自由职业者
发表于 2025-3-23 11:20:47
http://reply.papertrans.cn/67/6697/669625/669625_11.png
Implicit
发表于 2025-3-23 15:26:08
WConF: Weighted Contrastive Fusion for Multimodal Sentiment Analysisective unimodal representations to facilitate multimodal fusion, which mainly contain two parts of information: modality-common and modality-specific information. However, previous work does not consider the sentiment span information between different samples during the fusion process. In this pape
Kaleidoscope
发表于 2025-3-23 21:44:20
http://reply.papertrans.cn/67/6697/669625/669625_13.png
Bereavement
发表于 2025-3-24 00:44:17
http://reply.papertrans.cn/67/6697/669625/669625_14.png
高兴一回
发表于 2025-3-24 04:04:59
Emotion Cause Extraction in Conversations with Response Graphing, that reflect the causes of a certain type of emotion embedded in a target utterance in the conversation history. Since conversations are interactions between individuals, where one responds to the content from other participants, it is crucial to identify the potential responsive relations among u
immunity
发表于 2025-3-24 09:56:53
http://reply.papertrans.cn/67/6697/669625/669625_16.png
退潮
发表于 2025-3-24 14:43:27
CETA: Context-Enhanced and Target-Aware Hateful Meme Inference Methodfor comprehensive reasoning. Though great efforts have been made, existing detection methods overlook the specific target of hateful meme, resulting in inadequate meme comprehension and hindering performance. In this paper, we propose Context-Enhanced and Target-Aware Hateful Meme Inference Method (
催眠药
发表于 2025-3-24 17:46:39
A Survey of Zero-Shot Stance Detection Neither}. As an important research problem, reliance on high-quality annotated data poses a significant challenge. However, in the real world, with the rapid development of social media, it is impossible to annotate the massive amount of text on diverse topics, a universal framework for stance dete
渐强
发表于 2025-3-24 20:50:16
http://reply.papertrans.cn/67/6697/669625/669625_19.png
1FAWN
发表于 2025-3-24 23:11:50
http://reply.papertrans.cn/67/6697/669625/669625_20.png