FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2793857798> ?p ?o ?g. }

• W2793857798 endingPage "2525" @default.
• W2793857798 startingPage "2513" @default.
• W2793857798 abstract "Automatic assessment of sentiment from visual content has gained considerable attention with the increasing tendency of expressing opinions via images and videos online. This paper investigates the problem of visual sentiment analysis, which involves a high-level abstraction in the recognition process. While most of the current methods focus on improving holistic representations, we aim to utilize the local information, which is inspired by the observation that both the whole image and local regions convey significant sentiment information. We propose a framework to leverage affective regions, where we first use an off-the-shelf objectness tool to generate the candidates, and employ a candidate selection method to remove redundant and noisy proposals. Then, a convolutional neural network (CNN) is connected with each candidate to compute the sentiment scores, and the affective regions are automatically discovered, taking the objectness score as well as the sentiment score into consideration. Finally, the CNN outputs from local regions are aggregated with the whole images to produce the final predictions. Our framework only requires image-level labels, thereby significantly reducing the annotation burden otherwise required for training. This is especially important for sentiment analysis since sentiment can be abstract, and labeling affective regions is too subjective and labor-consuming. Extensive experiments show that the proposed algorithm outperforms the state-of-the-art approaches on eight popular benchmark datasets." @default.
• W2793857798 created "2018-03-29" @default.
• W2793857798 creator A5005084059 @default.
• W2793857798 creator A5037131575 @default.
• W2793857798 creator A5068129380 @default.
• W2793857798 creator A5076466251 @default.
• W2793857798 creator A5086664647 @default.
• W2793857798 creator A5089409678 @default.
• W2793857798 date "2018-09-01" @default.
• W2793857798 modified "2023-10-17" @default.
• W2793857798 title "Visual Sentiment Prediction Based on Automatic Discovery of Affective Regions" @default.
• W2793857798 cites W1536680647 @default.
• W2793857798 cites W1567302070 @default.
• W2793857798 cites W1570050281 @default.
• W2793857798 cites W1849277567 @default.
• W2793857798 cites W1930223417 @default.
• W2793857798 cites W1932624639 @default.
• W2793857798 cites W1950412479 @default.
• W2793857798 cites W1958328135 @default.
• W2793857798 cites W1976344353 @default.
• W2793857798 cites W2003217181 @default.
• W2793857798 cites W2003856922 @default.
• W2793857798 cites W2004236981 @default.
• W2793857798 cites W2009678853 @default.
• W2793857798 cites W2017411072 @default.
• W2793857798 cites W2046682605 @default.
• W2793857798 cites W2051308385 @default.
• W2793857798 cites W2056553798 @default.
• W2793857798 cites W2063948594 @default.
• W2793857798 cites W2066624635 @default.
• W2793857798 cites W2074356411 @default.
• W2793857798 cites W2075456404 @default.
• W2793857798 cites W2075953807 @default.
• W2793857798 cites W2078861472 @default.
• W2793857798 cites W2085940040 @default.
• W2793857798 cites W2086399953 @default.
• W2793857798 cites W2102605133 @default.
• W2793857798 cites W2104446196 @default.
• W2793857798 cites W2108598243 @default.
• W2793857798 cites W2110700950 @default.
• W2793857798 cites W2118526556 @default.
• W2793857798 cites W2118615399 @default.
• W2793857798 cites W2121947440 @default.
• W2793857798 cites W2124801089 @default.
• W2793857798 cites W2129305389 @default.
• W2793857798 cites W2147800946 @default.
• W2793857798 cites W2153049579 @default.
• W2793857798 cites W2153635508 @default.
• W2793857798 cites W2162745601 @default.
• W2793857798 cites W2183182206 @default.
• W2793857798 cites W2194775991 @default.
• W2793857798 cites W2241295367 @default.
• W2793857798 cites W2293236424 @default.
• W2793857798 cites W2497039038 @default.
• W2793857798 cites W2499468060 @default.
• W2793857798 cites W2513550067 @default.
• W2793857798 cites W2517991028 @default.
• W2793857798 cites W2519080876 @default.
• W2793857798 cites W2525668096 @default.
• W2793857798 cites W2531468424 @default.
• W2793857798 cites W2552972371 @default.
• W2793857798 cites W2570829410 @default.
• W2793857798 cites W2618530766 @default.
• W2793857798 cites W2741561025 @default.
• W2793857798 cites W2741630455 @default.
• W2793857798 cites W2766251611 @default.
• W2793857798 cites W2963037989 @default.
• W2793857798 cites W2964167669 @default.
• W2793857798 cites W4205184193 @default.
• W2793857798 cites W56385144 @default.
• W2793857798 cites W639708223 @default.
• W2793857798 cites W7746136 @default.
• W2793857798 cites W874179280 @default.
• W2793857798 doi "https://doi.org/10.1109/tmm.2018.2803520" @default.
• W2793857798 hasPublicationYear "2018" @default.
• W2793857798 type Work @default.
• W2793857798 sameAs 2793857798 @default.
• W2793857798 citedByCount "110" @default.
• W2793857798 countsByYear W27938577982018 @default.
• W2793857798 countsByYear W27938577982019 @default.
• W2793857798 countsByYear W27938577982020 @default.
• W2793857798 countsByYear W27938577982021 @default.
• W2793857798 countsByYear W27938577982022 @default.
• W2793857798 countsByYear W27938577982023 @default.
• W2793857798 crossrefType "journal-article" @default.
• W2793857798 hasAuthorship W2793857798A5005084059 @default.
• W2793857798 hasAuthorship W2793857798A5037131575 @default.
• W2793857798 hasAuthorship W2793857798A5068129380 @default.
• W2793857798 hasAuthorship W2793857798A5076466251 @default.
• W2793857798 hasAuthorship W2793857798A5086664647 @default.
• W2793857798 hasAuthorship W2793857798A5089409678 @default.
• W2793857798 hasBestOaLocation W27938577982 @default.
• W2793857798 hasConcept C111472728 @default.
• W2793857798 hasConcept C111919701 @default.
• W2793857798 hasConcept C119857082 @default.
• W2793857798 hasConcept C124304363 @default.
• W2793857798 hasConcept C13280743 @default.
• W2793857798 hasConcept C138885662 @default.

• next