Multi-scale Orderless Pooling of Deep Convolutional Activation Features. Gong, Y., Wang, L., Guo, R., & Lazebnik, S. In Fleet, D. J, Pajdla, T., Schiele, B., & Tuytelaars, T., editors, Computer Vision - ECCV 2014 - 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VII, pages 392–407, 2014. Springer. Paper doi abstract bibtex Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustnes
@inproceedings{Gong:2014jk,
author = {Gong, Yunchao and Wang, Liwei and Guo, Ruiqi and Lazebnik, Svetlana},
title = {{Multi-scale Orderless Pooling of Deep Convolutional Activation Features}},
booktitle = {Computer Vision - ECCV 2014 - 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VII},
year = {2014},
editor = {Fleet, David J and Pajdla, Tom{\'a}s and Schiele, Bernt and Tuytelaars, Tinne},
pages = {392--407},
publisher = {Springer},
annote = {Essentially, it's a Spatial Pyramid Matching method, using FC7 features....
In Section 3, they argued why FC7 has some spatial specificity. I think this is consistent with later works, such as "Understanding Deep Image Representations by Inverting Them".},
keywords = {deep learning},
doi = {10.1007/978-3-319-10584-0_26},
language = {English},
read = {Yes},
rating = {3},
date-added = {2017-05-05T20:06:51GMT},
date-modified = {2017-05-05T20:42:11GMT},
abstract = {Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustnes},
url = {http://dx.doi.org/10.1007/978-3-319-10584-0_26},
local-url = {file://localhost/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV%202014%20Part%20VII%202014%20Gong.pdf},
file = {{ECCV 2014 Part VII 2014 Gong.pdf:/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV 2014 Part VII 2014 Gong.pdf:application/pdf;ECCV 2014 Part VII 2014 Gong.pdf:/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV 2014 Part VII 2014 Gong.pdf:application/pdf}},
uri = {\url{papers3://publication/doi/10.1007/978-3-319-10584-0_26}}
}
Downloads: 0
{"_id":"PjfwvWa4Raxd8kkD7","bibbaseid":"gong-wang-guo-lazebnik-multiscaleorderlesspoolingofdeepconvolutionalactivationfeatures-2014","downloads":0,"creationDate":"2017-06-08T12:53:07.112Z","title":"Multi-scale Orderless Pooling of Deep Convolutional Activation Features","author_short":["Gong, Y.","Wang, L.","Guo, R.","Lazebnik, S."],"year":2014,"bibtype":"inproceedings","biburl":"https://leelabcnbc.github.io/lab-wiki/reference_library/computer_vision/bib.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Gong"],"firstnames":["Yunchao"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Liwei"],"suffixes":[]},{"propositions":[],"lastnames":["Guo"],"firstnames":["Ruiqi"],"suffixes":[]},{"propositions":[],"lastnames":["Lazebnik"],"firstnames":["Svetlana"],"suffixes":[]}],"title":"Multi-scale Orderless Pooling of Deep Convolutional Activation Features","booktitle":"Computer Vision - ECCV 2014 - 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VII","year":"2014","editor":[{"propositions":[],"lastnames":["Fleet"],"firstnames":["David","J"],"suffixes":[]},{"propositions":[],"lastnames":["Pajdla"],"firstnames":["Tomás"],"suffixes":[]},{"propositions":[],"lastnames":["Schiele"],"firstnames":["Bernt"],"suffixes":[]},{"propositions":[],"lastnames":["Tuytelaars"],"firstnames":["Tinne"],"suffixes":[]}],"pages":"392–407","publisher":"Springer","annote":"Essentially, it's a Spatial Pyramid Matching method, using FC7 features.... In Section 3, they argued why FC7 has some spatial specificity. I think this is consistent with later works, such as \"Understanding Deep Image Representations by Inverting Them\".","keywords":"deep learning","doi":"10.1007/978-3-319-10584-0_26","language":"English","read":"Yes","rating":"3","date-added":"2017-05-05T20:06:51GMT","date-modified":"2017-05-05T20:42:11GMT","abstract":"Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustnes","url":"http://dx.doi.org/10.1007/978-3-319-10584-0_26","local-url":"file://localhost/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV%202014%20Part%20VII%202014%20Gong.pdf","file":"ECCV 2014 Part VII 2014 Gong.pdf:/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV 2014 Part VII 2014 Gong.pdf:application/pdf;ECCV 2014 Part VII 2014 Gong.pdf:/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV 2014 Part VII 2014 Gong.pdf:application/pdf","uri":"˘rlpapers3://publication/doi/10.1007/978-3-319-10584-0_26","bibtex":"@inproceedings{Gong:2014jk,\nauthor = {Gong, Yunchao and Wang, Liwei and Guo, Ruiqi and Lazebnik, Svetlana},\ntitle = {{Multi-scale Orderless Pooling of Deep Convolutional Activation Features}},\nbooktitle = {Computer Vision - ECCV 2014 - 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VII},\nyear = {2014},\neditor = {Fleet, David J and Pajdla, Tom{\\'a}s and Schiele, Bernt and Tuytelaars, Tinne},\npages = {392--407},\npublisher = {Springer},\nannote = {Essentially, it's a Spatial Pyramid Matching method, using FC7 features....\n\nIn Section 3, they argued why FC7 has some spatial specificity. I think this is consistent with later works, such as \"Understanding Deep Image Representations by Inverting Them\".},\nkeywords = {deep learning},\ndoi = {10.1007/978-3-319-10584-0_26},\nlanguage = {English},\nread = {Yes},\nrating = {3},\ndate-added = {2017-05-05T20:06:51GMT},\ndate-modified = {2017-05-05T20:42:11GMT},\nabstract = {Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustnes},\nurl = {http://dx.doi.org/10.1007/978-3-319-10584-0_26},\nlocal-url = {file://localhost/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV%202014%20Part%20VII%202014%20Gong.pdf},\nfile = {{ECCV 2014 Part VII 2014 Gong.pdf:/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV 2014 Part VII 2014 Gong.pdf:application/pdf;ECCV 2014 Part VII 2014 Gong.pdf:/Users/yimengzh/Documents/Papers3_revised/Library.papers3/Articles/2014/Gong/ECCV 2014 Part VII 2014 Gong.pdf:application/pdf}},\nuri = {\\url{papers3://publication/doi/10.1007/978-3-319-10584-0_26}}\n}\n\n\n\n","author_short":["Gong, Y.","Wang, L.","Guo, R.","Lazebnik, S."],"editor_short":["Fleet, D. J","Pajdla, T.","Schiele, B.","Tuytelaars, T."],"key":"Gong:2014jk","id":"Gong:2014jk","bibbaseid":"gong-wang-guo-lazebnik-multiscaleorderlesspoolingofdeepconvolutionalactivationfeatures-2014","role":"author","urls":{"Paper":"http://dx.doi.org/10.1007/978-3-319-10584-0_26"},"keyword":["deep learning"],"metadata":{"authorlinks":{}}},"search_terms":["multi","scale","orderless","pooling","deep","convolutional","activation","features","gong","wang","guo","lazebnik"],"keywords":["deep learning"],"authorIDs":[],"dataSources":["cTc7exbZeMNcenq9s","bzxc3uBcwMv3h47xE","KZFesWbmGy4yc4ZLC"]}