TY - GEN
T1 - Convolutional Image Captioning
AU - Aneja, Jyoti
AU - Deshpande, Aditya
AU - Schwing, Alexander G.
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - Image captioning is an important task, applicable to virtual assistants, editing tools, image indexing, and support of the disabled. In recent years significant progress has been made in image captioning, using Recurrent Neural Networks powered by long-short-term-memory (LSTM) units. Despite mitigating the vanishing gradient problem, and despite their compelling ability to memorize dependencies, LSTM units are complex and inherently sequential across time. To address this issue, recent work has shown benefits of convolutional networks for machine translation and conditional image generation [9, 34, 35]. Inspired by their success, in this paper, we develop a convolutional image captioning technique. We demonstrate its efficacy on the challenging MSCOCO dataset and demonstrate performance on par with the LSTM baseline [16], while having a faster training time per number of parameters. We also perform a detailed analysis, providing compelling reasons in favor of convolutional language generation approaches.
AB - Image captioning is an important task, applicable to virtual assistants, editing tools, image indexing, and support of the disabled. In recent years significant progress has been made in image captioning, using Recurrent Neural Networks powered by long-short-term-memory (LSTM) units. Despite mitigating the vanishing gradient problem, and despite their compelling ability to memorize dependencies, LSTM units are complex and inherently sequential across time. To address this issue, recent work has shown benefits of convolutional networks for machine translation and conditional image generation [9, 34, 35]. Inspired by their success, in this paper, we develop a convolutional image captioning technique. We demonstrate its efficacy on the challenging MSCOCO dataset and demonstrate performance on par with the LSTM baseline [16], while having a faster training time per number of parameters. We also perform a detailed analysis, providing compelling reasons in favor of convolutional language generation approaches.
UR - http://www.scopus.com/inward/record.url?scp=85061738457&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061738457&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00583
DO - 10.1109/CVPR.2018.00583
M3 - Conference contribution
AN - SCOPUS:85061738457
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 5561
EP - 5570
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE Computer Society
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Y2 - 18 June 2018 through 22 June 2018
ER -