Nikita Araslanov
@neekans.bsky.social
๐ค 90
๐ฅ 212
๐ 5
Researcher at University of Oxford / TU Munich
https://arnike.github.io
pinned post!
In-context learning suggests that a model has learned versatile representations. What if we use in-context learning itself as a training task for visual representations? ๐ฃ Introducing ๐๐๐๐: ๐๐ถ๐ป๐ฒ๐ฎ๐ฟ ๐๐ป-๐๐ผ๐ป๐๐ฒ๐ ๐ ๐๐ฒ๐ฎ๐ฟ๐ป๐ถ๐ป๐ด โจ CVPR 2026 Oral โจ Paper, code and more:
lila-pixels.github.io
#CVPR2026
๐งต๐
loading . . .
about 14 hours ago
1
0
0
In-context learning suggests that a model has learned versatile representations. What if we use in-context learning itself as a training task for visual representations? ๐ฃ Introducing ๐๐๐๐: ๐๐ถ๐ป๐ฒ๐ฎ๐ฟ ๐๐ป-๐๐ผ๐ป๐๐ฒ๐ ๐ ๐๐ฒ๐ฎ๐ฟ๐ป๐ถ๐ป๐ด โจ CVPR 2026 Oral โจ Paper, code and more:
lila-pixels.github.io
#CVPR2026
๐งต๐
loading . . .
about 14 hours ago
1
0
0
๐ข NeurIPS 2025 Spotlight ๐ข Can we embed motion into image representations? FlowFeat embeds optical flow into pixel-level representations, which results in sharp feature grids, especially for dynamic objects. Project website:
tum-vision.github.io/flowfeat
With Anna Sonnweber and Daniel Cremers.
loading . . .
6 months ago
0
6
2
reposted by
Nikita Araslanov
Dominik Schnaus
12 months ago
Can we match vision and language representations without any supervision or paired data? Surprisingly, yes!ย Our
#CVPR2025
paper with
@neekans.bsky.social
and
@dcremers.bsky.social
shows that the pairwise distances in both modalities are often enough to find correspondences. โฌ๏ธ 1/4
loading . . .
1
27
12
reposted by
Nikita Araslanov
Zhenjun Zhao
about 1 year ago
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction Weirong Chen,
@ganlinzhang.xyz
,
@fwimbauer.bsky.social
, Rui Wang,
@neekans.bsky.social
, Andrea Vedaldi,
@dcremers.bsky.social
tl;dr: learning-based 3D point tracker decouples camera and object-based motion
arxiv.org/abs/2504.14516
0
13
6
reposted by
Nikita Araslanov
Visual Inference Lab
about 1 year ago
๐ข
#CVPR2025
Highlight: Scene-Centric Unsupervised Panoptic Segmentation ๐ฅ We present CUPS, the first unsupervised panoptic segmentation method trained directly on scene-centric imagery. Using self-supervised features, depth & motion, we achieve SotA results! ๐
visinf.github.io/cups
1
22
8
โAfter carefully reading the other reviews and the author response, I keep my score โborderlineโโ ๐ฃ
#CVPR2025
over 1 year ago
0
4
0
reposted by
Nikita Araslanov
Dimitris Tzionas
over 1 year ago
๐ข I am
#hiring
2x
#PhD
candidates to work on Human-centric
#3D
#ComputerVision
at the University of
#Amsterdam
! The positions are funded by an
#ERC
#StartingGrant
. For details and for submitting your application please see:
werkenbij.uva.nl/en/vacancies...
๐ Deadline: Feb 16 ๐
loading . . .
Vacancy โ PhD Positions, Project 'Spatiotemporal Reconstruction of Interacting People for Perceiving Systems'
Do you want to help computers see, understand, and assist us, humans, in everyday life?ย Are you excited with 3D Machine Perception, 3D Human and Object Understanding, 3D Human Avatars, and Machine Le...
https://werkenbij.uva.nl/en/vacancies/phd-positions-project-spatiotemporal-reconstruction-of-interacting-people-for-perceiving-systems-netherlands-13444
1
15
8
reposted by
Nikita Araslanov
Justus Thies
over 1 year ago
My group is looking for motivated PhD students that want to work on the future of digital humans. Within the ERC project 'LeMo: Learning Digital Humans in Motion' there are two open positions:
www.career.tu-darmstadt.de/HPv3.Jobs/TU...
www.career.tu-darmstadt.de/HPv3.Jobs/TU...
0
19
7
you reached the end!!
feeds!
log in