.

1 files changed, 1 insertions, 0 deletions

diff --git a/datasets/scholar/entries/The Do's and Don'ts for CNN-based Face Verification.csv b/datasets/scholar/entries/The Do's and Don'ts for CNN-based Face Verification.csv
new file mode 100644
index 00000000..d494c943
--- /dev/null
+++ b/datasets/scholar/entries/The Do's and Don'ts for CNN-based Face Verification.csv
@@ -0,0 +1 @@
+The Do's and Don'ts for CNN-based Face Verification.|http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w37/Bansal_The_Dos_and_ICCV_2017_paper.pdf|2017|21|7|16583671830808674747|http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w37/Bansal_The_Dos_and_ICCV_2017_paper.pdf|http://scholar.google.com/scholar?cites=16583671830808674747&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=16583671830808674747&hl=en&as_sdt=0,5|None|While the research community appears to have developed a consensus on the methods of acquiring annotated data, design and training of CNNs, many questions still remain to be answered. In this paper, we explore the following questions that are critical to face recognition research:(i) Can we train on still images and expect the systems to work on videos?(ii) Are deeper datasets better than wider datasets?(iii) Does adding label noise lead to improvement in performance of deep networks?(iv) Is alignment needed for face …