Discover and read the best of Twitter Threads about #iccv
Most recents (4)
2nd paper π°π° Vaccine Cohort π We analysed vaccine responses in 585 patients with cancer after COVID-19 vaccination, measuring neutralising responses against the original SARS-CoV-2 and variants of concern (incl. Delta) and T cell responses (1/11) 
After two doses of either Pfizer-BionTech or Oxford-AstraZeneca, 83% of infection-naΓ―ve patients with cancer developed antibodies against the original strain, but only 54% of those had neutralising antibodies against Delta (2/11)
Importantly, we show that while the proportion of patients with S1-reactive antibodies is concordant to patients with NAb against WT SARS-CoV-2 it can overestimate neutralising responses against variants of concern (3/11)
Excited to introduce a new generation of privacy protecting smart cameras in our #ICCV2021 Oral paper by @CarlosH_93, @henarfu and myself πΊπΈπ¨π΄. See 𧡠below for details!
PDF: openaccess.thecvf.com/content/ICCV20β¦
Talk:
Project: carloshinojosa.me/project/privacβ¦
@StanfordAILab
PDF: openaccess.thecvf.com/content/ICCV20β¦
Talk:
Project: carloshinojosa.me/project/privacβ¦
@StanfordAILab
Our cameras introduce optical distortions at acquisition time, capturing images that protect the identity of people in the scene while enabling vision algorithms to perform inference accurately.
*Key idea*: joint end-to-end optimization of optical distortions & vision algorithm.
*Key idea*: joint end-to-end optimization of optical distortions & vision algorithm.
We achieve this by back-propagating all the way down to the camera lens. To make the lens shape differentiable, we parametrize it using Zernike polynomials.
π’ In our #ACMMM21 paper, we highlight issues with training and evaluation of π°πΏπΌππ± π°πΌππ»ππΆπ»π΄ deep networks. π§΅π
For far too long, π°πΏπΌππ± π°πΌππ»ππΆπ»π΄ works in #CVPR, #AAAI, #ICCV, #NeurIPS have reported only MAE, but not standard deviation.
Looking at MAE and standard deviation from MAE, a very grim picture emerges. E.g. Imagine a SOTA net with MAE 71.7 but deviation is a whopping 376.4 !
1/n This #ICML #ICCV plagiarism issue reminds me of an uncomfortable experience of mine. I believe that the code of my ICLR 2020 paper Program Guided Agent (openreview.net/forum?id=BkxUvβ¦), which is not publicly released
2/n and was only submitted to NeurIPS 2019 and ICLR 2020 for reviewing purposes only, was used to produce results and visualizations of another paper without asking for my permission.
3/n When I first saw that paper, I did not even know that crosses a line let alone doing something about it, but I definitely felt really uncomfortable. It has been a while and I still have not heard from the authors.
