021C154945302 @default.
- W2739384021 hasConceptScore W2739384021C157657479 @default.
- W2739384021 hasConceptScore W2739384021C2781238097 @default.
- W2739384021 hasConceptScore W2739384021C31972630 @default.