FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971765953> ?p ?o ?g. }

• W2971765953 endingPage "1371" @default.
• W2971765953 startingPage "1358" @default.
• W2971765953 abstract "Automatic assessment of sentiment from visual content has gained considerable attention with the increasing tendency of expressing opinions online. In this paper, we solve the problem of visual sentiment analysis, which is challenging due to the high-level abstraction in the recognition process. Existing methods based on convolutional neural networks learn sentiment representations from the holistic image, despite the fact that different image regions can have different influence on the evoked sentiment. In this paper, we introduce a weakly supervised coupled convolutional network (WSCNet). Our method is dedicated to automatically selecting relevant soft proposals given weak annotations (e.g., global image labels), thereby significantly reducing the annotation burden, and encompasses the following contributions. First, the proposed WSCNet detects a sentiment-specific soft map by training a fully convolutional network with the cross spatial pooling strategy in the detection branch. Second, both the holistic and localized information are utilized by coupling the sentiment map with deep features as semantic vector in the classification branch. The sentiment detection and classification branches are integrated into a unified deep framework optimized in an end-to-end manner. Extensive experiments demonstrate that the proposed WSCNet outperforms the state-of-the-art results on seven benchmark datasets." @default.
• W2971765953 created "2019-09-12" @default.
• W2971765953 creator A5005084059 @default.
• W2971765953 creator A5037131575 @default.
• W2971765953 creator A5067850699 @default.
• W2971765953 creator A5068129380 @default.
• W2971765953 creator A5086664647 @default.
• W2971765953 creator A5089409678 @default.
• W2971765953 date "2020-05-01" @default.
• W2971765953 modified "2023-10-14" @default.
• W2971765953 title "WSCNet: Weakly Supervised Coupled Networks for Visual Sentiment Classification and Detection" @default.
• W2971765953 cites W1849277567 @default.
• W2971765953 cites W1938425378 @default.
• W2971765953 cites W1950412479 @default.
• W2971765953 cites W1976344353 @default.
• W2971765953 cites W1994488211 @default.
• W2971765953 cites W1995270501 @default.
• W2971765953 cites W2003856922 @default.
• W2971765953 cites W2016016818 @default.
• W2971765953 cites W2017481703 @default.
• W2971765953 cites W2028979196 @default.
• W2971765953 cites W2046682605 @default.
• W2971765953 cites W2051308385 @default.
• W2971765953 cites W2056553798 @default.
• W2971765953 cites W2063948594 @default.
• W2971765953 cites W2066624635 @default.
• W2971765953 cites W2074356411 @default.
• W2971765953 cites W2075456404 @default.
• W2971765953 cites W2097726431 @default.
• W2971765953 cites W2108598243 @default.
• W2971765953 cites W2125387256 @default.
• W2971765953 cites W2128272608 @default.
• W2971765953 cites W2133324800 @default.
• W2971765953 cites W2143668817 @default.
• W2971765953 cites W2153049579 @default.
• W2971765953 cites W2153635508 @default.
• W2971765953 cites W2169949291 @default.
• W2971765953 cites W2194775991 @default.
• W2971765953 cites W2212216676 @default.
• W2971765953 cites W2248800885 @default.
• W2971765953 cites W2295107390 @default.
• W2971765953 cites W2306853856 @default.
• W2971765953 cites W2342491128 @default.
• W2971765953 cites W2358876993 @default.
• W2971765953 cites W2403015048 @default.
• W2971765953 cites W2412155161 @default.
• W2971765953 cites W2512351403 @default.
• W2971765953 cites W2513550067 @default.
• W2971765953 cites W2517991028 @default.
• W2971765953 cites W2525668096 @default.
• W2971765953 cites W2531468424 @default.
• W2971765953 cites W2538855059 @default.
• W2971765953 cites W2552972371 @default.
• W2971765953 cites W2559348937 @default.
• W2971765953 cites W2600144439 @default.
• W2971765953 cites W2604758567 @default.
• W2971765953 cites W2617085328 @default.
• W2971765953 cites W2618530766 @default.
• W2971765953 cites W2738853914 @default.
• W2971765953 cites W2739474071 @default.
• W2971765953 cites W2740046088 @default.
• W2971765953 cites W2741561025 @default.
• W2971765953 cites W2741630455 @default.
• W2971765953 cites W2766094568 @default.
• W2971765953 cites W2766154025 @default.
• W2971765953 cites W2791779647 @default.
• W2971765953 cites W2793560625 @default.
• W2971765953 cites W2793857798 @default.
• W2971765953 cites W2798322248 @default.
• W2971765953 cites W2798376494 @default.
• W2971765953 cites W2798503473 @default.
• W2971765953 cites W2883554151 @default.
• W2971765953 cites W2908347420 @default.
• W2971765953 cites W2914885528 @default.
• W2971765953 cites W2962858109 @default.
• W2971765953 cites W2963503775 @default.
• W2971765953 cites W2963603913 @default.
• W2971765953 cites W2963795442 @default.
• W2971765953 cites W2964167669 @default.
• W2971765953 cites W2964274719 @default.
• W2971765953 cites W2981669886 @default.
• W2971765953 cites W2981843773 @default.
• W2971765953 cites W3080873008 @default.
• W2971765953 cites W4243553907 @default.
• W2971765953 cites W4249467711 @default.
• W2971765953 cites W639708223 @default.
• W2971765953 doi "https://doi.org/10.1109/tmm.2019.2939744" @default.
• W2971765953 hasPublicationYear "2020" @default.
• W2971765953 type Work @default.
• W2971765953 sameAs 2971765953 @default.
• W2971765953 citedByCount "46" @default.
• W2971765953 countsByYear W29717659532020 @default.
• W2971765953 countsByYear W29717659532021 @default.
• W2971765953 countsByYear W29717659532022 @default.
• W2971765953 countsByYear W29717659532023 @default.
• W2971765953 crossrefType "journal-article" @default.
• W2971765953 hasAuthorship W2971765953A5005084059 @default.
• W2971765953 hasAuthorship W2971765953A5037131575 @default.

• next