Olivier Pascaud
OlivierHuggingface
·
AI & ML interests
https://orcid.org/0009-0004-1803-4943
Recent Activity
authored a paper about 1 month ago
TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film posted an update about 1 month ago
Films communicate through deliberate creative choices, including lighting, color, composition, editing, dialogue, music, and sound. Humans naturally interpret these signals as directorial intent, yet current multimodal large language models (MLLMs) are evaluated almost exclusively on understanding what happens rather than why it is presented that way. We introduce TAKE 85, the first benchmark for directorial-intent understanding, comprising 398 short films (85 hours) with expert-verified question-answer pairs spanning global and fine-grained visual and audio intent.
https://arxiv.org/pdf/2608.30068