Rezultati iskanja Ning, Shangwei NUK

11 12 13

zadetkov: 122

121.	Contrastive Fusion Representation: Mitigating Adversarial Attacks on VQA Models He, Jialing; Qin, Zhen; Liu, Hangcheng ... 2023 IEEE International Conference on Multimedia and Expo (ICME), 2023-July Conference Proceeding Visual Question Answering (VQA) is the vision-language task of answering text-based questions presented in an image and has been advanced by the remarkable success of multimodal deep networks. ...	Celotno besedilo
122.	Smaller Is Bigger: Rethinking the Embedding Rate of Deep Hiding Li, Han; Liu, Hangcheng; Guo, Shangwei ... arXiv.org, 02/2023 Paper, Journal Article Odprti dostop Deep hiding, concealing secret information using Deep Neural Networks (DNNs), can significantly increase the embedding rate and improve the efficiency of secret sharing. Existing works mainly force ...	Celotno besedilo

Rezultati iskanja