Abstract | ||
---|---|---|
Recent years, with the development of e-commerce and population of mobile phones, image-based commodity retrieval has attracted much attention. This paper proposed a deep framework for commodity image retrieval(CMIR) from the view that they are same designed commodities. Our framework can catch as many design details as possible by exploring object detection and ranking sensitive feature learning, while the former is performed based on Faster R-CNN, and the later is learned with a multi-task Siamese Network. Besides, we refine the processing speed of the framework to make it a live system. Our framework is implemented on an android application based on Client/Server structure model whose server response time is about 150 ms per query. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/2911996.2912027 | ICMR |
Keywords | Field | DocType |
Deep Network, Commodity Retrieval, Object Detection | Object detection,Population,Android (operating system),Ranking,Commodity,Computer science,Image retrieval,Response time,Artificial intelligence,Feature learning,Machine learning | Conference |
Citations | PageRank | References |
2 | 0.36 | 5 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhiwei Fang | 1 | 141 | 8.01 |
Jing Liu | 2 | 1781 | 88.09 |
Yuhang Wang | 3 | 2 | 0.36 |
Yong Li | 4 | 254 | 28.66 |
Hang Song | 5 | 2 | 0.36 |
Jinhui Tang | 6 | 5180 | 212.18 |
Hanqing Lu | 7 | 4620 | 291.38 |