Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304080405> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4304080405 abstract "With the popularity of instant messaging applications, online chatting plays an essential role in our daily life. The prevailing use of stickers to express emotions in online chatting leads to the necessity of multimodal sticker emotion recognition. Considering the lack of sticker emotion data, we collect a large-scale sticker emotion recognition dataset named SER30K. It consists of a total of 1,887 sticker themes with total 30,739 sticker images. Some commonly used images, such as realistic images and facial expression images, have been well studied in the field of emotion analysis. However, it is still challenging to understand the emotion of sticker images. Since the characteristics in stickers from the same theme are similar, we can only accurately predict the emotion by capturing the local information (e.g., expressions, poses) and understanding the global information (e.g., relations among objects). To tackle this challenge, we propose a LOcal Re-Attention multimodal network (LORA) to learn sticker emotions in an end-to-end manner. Different from previous approaches using convolutional neural networks, LORA employs the vision transformer to extract visual features, leading to better capture the global relations. In addition, we design a local re-attention module to focus on important region information. Then a simple but efficient modal fusion module combines visual and language features. Extensive experiments are performed on the SER30K and other emotion recognition datasets, demonstrating the effectiveness of our proposed method. Our code, model and dataset are released on https://github.com/nku-shengzheliu/SER30K." @default.
- W4304080405 created "2022-10-10" @default.
- W4304080405 creator A5006651636 @default.
- W4304080405 creator A5029562842 @default.
- W4304080405 creator A5089409678 @default.
- W4304080405 date "2022-10-10" @default.
- W4304080405 modified "2023-09-27" @default.
- W4304080405 title "SER30K" @default.
- W4304080405 cites W2074356411 @default.
- W4304080405 cites W2075456404 @default.
- W4304080405 cites W2525668096 @default.
- W4304080405 cites W2604769266 @default.
- W4304080405 cites W2732026016 @default.
- W4304080405 cites W2740046088 @default.
- W4304080405 cites W2741630455 @default.
- W4304080405 cites W2770912167 @default.
- W4304080405 cites W2793857798 @default.
- W4304080405 cites W2798503473 @default.
- W4304080405 cites W2887175137 @default.
- W4304080405 cites W2951937667 @default.
- W4304080405 cites W2958208506 @default.
- W4304080405 cites W2963066927 @default.
- W4304080405 cites W2981669886 @default.
- W4304080405 cites W3095024162 @default.
- W4304080405 cites W3098061148 @default.
- W4304080405 cites W3108525755 @default.
- W4304080405 cites W3131500599 @default.
- W4304080405 cites W3187313248 @default.
- W4304080405 cites W3197507611 @default.
- W4304080405 cites W3206577156 @default.
- W4304080405 doi "https://doi.org/10.1145/3503161.3548407" @default.
- W4304080405 hasPublicationYear "2022" @default.
- W4304080405 type Work @default.
- W4304080405 citedByCount "1" @default.
- W4304080405 countsByYear W43040804052023 @default.
- W4304080405 crossrefType "proceedings-article" @default.
- W4304080405 hasAuthorship W4304080405A5006651636 @default.
- W4304080405 hasAuthorship W4304080405A5029562842 @default.
- W4304080405 hasAuthorship W4304080405A5089409678 @default.
- W4304080405 hasConcept C120665830 @default.
- W4304080405 hasConcept C121332964 @default.
- W4304080405 hasConcept C136764020 @default.
- W4304080405 hasConcept C154945302 @default.
- W4304080405 hasConcept C15744967 @default.
- W4304080405 hasConcept C192209626 @default.
- W4304080405 hasConcept C195704467 @default.
- W4304080405 hasConcept C206310091 @default.
- W4304080405 hasConcept C2777438025 @default.
- W4304080405 hasConcept C2780586970 @default.
- W4304080405 hasConcept C33566652 @default.
- W4304080405 hasConcept C41008148 @default.
- W4304080405 hasConcept C77805123 @default.
- W4304080405 hasConcept C81363708 @default.
- W4304080405 hasConceptScore W4304080405C120665830 @default.
- W4304080405 hasConceptScore W4304080405C121332964 @default.
- W4304080405 hasConceptScore W4304080405C136764020 @default.
- W4304080405 hasConceptScore W4304080405C154945302 @default.
- W4304080405 hasConceptScore W4304080405C15744967 @default.
- W4304080405 hasConceptScore W4304080405C192209626 @default.
- W4304080405 hasConceptScore W4304080405C195704467 @default.
- W4304080405 hasConceptScore W4304080405C206310091 @default.
- W4304080405 hasConceptScore W4304080405C2777438025 @default.
- W4304080405 hasConceptScore W4304080405C2780586970 @default.
- W4304080405 hasConceptScore W4304080405C33566652 @default.
- W4304080405 hasConceptScore W4304080405C41008148 @default.
- W4304080405 hasConceptScore W4304080405C77805123 @default.
- W4304080405 hasConceptScore W4304080405C81363708 @default.
- W4304080405 hasLocation W43040804051 @default.
- W4304080405 hasOpenAccess W4304080405 @default.
- W4304080405 hasPrimaryLocation W43040804051 @default.
- W4304080405 hasRelatedWork W2014713986 @default.
- W4304080405 hasRelatedWork W3118234491 @default.
- W4304080405 hasRelatedWork W3170928364 @default.
- W4304080405 hasRelatedWork W3180630304 @default.
- W4304080405 hasRelatedWork W3186847174 @default.
- W4304080405 hasRelatedWork W4226363307 @default.
- W4304080405 hasRelatedWork W4313182991 @default.
- W4304080405 hasRelatedWork W4316021163 @default.
- W4304080405 hasRelatedWork W4319309783 @default.
- W4304080405 hasRelatedWork W4380854332 @default.
- W4304080405 isParatext "false" @default.
- W4304080405 isRetracted "false" @default.
- W4304080405 workType "article" @default.