نسخة أولية وصول مفتوح
FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering
Query-aware keyframe selection enables multimodal large language models (MLLMs) to process long videos using only a small set of question-relevant frames. Existing score-based methods, however, typically search within a fixed, uniformly sampled candidate pool, preventing evidence outside this pool from ever being selec …