ResearchBenchmarksQuery-based video segmentation (Audio→Text) on AVSBench-S4 VGGSound-AVEL 90KFollow76.5mIoUCoDAAR74.73275.19175.6576.109May 12, 2026Evaluation ResultsMethodMethodLinksmIoUF-scoreCoDAARSetting=AVT, Fine-tune...Setting=AVT, Fine-tuned epoch=4th2026.0576.586.4MICUSetting=AVT, Fine-tune...Setting=AVT, Fine-tuned epoch=4th2026.0576.486DCIDSetting=AVT, Fine-tune...Setting=AVT, Fine-tuned epoch=4th2026.0574.884.7