TY - GEN
T1 - Watch and Buy
T2 - 1st Workshop on Multimodal Product Identification in Livestreaming and WAB Challenge, WAB 2021, held in conjunction with the ACM Multimedia 2021
AU - Rao, Jun
AU - Cao, Yue
AU - Qi, Shuhan
AU - Dong, Zeyu
AU - Qian, Tao
AU - Wang, Xuan
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/10/22
Y1 - 2021/10/22
N2 - "Watch and Buy: Multimodal Product Identification(WAB)"challenge is a new task in the field of cross-modal retrieval, which aims to retrieve the relevant products when users watching live streamers selling fashion products. In practice, it is very hard to get the product items accurately and quickly because of large deformations, occlusions and motion blur of product items in a real-world live streaming environment. In this paper, our solution for WAB challenge is presented, which includes the model and training methods of fashion product localization and identification, as well as the detailed strategy for optimization, model assembly, and post-process rank. Experiments show that our strategies for data enhancement, model fusion and result ranking can lead to a better result. Finally, our model is small and efficient with competitive results and attains 0.4915 on test B in the final season, ranking 5th. And our model attains 0.5604 on test A, ranking 1st in the late submission.
AB - "Watch and Buy: Multimodal Product Identification(WAB)"challenge is a new task in the field of cross-modal retrieval, which aims to retrieve the relevant products when users watching live streamers selling fashion products. In practice, it is very hard to get the product items accurately and quickly because of large deformations, occlusions and motion blur of product items in a real-world live streaming environment. In this paper, our solution for WAB challenge is presented, which includes the model and training methods of fashion product localization and identification, as well as the detailed strategy for optimization, model assembly, and post-process rank. Experiments show that our strategies for data enhancement, model fusion and result ranking can lead to a better result. Finally, our model is small and efficient with competitive results and attains 0.4915 on test B in the final season, ranking 5th. And our model attains 0.5604 on test A, ranking 1st in the late submission.
KW - fashion identification
KW - fashion retrieval
KW - object detection
UR - https://www.scopus.com/pages/publications/85119010066
U2 - 10.1145/3475956.3484482
DO - 10.1145/3475956.3484482
M3 - 会议稿件
AN - SCOPUS:85119010066
T3 - WAB 2021 - Proceedings of the 1st Workshop on Multimodal Product Identification in Livestreaming and WAB Challenge, co-located with ACM MM 2021
SP - 23
EP - 31
BT - WAB 2021 - Proceedings of the 1st Workshop on Multimodal Product Identification in Livestreaming and WAB Challenge, co-located with ACM MM 2021
PB - Association for Computing Machinery, Inc
Y2 - 24 October 2021 through 24 October 2021
ER -