Мақола

MPCCT: Multimodal vision-language learning paradigm with context-based compact Transformer

Chongqing ChenSchool of Information Engineering, Shanghai Maritime University, Shanghai, 201306, ChinaDezhi HanSchool of Information Engineering, Shanghai Maritime University, Shanghai, 201306, ChinaChin‐Chen ChangDepartment of Information Engineering and Computer Science, Feng Chia University, Taichung 407, Taiwan

2023en

ABI

Аннотация

Аннотация мавжуд эмас.

Идентификаторлар

DOI: 10.1016/j.patcog.2023.110084

Иқтибослар ва манбалар

4 та иқтибос0 та фойдаланилган манба

Кўрсаткичлар — AkademScholar