News on Washington L. S. Ramos

Paper accepted to CVPR 2026: TIPSv2

Thu, 09 Apr 2026 00:00:00 +0000

We’ve had a paper accepted to CVPR 2026: “TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment”!

Check out the recent activity on OpenReview.

For more details about the paper, please visit the Publications Section.

First Place at the SIBGRAPI 2024 Workshop of Theses and Dissertations!

Thu, 03 Oct 2024 00:00:00 -0300

Great news! I received the First Place Award for the Best Doctoral Thesis (Ph.D. category) in the Workshop of Theses and Dissertations at the 37th Conference on Graphics, Patterns and Images (SIBGRAPI 2024), the largest national conference on Computer Vision in Brazil.

The awarded thesis, titled “Text-driven Video Acceleration”, presents a methodology based on reinforcement learning to accelerate instructional videos using text.

I would like to deeply thank my advisors, Prof. Erickson R. Nascimento (DCC/UFMG) and Prof. Leandro Soriano Marcolino (Lancaster University), as well as VeRLab, DCC/UFMG, CAPES, FAPEMIG, and CNPq for all the support throughout this journey!

For more details about the thesis paper, please visit the Publications Section. You can also find more information about this award in the Awards Section.

We've had a SIBGRAPI paper accepted!

Thu, 01 Aug 2024 00:00:00 +0000

We’ve got our paper accepted to the Conference on Graphics, Patterns and Images (SIBGRAPI)!

Our paper is titled “Text-driven Video Acceleration”. For more details about the paper, please visit the Publications Section.

We've had a paper accepted to WACV 2024!

Wed, 29 Nov 2023 00:00:00 +0000

We’ve got our paper accepted to the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)!

Our paper is titled “Leveraging synthetic data to learn video stabilization under adverse conditions”. For more details about the paper, please visit the Publications Section.

We've had a Circulation abstract accepted!

Sun, 30 Oct 2022 00:00:00 +0000

We’ve got an abstract accepted to Circulation!

Our abstract is titled “Spatial-Temporal Deep Learning for Automatic Detection of Echocardiographic Predictors of Mortality in Patients Hospitalized With Covid-19-Data From the PROVAR-COVID Study”. For more details about the abstract, please visit the Publications Section.

Paper accepted to BMVC 2022: Semantic segmentation under adverse conditions

Sat, 01 Oct 2022 00:00:00 +0000

We’ve had a paper accepted to BMVC 2022: “Semantic segmentation under adverse conditions: A weather and nighttime-aware synthetic data-based approach”!

For more details about the paper, please visit the Publications Section.

We've had a Pattern Recognition Letters paper accepted!

Thu, 25 Aug 2022 00:00:00 +0000

We’ve got our journal paper accepted to Pattern Recognition Letters!

Our paper is titled “A multimodal hyperlapse method based on video and songs’ emotion alignment”. For more details about the paper, please visit the Publications Section.

We've had a TPAMI paper accepted!

Tue, 01 Mar 2022 00:00:00 -0300

We’ve got our journal paper accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)!

Our paper is titled “Text-driven video acceleration: A weakly-supervised reinforcement learning method”. For more details about the paper, please visit the Publications Section.

SIBGRAPI 2021 paper awarded!

Fri, 22 Oct 2021 18:00:00 -0300

Our conference paper “Musical Hyperlapse: A Multimodal Approach to Accelerate First-Person Videos” was awarded the Best paper on Pattern Recognition and Related Fields in the 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)!

For more details about the paper, please visit the Publications Section.

Awarded with the Microsoft Research PhD Fellowship!

Thu, 21 Oct 2021 18:30:00 -0300

I’ve been selected as one of the 2021-2022 Microsoft Research PhD Fellows!!

More details about the fellowship in the Awards Section.

SIBGRAPI 2021 paper accepted!

Mon, 16 Aug 2021 18:45:00 -0300

We’ve got our conference paper accepted to the 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images(SIBGRAPI)!

Our paper is titled “Musical Hyperlapse: A Multimodal Approach to Accelerate First-Person Videos”. For more details about the paper, please visit the Publications Section.

TPAMI paper accepted!

Wed, 18 Mar 2020 00:00:00 -0300

We’ve got our journal paper accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)!

Our paper is titled “A Sparse Sampling-based framework for Semantic Fast-Forward of First-Person Videos”. For more details about the paper, please visit the Publications Section.

CVPR 2020 paper accepted!

Sun, 23 Feb 2020 00:00:00 -0300

We’ve got our paper accepted to the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)! Our RL agent is guided by documents to take you straight to the point in videos!

Our paper is titled “Straight to the Point: Fast-forwarding Videos via Reinforcement Learning Using Textual Data”. For more details about the paper, please visit the Publications Section.

WACV 2020 paper accepted!

Mon, 16 Sep 2019 19:28:00 -0300

Our paper titled “Personalizing Fast-Forward Videos Based on Visual and Textual Features from Social Network” has been accepted in the IEEE Winter Conference on Applications of Computer Vision (WACV) 2020!

For more details about the paper, please visit the Publications Section. You can get more info about the project on our page: https://www.verlab.dcc.ufmg.br/semantic-hyperlapse/

SIBGRAPI 2019 tutorial proposal accepted!

Thu, 15 Aug 2019 10:42:00 -0300

Great News! Our tutorial proposal titled “A Hands-on Tutorial on Fast Forwarding First-Person Videos” was accepted and presented at the 32nd Conference on Graphics, Patterns and Images (SIBGRAPI) 2019!

Our survey paper titled “Fast-Forward Methods for Egocentric Videos: A Review” is now available through this DOI link.

For more details about the paper, please visit the Publications Section. You can get more info about the project on our page: https://www.verlab.dcc.ufmg.br/semantic-hyperlapse/