Giorgos Tolias
gtolias.bsky.social
Giorgos Tolias
@gtolias.bsky.social
Associate Professor at CTU in Prague. Computer Vision Researcher at the Visual Recognition Group vrg.fel.cvut.cz. Made in Greece, exported to France and Czech Republic.
https://cmp.felk.cvut.cz/~toliageo
The colloquium at CTU in Prague had 6 great talks and a lot of discussions before, during and after the event. The slides are now shared online. It was the 50th and our administrators surprised us with a huge Czech cake - Koláč. See you in April again!
October 15, 2025 at 7:53 AM
The Visual Recognition Group at CTU in Prague organizes the 50th Pattern Recognition and Computer Vision Colloquium with
Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann.
On Thursday Oct 9, 11:00-17:00.

cmp.felk.cvut.cz/colloquium/
October 6, 2025 at 3:13 PM
Better than just hope: in our ECCV2020 we show that GAP (global average pooling) is a good way to optimize local descriptors using image-level supervision and loss. The dino.txt paper switches from the CLS token to GAP and look at the segmentation task improvements.
August 19, 2025 at 11:42 AM
A CVL is better able to predict the image processing or acquisition settings given solely the image representation when it is trained without image augmentations.
August 19, 2025 at 7:54 AM
growing audience
April 10, 2025 at 10:05 AM
The Visual Recognition Group at CTU in Prague organizes the 49th Pattern Recognition and Computer Vision Colloquium with D. Karatzas, M. Masana, T. Tommasi, P. Mettes @pascalmettes.bsky.social , E. Brachmann @ericbrachmann.bsky.social and V. Stojnic @stojnicv.xyz

cmp.felk.cvut.cz/colloquium/#...
April 7, 2025 at 1:57 PM
Clutter is a major challenge. Small objects are ranked very low using global representations. Oracle experiment: we mask out the background or crop-resize the object and observe a big space for improvements if you can handle heavy clutter.
February 28, 2025 at 1:15 PM
It is striking that off-the-shelf use of VLMs shows that particular objects can be retrieved with textual queries nearly as effectively as with image queries
February 28, 2025 at 11:55 AM
CVPR
February 14, 2025 at 1:37 PM
history
January 22, 2025 at 10:47 PM
from a paper - not a joke
December 12, 2024 at 3:34 PM
in a comparison between using frozen DINOv2 and a model trained for the specific domain in a supervised way (SG/CVNet): DINOv2 is much worse as a global descriptor, but much better for local descriptors.
November 22, 2024 at 8:13 PM
AMES is the new state-of-the-art in instance-level retrieval, has a better performance-memory trade-off than existing models and can improve global descriptor performance even with as few as 10 128D binary local descriptors
November 20, 2024 at 9:17 PM
Transformers are sensitive to sequence length discrepancy between training and testing. Training AMES for a fixed number of local descriptors and testing it for a different one shows performance losses. We eventually train a universal model with a varying number of descriptors
November 20, 2024 at 9:17 PM
Architecture: image2image similarity via a binary classifier that processes two vector sets with within image and across image attention. Memory savings: more local descriptors for the query and less for the database image + use binary descriptors at a tiny performance drop
November 20, 2024 at 9:17 PM
Deep global descriptors give a convenient way for retrieval, but local descriptors are a game changer in finding needles in a haystack (particular objects in clutter). Due to their high cost, with AMES we optimize the performance/memory trade-off during re-ranking. #ECCV2024
November 20, 2024 at 9:14 PM