iiinova — where your digital self keeps evolving

Matteo Dunnhofer @mdunnhofer.bsky.social · 18/10/2025

As an Highlight ✨ in the main conference, we will present results of a new investigation on object tracking in first-person vision by comparison against third-person videos. Work done at the MLP lab at the University of Udine led by Christian Micheloni 📆 Oct 21th, 15:00 - 17:00 📍Poster #542 3/3

010

Matteo Dunnhofer @mdunnhofer.bsky.social · 18/10/2025

At the Human-inspired Computer Vision #HiCV2025 workshop, I will present a poster with recent results on comparing video-based ANNs and the primate visual system. Ongoing project at the ViTA lab @yorkuniversity.bsky.social led by @kohitij.bsky.social 📆 Oct 20th, 8:30 - 12:30 📍Room 309 2/3

121

Matteo Dunnhofer @mdunnhofer.bsky.social · 18/10/2025

On my way to #ICCV2025 in Honolulu 🏝️ @iccv.bsky.social I will share results on ongoing projects I am working on at @yorkuniversity.bsky.social and at the University of Udine Looking forward to discussions! 1/3

120

Matteo Dunnhofer @mdunnhofer.bsky.social · 24/07/2025

Our #ICCV2025 paper will be presented as an Highlight ✨

010

Matteo Dunnhofer @mdunnhofer.bsky.social · 23/07/2025

Joint work with @zairamanigrasso.bsky.social and Christian Micheloni Funded by PRIN 2022 PNRR, MSCA Actions (7/7)

000

Matteo Dunnhofer @mdunnhofer.bsky.social · 23/07/2025

These FPV-specific challenges include: - Frequent object disappearances - Continuous camera motion altering object appearance - Object distractors - Wide field-of-view distortions near frame edges (5/7)

100

Matteo Dunnhofer @mdunnhofer.bsky.social · 23/07/2025

- Trackers learn viewpoint biases and perform best on the viewpoint used during training. - FPV tracking presents its specific challenges. (4/7)

100

Matteo Dunnhofer @mdunnhofer.bsky.social · 23/07/2025

Key takeaways from our study: - FPV is challenging for state-of-the-art generalistic trackers. - Tracking objects in human-object interaction videos is difficult across both first- and third-person viewpoints. (3/7)

100

Matteo Dunnhofer @mdunnhofer.bsky.social · 23/07/2025

We specifically examined whether these drops are due to FPV itself or to the complexity of human-object interaction scenarios. To do this, we designed VISTA, a benchmark using synchronized first and third-person recordings of the same activities. (2/7)

100

Matteo Dunnhofer @mdunnhofer.bsky.social · 23/07/2025

Is Tracking really more challenging in First Person Egocentric Vision? Our new #ICCV2025 paper follows up our IJCV 2023 study (bit.ly/4nVRJw9). We further investigate the causes of performance drops in object and segmentation tracking under egocentric FPV settings. 🧵 (1/7)

120

Matteo Dunnhofer @mdunnhofer.bsky.social · 20/06/2025

In the past weeks we have been around NETI at @utaustin.bsky.social, @vssmtg.bsky.social 2025, and the CVR-CIAN conf. @yorkuniversity.bsky.social, to discuss early findings on modeling object motion in the macaque visual system by deep neural networks. Details to appear soon! @kohitij.bsky.social

020

Matteo Dunnhofer @mdunnhofer.bsky.social · 29/05/2025

The teams behind the workshops on Computer Vision for Winter Sports at @wacvconference.bsky.social and on Computer Vision in Sports at @cvprconference.bsky.social have joined forces in the organisation of a special issue in CVIU on topics related to computer vision applications in sports. 1/2

111

Matteo Dunnhofer @mdunnhofer.bsky.social · 11/05/2025

Honored to be on the list this year!

010

Matteo Dunnhofer @mdunnhofer.bsky.social · 04/03/2025

We are now live with the 3d Workshop on Computer Vision for Winter Sports @wacvconference.bsky.social #WACV2025. Make sure to attend if you are around!

021

Matteo Dunnhofer @mdunnhofer.bsky.social · 03/03/2025

This paper contributes to our projects PRIN 2022 EXTRA EYE and Project PRIN 2022 PNRR TEAM funded by European Union-NextGenerationEU. 6/6

000

Matteo Dunnhofer @mdunnhofer.bsky.social · 03/03/2025

This work was led by Moritz Nottebaum (stop by his poster!) at the Machine Learning and Perception Lab of the University of Udine 5/6

100

Matteo Dunnhofer @mdunnhofer.bsky.social · 03/03/2025

LowFormer achieves significant speedups in image throughput and latency on various hardware platforms, while maintaining or surpassing the accuracy of current state-of-the-art models across image recognition, object detection, and semantic segmentation. 4/6

100

Matteo Dunnhofer @mdunnhofer.bsky.social · 03/03/2025

We used insights from such an analysis to enhance the hardware efficiency of backbones at the macro level, and introduced a slimmed-down version of multi-head self-attention to improve efficiency in the micro design. 3/6

100

Matteo Dunnhofer @mdunnhofer.bsky.social · 03/03/2025

We empirically found out that MACs alone do not accurately account for inference speed. 2/6

100

Matteo Dunnhofer @mdunnhofer.bsky.social · 23/12/2024

Is attendance open to YorkU researchers (e.g. postdocs)? Would like a lot to learn from your teaching style!

130

Matteo Dunnhofer @mdunnhofer.bsky.social · 15/12/2024

Did the same a few weeks ago in Toronto. I think this is the best pizza flavor you can get in Canada 😂

110

Matteo Dunnhofer @mdunnhofer.bsky.social · 01/12/2024

The top-performing teams will be invited to present their solution at the 3rd Workshop on Computer Vision for Winter Sports at #WACV2025! 📄 sites.google.com/unitn.it/cv4... 3/3

sites.google.com

CV4WS@WACV2025

UPDATE (11/19/24): DEADLINE EXTENDED

010

Matteo Dunnhofer @mdunnhofer.bsky.social · 01/12/2024

The challenge platform is hosted on CodaLab and you can find all the submission instructions there. Deadline for submission is January 31st 2025. 🏆 codalab.lisn.upsaclay.fr/competitions... 2/3

codalab.lisn.upsaclay.fr

CodaLab - Competition

110

Matteo Dunnhofer @mdunnhofer.bsky.social · 01/12/2024

The #SkiTB Visual Tracking Challenge at #WACV2025 is open for submissions! The goal is to track a skier in a video capturing his/her full performance across multiple video cameras, and it is based on our recently released SkiTB dataset. 🎥 youtu.be/Aos5iKrYM5o 1/3

youtu.be

[WACV 2024] Tracking Skiers from the Top to the Bottom - qualitative examples

YouTube video by Matteo Dunnhofer

151

Matteo Dunnhofer @mdunnhofer.bsky.social · 24/11/2024

Would be happy to be added as well :) I am working on visual tracking, currently at YorkU ;)

000

Matteo Dunnhofer @mdunnhofer.bsky.social · 18/11/2024

The outgoing phase of my MSCA project PRINNEVOT has started a few days ago. I am now at the #CentreforVisionResearch of #YorkUniversity. I am looking forward to the next two years of research at the intersection of computer vision and visual neuroscience! 🤖🧠

120