search

imatge-upc / retrieval-2016-icmr

Bags of Local Convolutional Features for Scalable Instance Search (ICMR 2016)
https://imatge-upc.github.io/retrieval-2016-icmr/
111 stars 36 forks source link

About the reranking and query expansion #7

Open Paul0629 opened 6 years ago

Paul0629 commented 6 years ago

@evamohe Dear Eva, Thanks for your effort, it really helps me a lot. You mentioned reranking and QE in your paper but your code doesn't seem to contain that part. So where can I get the code. Thanks again.

xavigiro commented 6 years ago

Hi,

I did not write the code but, if you cannot find these functions in this project, you might want to check our more recent paper that improves performance and includes a cleaner code:

Mohedano, E., McGuinness, K., Giro-i-Nieto, X., & O'Connor, N. E. (2017). Saliency Weighted Convolutional Features for Instance Search. arXiv preprint arXiv:1711.10795.   For example, I see the part running the query expansion in this file.

I also authored another paper whose re-reranking and query expansion experiments were based from the present code:

Albert Jimenez, Jose M. Alvarez, and Xavier Giro-i-Nieto. “Class-Weighted Convolutional Features for Visual Instance Search.” In Proceedings of the 28th British Machine Vision Conference (BMVC). 2017.