Multimedia technologies are becoming more and more widely applied in e-commerce platforms, and e-commerce is a solid carrier for advanced multimedia technologies at the same time. For example, image based product search, product recognition from images, product image filtering, OCR, product attribute recognition, 3D product reconstruction and presentation, dress collocation, advertising in images and/or videos, etc., all these techniques are now exploited in online shopping platforms.
E-commerce is a solid and ideal venue for applying and advancing multimedia technologies for the following reasons: (1) online shopping on mobile devices are increasing rapidly, and now most smart phones have cameras and big screens, which provides both the requirements and demands of multimedia technologies; (2) e-commerce has a large-number of active users (for example, Alibaba’s image based product search now has a few million active users every day and the trading volume based on this technique is also over a million US dollars every day); (3) images are one of the key factors for showing and purchasing products, and many multimedia techniques can be and should be applied there (see above: the topic list); (4) Real and large-scale user data is generated on the e-commerce platform every day, which is a strong impetus for advancing multimedia research.
For example, Image recognition and search have been studied for decades and became very hot again in recently years due to the rapid development of distributed computing, high-dimensional indexing, deep learning and big data analytical techniques. Many visual search and recognition research prototypes and preliminary products are available to the public. However, have we solved all the big technical challenges? What are the key factors of realizing a real-world visual recognition/search system? Are semantic gaps still there, and do they really matter? What is the right business model for those technologies? Which direction that visual search/recognition is going towards? What are still missing? All these questions can be tested, verified and answered on e-commerce platforms due to the aforementioned reasons.
07月11日
2016
会议日期
注册截止日期
留言