Metraipolis › archive › dc_6e8769bb3d39
PI-MLLM: Psychophysics-Inspired Multimodal Large Language Model for Oddly Satisfying Video Emotion Analysis — arXiv:2610.28264
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.28264
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:08:22.394Z
- SHA-256 of the archived text
88c23be962d3122a6fe07b443cb0091b361cf9e21b948fd7fedaa53621e041b6- Stable URL of this page
https://metraipolis.com/documento/dc_6e8769bb3d39
How to cite
PI-MLLM: Psychophysics-Inspired Multimodal Large Language Model for Oddly Satisfying Video Emotion Analysis — arXiv:2610.28264 — arXiv (en), https://arxiv.org/abs/2610.28264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e8769bb3d39 (Metraipolis archive dc_6e8769bb3d39, sha256 88c23be962d3122a6fe07b443cb0091b361cf9e21b948fd7fedaa53621e041b6)
BibTeX
@misc{dc6e8769bb3d39,
title = {PI-MLLM: Psychophysics-Inspired Multimodal Large Language Model for Oddly Satisfying Video Emotion Analysis — arXiv:2610.28264},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.28264},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e8769bb3d39; sha256 88c23be962d3122a6fe07b443cb0091b361cf9e21b948fd7fedaa53621e041b6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Oddly Satisfying Videos (OSVs) can evoke strong viewer responses through repetitive motion, visual tactility, and ASMR-like sounds despite containing few explicit semantic emotion cues. This makes OSVs a challenging setting for Video Emotion Analysis (VEA), since most existing methods focus on semantic video content and under-model the physical sensory dynamics that shape viewer responses. To support Oddly Satisfying Video Emotion Analysis (OSVEA), we construct the Oddly Satisfying Video Dataset (OSVD), comprising 12,000 annotated 5-second clips. Each clip provides viewer-emotion labels under video-only, audio-only, and audio-visual conditions, together with explanations grounded in visual and acoustic sensory evidence. Building on OSVD, we propose PI-MLLM, a psychophysics-inspired multimodal large language model that integrates Modality-Specific Dynamics Alignment (MSDA) and Coalition-Based Audio-Visual Attribution (CAVA). MSDA uses auxiliary prediction objectives to align modality representations with visual motion and acoustic energy-onset dynamics. CAVA evaluates emotion scores across modality coalitions and applies Shapley attribution to identify the dominant modality and determine whether visual and auditory evidence is synergistic or conflicting. Experiments show that PI-MLLM improves both viewer-side emotion prediction and sensory-grounded explanation quality, suggesting the value of physical sensory cues to video emotion analysis. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.28264 — 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 2026-10-21T07:05:43.636Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).