A method that decomposes CLIP image and text features into a shared low-rank component and modality-specific sparse components, then uses an attention-weighted soft prompt to guide an LLM for sentiment, emotion, and hateful meme tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Representation Decomposition for Learning Similarity and Contrastness Across Modalities for Affective Computing
A method that decomposes CLIP image and text features into a shared low-rank component and modality-specific sparse components, then uses an attention-weighted soft prompt to guide an LLM for sentiment, emotion, and hateful meme tasks.