Bao Tran Tien Do Thanh Duc Ngo Duy-Dinh Le Shin'ichi Satoh 0001 NII-UIT at VBS2026: Towards Effective Visual Question Answering for Interactive and Multimodal Video Retrieval. MMM (4) 2026 238-244 conf/mmm/2026-4 https://doi.org/10.1007/978-981-95-6963-2_26 db/conf/mmm/mmm2026-4.html#TranDNLS26 streams/conf/mmm