Sidan finns bara på engelska

Reading Group in Computer and Robot Vision

The purpose of this reading group is to provide an overview of the rapidly evolving computer vision literature. We meet once a week to discuss an article that all participants should read before the seminar.

All participants are welcome to suggest, and present articles of their choosing. The theme for articles should be computer and robot vision, with emphasis on new, high-impact conference papers (e.g. from ICCV, CVPR, RSS, or ECCV). To make best use of time, you may consider choosing an article that relates to your work, that you presumably would read anyway. If the article is well written that is also a plus. To ensure that all participants benefit from the discussion, it is recommended that the speaker provide a list of 2-3 relevant papers before the meeting, from which we can collectively select one. We have a dedicated channel in Teams, where we discuss this. Send me an email, and I will add you to it.

You have the option to attend the seminars as part of a PhD course. You will get one 1hp for each time you present a paper, and participate in another three seminars. If you want to go for the PhD course option, let me know in advance by sending me an email with your personal number, so I can register your attendance.
/Pavlo

Meeting room: Visionen, Stora Konf.rummet, Campus Valla, Building B.
Time: Wednesday at 13.00-14.00.
E-mail list: Upcoming meetings and articles are announced on the mailing list vision-seminars.

Upcoming articles

November 19: Aprilia Rinasti presents Nejjar, I., et al., DARE-GRAM: Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices, CVPR 2023 [PDF].
November 26: Nothing scheduled right now. Please volunteer to present!
December 3: Nothing scheduled right now. Please volunteer to present!

Paper log autumn 2025

October 29: Maeva Caut presents Z. Xu et al., Learning Imbalanced Data with Vision Transformers, CVPR'23 [PDF].
Tuesday, October 21, 10.00-11.00: Sigmund Rolfsjord and/or Daniel Gusland present Vonheim Larsen et al., BASE: Probably a Better Approach to Visual Multi-Object Tracking [PDF]
October 1: Ziliang Xiong presents Kock et al., Calibrated Multivariate Regression with Localized PIT Mappings [PDF].
September 24: Johan Edstedt presents Lukoianov et al., Locality in Image Diffusion Models Emerges from Data Statistics [PDF].
September 3: Johan Edstedt presents Siméoni et al., DINOv3 [PDF].

Paper log spring 2025

June 11: Anmar Karmush presents C.K. Joshi et al., All-atom Diffusion Transformers: Unified generative modelling of molecules and materials, ICML'25 [PDF].
May 28: Aprilia Rinasti presents Q. Wang et al., ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks, CVPR'20 [PDF].
May 21: Instead of a reading group session, we will attend a talk by Professor Robert Forchheimer titled "ChatGPT - How it works (and partly why)". Location: Ada-Lovelace, B-huset.
April 30: Sara Tehrani presents K. Kuckreja et al., GeoChat: Grounded Large Vision-Language Model for Remote Sensing, CVPR'24 [PDF].
April 23: Gulnaz Zhambulova presents W. Ma et al., Learning Modality Knowledge Alignment for Cross-Modality Transfer, ICML'24 [PDF].
April 16: Maeva Caut presents S.C. Lowe et al., An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders, ICML'24 Workshop [PDF].
April 9: Ziyu Cao presents C. Sommer et al., Efficient derivative computation for cumulative B-splines on Lie groups, CVPR'20 [PDF].
March 31: Bao-Long Tran presents Z. Zhong et al., Blur Interpolation Transformer for Real-World Motion Blur, CVPR'23 [PDF].

Paper log spring 2024

March 6: Johan presents: T. Karras et al., Elucidating the Design Space of Diffusion-Based Generative Models, NeurIPS'22 [ArXiv] [OpenReview]

Old paper logs

See also the full list of PhD courses at the division.