diff options
| author | Jules Laplace <julescarbon@gmail.com> | 2018-10-31 02:15:42 +0100 |
|---|---|---|
| committer | Jules Laplace <julescarbon@gmail.com> | 2018-10-31 02:15:42 +0100 |
| commit | a16c3cf801b70670dffc7041d92f7ccec56a0e18 (patch) | |
| tree | 189c6f52c347cad780aba982c04efb8668eaa57f /datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv | |
| parent | 640fb390baf494571114bc50b8059c9823ee899e (diff) | |
| parent | ab81e78a0bca427ba9b0283ec3a1b5fc2d98cf2d (diff) | |
Merge branch 'master' of asdf.us:megapixels_dev
Diffstat (limited to 'datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv')
| -rw-r--r-- | datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv b/datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv new file mode 100644 index 00000000..0b36206c --- /dev/null +++ b/datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv @@ -0,0 +1 @@ +Beyond frontal faces: Improving person recognition using multiple cues|http://scholar.google.com/https://www.cv-foundation.org/openaccess/content_cvpr_2015/html/Zhang_Beyond_Frontal_Faces_2015_CVPR_paper.html|2015|70|13|4032136205953773331|None|http://scholar.google.com/scholar?cites=4032136205953773331&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=4032136205953773331&hl=en&as_sdt=0,5|None|We explore the task of recognizing peoples' identities in photo albums in an unconstrained setting. To facilitate this, we introduce the new People In Photo Albums (PIPA) dataset, consisting of over 60000 instances of~ 2000 individuals collected from public Flickr photo albums. With only about half of the person images containing a frontal face, the recognition task is very challenging due to the large variations in pose, clothing, camera viewpoint, image resolution and illumination. We propose the Pose Invariant PErson Recognition … |