TY - GEN
T1 - Frame difference generative adversarial networks
T2 - 7th International Symposium on Computing and Networking Workshops, CANDARW 2019
AU - Qiu, Rui
AU - Vargas, Danilo Vasconcellos
AU - Sakurai, Kouich
PY - 2019/11
Y1 - 2019/11
N2 - Generating image and video is a hot topic in Deep Learning. Especially, generating video is a difficult but meaningful work. How to generate video which has diversity and plausibility is still a problem to be solved. In this paper, we propose a novel model of Generative Adversarial Network(GAN) which called FDGAN to generate clear contour lines. Unlike existing GAN that only use frames, our method extends to use inter-frame difference. First introduce two temporal difference methods to process the inter-frame. Then increase a frame difference discriminator to discriminate whether the inter-frame is true or not. Using the model and new structure proposed, we perform video generation experiments on several widely used benchmark datasets such as MOVING MNIST, UCF-101. Consequently, the results achieve state-of-the-art performance for clarifying contour lines. Both quantitative and qualitative evaluations were made to show the effectiveness of our methods.
AB - Generating image and video is a hot topic in Deep Learning. Especially, generating video is a difficult but meaningful work. How to generate video which has diversity and plausibility is still a problem to be solved. In this paper, we propose a novel model of Generative Adversarial Network(GAN) which called FDGAN to generate clear contour lines. Unlike existing GAN that only use frames, our method extends to use inter-frame difference. First introduce two temporal difference methods to process the inter-frame. Then increase a frame difference discriminator to discriminate whether the inter-frame is true or not. Using the model and new structure proposed, we perform video generation experiments on several widely used benchmark datasets such as MOVING MNIST, UCF-101. Consequently, the results achieve state-of-the-art performance for clarifying contour lines. Both quantitative and qualitative evaluations were made to show the effectiveness of our methods.
UR - http://www.scopus.com/inward/record.url?scp=85078825789&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078825789&partnerID=8YFLogxK
U2 - 10.1109/CANDARW.2019.00037
DO - 10.1109/CANDARW.2019.00037
M3 - Conference contribution
T3 - Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019
SP - 169
EP - 175
BT - Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 26 November 2019 through 29 November 2019
ER -