TY - GEN
T1 - Does text attract attention on e-commerce images
T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
AU - Jiang, Lai
AU - Li, Yifei
AU - Li, Shengxi
AU - Xu, Mai
AU - Lei, Se
AU - Guo, Yichen
AU - Huang, Bo
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - E-commerce images are playing a central role in attracting people's attention when retailing and shopping online, and an accurate attention prediction is of significant importance for both customers and retailers, where its research is yet to start. In this paper, we establish the first dataset of saliency e-commerce images (SalECI), which allows for learning to predict saliency on the e-commerce images. We then provide specialized and thorough analysis by high-lighting the distinct features of e-commerce images, e.g., non-locality and correlation to text regions. Correspondingly, taking advantages of the non-local and self-attention mechanisms, we propose a salient SWin-Transformer back-bone, followed by a multi-task learning with saliency and text detection heads, where an information flow mechanism is proposed to further benefit both tasks. Experimental results have verified the state-of-the-art performances of our work in the e-commerce scenario.
AB - E-commerce images are playing a central role in attracting people's attention when retailing and shopping online, and an accurate attention prediction is of significant importance for both customers and retailers, where its research is yet to start. In this paper, we establish the first dataset of saliency e-commerce images (SalECI), which allows for learning to predict saliency on the e-commerce images. We then provide specialized and thorough analysis by high-lighting the distinct features of e-commerce images, e.g., non-locality and correlation to text regions. Correspondingly, taking advantages of the non-local and self-attention mechanisms, we propose a salient SWin-Transformer back-bone, followed by a multi-task learning with saliency and text detection heads, where an information flow mechanism is proposed to further benefit both tasks. Experimental results have verified the state-of-the-art performances of our work in the e-commerce scenario.
KW - Low-level vision
KW - Vision applications and systems
UR - https://www.scopus.com/pages/publications/85136194455
U2 - 10.1109/CVPR52688.2022.00213
DO - 10.1109/CVPR52688.2022.00213
M3 - 会议稿件
AN - SCOPUS:85136194455
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2078
EP - 2087
BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
PB - IEEE Computer Society
Y2 - 19 June 2022 through 24 June 2022
ER -