Towards Real-World Stickers Use: A New Dataset for Multi-Tag Sticker Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929387015766016 |
|---|---|
| author | Wang, Bingbing Liang, Bin Feng, Chun-Mei Zuo, Wangmeng Bai, Zhixin Huang, Shijue Wong, Kam-Fai Zeng, Xi Xu, Ruifeng |
| author_facet | Wang, Bingbing Liang, Bin Feng, Chun-Mei Zuo, Wangmeng Bai, Zhixin Huang, Shijue Wong, Kam-Fai Zeng, Xi Xu, Ruifeng |
| contents | In real-world conversations, the diversity and ambiguity of stickers often lead to varied interpretations based on the context, necessitating the requirement for comprehensively understanding stickers and supporting multi-tagging. To address this challenge, we introduce StickerTAG, the first multi-tag sticker dataset comprising a collected tag set with 461 tags and 13,571 sticker-tag pairs, designed to provide a deeper understanding of stickers. Recognizing multiple tags for stickers becomes particularly challenging due to sticker tags usually are fine-grained attribute aware. Hence, we propose an Attentive Attribute-oriented Prompt Learning method, ie, Att$^2$PL, to capture informative features of stickers in a fine-grained manner to better differentiate tags. Specifically, we first apply an Attribute-oriented Description Generation (ADG) module to obtain the description for stickers from four attributes. Then, a Local Re-attention (LoR) module is designed to perceive the importance of local information. Finally, we use prompt learning to guide the recognition process and adopt confidence penalty optimization to penalize the confident output distribution. Extensive experiments show that our method achieves encouraging results for all commonly used metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05428 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Real-World Stickers Use: A New Dataset for Multi-Tag Sticker Recognition Wang, Bingbing Liang, Bin Feng, Chun-Mei Zuo, Wangmeng Bai, Zhixin Huang, Shijue Wong, Kam-Fai Zeng, Xi Xu, Ruifeng Multimedia In real-world conversations, the diversity and ambiguity of stickers often lead to varied interpretations based on the context, necessitating the requirement for comprehensively understanding stickers and supporting multi-tagging. To address this challenge, we introduce StickerTAG, the first multi-tag sticker dataset comprising a collected tag set with 461 tags and 13,571 sticker-tag pairs, designed to provide a deeper understanding of stickers. Recognizing multiple tags for stickers becomes particularly challenging due to sticker tags usually are fine-grained attribute aware. Hence, we propose an Attentive Attribute-oriented Prompt Learning method, ie, Att$^2$PL, to capture informative features of stickers in a fine-grained manner to better differentiate tags. Specifically, we first apply an Attribute-oriented Description Generation (ADG) module to obtain the description for stickers from four attributes. Then, a Local Re-attention (LoR) module is designed to perceive the importance of local information. Finally, we use prompt learning to guide the recognition process and adopt confidence penalty optimization to penalize the confident output distribution. Extensive experiments show that our method achieves encouraging results for all commonly used metrics. |
| title | Towards Real-World Stickers Use: A New Dataset for Multi-Tag Sticker Recognition |
| topic | Multimedia |
| url | https://arxiv.org/abs/2403.05428 |