Metraipolis › archive › dc_b2a4f5847747
Vision-Guided Text Prompt Tuning for Multimodal Sentiment Analysis — arXiv:2609.06497
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06497
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:12:40.118Z
- SHA-256 of the archived text
fbdedb45ce3c7d7a887a46dbc25ad4ccbe6fcd234911f7b1482978cf29177225- Stable URL of this page
https://metraipolis.com/documento/dc_b2a4f5847747
How to cite
Vision-Guided Text Prompt Tuning for Multimodal Sentiment Analysis — arXiv:2609.06497 — arXiv (en), https://arxiv.org/abs/2609.06497 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2a4f5847747 (Metraipolis archive dc_b2a4f5847747, sha256 fbdedb45ce3c7d7a887a46dbc25ad4ccbe6fcd234911f7b1482978cf29177225)
BibTeX
@misc{dcb2a4f5847747,
title = {Vision-Guided Text Prompt Tuning for Multimodal Sentiment Analysis — arXiv:2609.06497},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06497},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2a4f5847747; sha256 fbdedb45ce3c7d7a887a46dbc25ad4ccbe6fcd234911f7b1482978cf29177225},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06497. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal sentiment analysis requires effective modeling of both verbal semantics and non-verbal affective cues. A central challenge is to calibrate text-centered sentiment understanding with visual facial evidence in a controlled, adaptive, and parameter-efficient manner. Text usually serves as the semantic anchor, whereas visual cues provide complementary evidence for ambiguous or implicit expressions; however, indiscriminate fusion may introduce visual noise and distort textual semantics. Moreover, fully fine-tuning large visual and textual encoders is costly and prone to overfitting on limited and scenario-dependent MSA benchmarks. To address these issues, we propose Vision-Guided Text Prompt Tuning (VG-TPT), which formulates visual-text sentiment modeling as controllable visual calibration of frozen text representations. VG-TPT injects visual affective cues into a frozen BERT encoder through layer-wise adaptive prompts, rather than relying on late-stage feature fusion or full backbone tuning. A co-guided router composes prompts from a trainable prompt bank according to both the evolving text state and the visual guidance feature, enabling sample-specific and layer-specific modulation. Experiments on CMU-MOSEI and CMU-MOSI show that VG-TPT consistently improves over text-only baselines and achieves competitive or superior performance compared with several full-modality methods, while updating only 2.4M trainable parameters. The code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Multimedia (cs.MM) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.06497 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T14:49:57.418Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).