@patrick-ramos.bsky.social
PhD student @ ISLab, Osaka University
Congrats!
31.10.2025 06:43 β π 1 π 0 π¬ 0 π 0Forgot to post about our workshop poster in #ICCV2025! (Data Leakage in Visual Datasets) Thank you @noagarciad.bsky.social!
The only reason weβve been putting in more effort into posters is our wonderful advisor πββοΈ
(Poster typo: there should be an equal contribution mark on Ryanβs and my names)
This is today in less than 2 hours. Come by and say hi!
22.10.2025 22:45 β π 3 π 1 π¬ 0 π 0Today at #ICCV2025 (afternoon poster session): see how sensitive some foundational models are to non-semantic cues like JPEG compression and camera model. Such cues can heavily distort their semantic predictions.
22.10.2025 19:58 β π 13 π 2 π¬ 0 π 0Are you at @iccv.bsky.social #ICCV2025? Come by our poster.
Β π
October 22, 2025, 14:30 β 16:30 HST
Β π Location: Exhibit Hall I, Poster #207
Super excited to be flying to Hawaii for the first time for #iccv2025. I can't wait to meet old friends and make new ones. Find me at these talks and workshops the first two days!
17.10.2025 22:07 β π 6 π 2 π¬ 1 π 0
Our list of papers to be presented at #iccv2025 workshops and main conference. Please come by and say hi!
* Oct 19, STREAM workshop
* Oct 20, Findings workshop
* Oct 21, Poster session 2 id #801
* Oct 22, Poster session 4 id #1572 (highlight)
Respectfully, Iβm surprised you consider CLIP to be SSL. SSL implies that the supervision guiding the image reps comes from the images (ex. masked input, full image target). Thatβs not the case with CLIP, as the text supervision isnβt directly derived from the images, but is collected with them
24.08.2025 14:02 β π 2 π 0 π¬ 0 π 0
Have you ever asked yourself how much your favorite vision model knows about image capture parameters (e.g., the amount of JPEG compression, the camera model, etc.)? Furthermore, could these parameters influence its semantic recognition abilities?
18.08.2025 10:48 β π 26 π 8 π¬ 1 π 4
(Thought I hit post but it didnβt send earlier)
My posterβs up at #MIRU2025 !
If you want to talk about labeling sparse autoencoders with VLMs, feel free to swing by IS1-082!
Work done with my advisors Yuta Nakashima and @noagarciad.bsky.social !
Posterβs up at #WACV2025 !
02.03.2025 18:47 β π 2 π 1 π¬ 0 π 0
Merry Christmas! My gift to myself is being mentored by my awesome advisor @noagarciad.bsky.social
Also featuring @ryan-ramos.bsky.social
The message makes sense in context of the other pictures we took that day lol
Geospatial folks, what are your dreams about remote sensing data ? What would you like to do that your model can't for the moment ?
I am looking for hard problems with AI on remote sensing data.
I am very pleased to see the publication of this project, which is a continuation of my PhD work on weakly supervised object detection in artworks.
Going a step further by proposing an approach for zero-shot object detection in artworks.
bsky.app/profile/noag...
My first PhD paper at Osaka University! Very very very thankful for my wonderful collaborators and advisors!
10.12.2024 08:18 β π 4 π 2 π¬ 0 π 0
What better time to announce a new paper than during NeurIPS and ACCV?
happy happy happy to introduce NADA, our latest work on object detection in art! π¨
with amazing collaborators:
@patrick-ramos.bsky.social, @nicaogr.bsky.social, Selina Khan, Yuta Nakashima
