TV100:a TV series dataset that pre-trained CLlP has not seen  

作　　者：Da-Wei ZHOU Zhi-Hong QI Han-Jia YE De-Chuan ZHAN 

机构地区：[1]National Key Laboratory for Novel Sofware Technology,Nanjing University,Nanjing 210023,China [2]School of Artificial Intelligence,Nanjing University,Nanjing 2i0023,China

出　　处：《Frontiers of Computer Science》2024年第5期237-238,共2页计算机科学前沿（英文版）

基　　金：This work was partially supported by the National Science and Technology Major Project(2022ZD0114805);the National Natural Science Foundation of China(Grant Nos.62376118,62006112,62250069,61921006);the Collaborative Innovation Center of Novel Software Technology and Industrialization.

摘　　要：In recent years,the field of deep learning has experienced remarkable growth,leading to the emergence of large,pretrained models such as ChatGPT[1],which demonstrates significant capability in understanding and responding to human language inputs,and DALL-E[2],which creatively generates images from textual descriptions in a zero-shot manner.

关 键 词：SUCH TEXTUAL SEE 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]