Fida Mohammad

PhD student at University of Amsterdam | Deep learning for Computer Vision

[KAUST Computer Vision Lab (IVUL) @KaustVision]

Come visit the IVUL posters and oral presentations at #CVPR2026! @KAUST_News

Poster numbers and presentation times for each paper are highlighted in the colored boxes.
See you there!

[Fida Mohammad @fmthoker]

@neerjathakkar @GoogleDeepMind Great work!!
We applied a similar approach for the problem of video self supervised learning by predicting masked point tracks. https://t.co/jB1QAVVaSn
Would be interesting to incorporate the token representation of the point tracks from your paper for video SSL learning.

[KAUST CEMSE @KAUST_CEMSE]

Ready to rise among the next generation of #AI innovators?

Apply for the #KAUST Rising Stars in AI Symposium, organized by the #Center of Excellence for Generative AI, and join a global cohort of AI innovators!

Deadline: Nov 15, 2025
🔗 https://t.co/BaD8XnSCkQ

[Hasan Hammoud @hammh0a]

Just released "DiffCLIP", extending Differential Attention proposed by @ytz2024 to CLIP models - replacing both visual & text encoder attention with the differential attention mechanism!

TL;DR: Consistent improvements across all tasks with only 0.003% extra parameters!

[KAUST Computer Vision Lab (IVUL) @KaustVision]

Super excited to share that 4 papers from our @KaustVision IVUL lab got into #CVPR2025! Huge congrats to all the authors and our amazing collaborators! 🎉👏

@CVPR @KaustResearch

[Fida Mohammad @fmthoker]

@doughty_hazel @ACCVConf @ACCVConf so far so good

[Hazel Doughty @doughty_hazel]

Our #ACCV2024 Oral "LocoMotion: Learning Motion-Focused Video-Language Representations" w/ @fmthoker and @cgmsnoek is now on ArXiv https://t.co/GpqIPGxrNU

We remove the spatial focus of video-language representations and instead train representations to have a motion focus.

[Fida Mohammad @fmthoker]

Checkout our poster if you are at #ECCV2024

[Mohammadreza Salehi @MrzSalehi]

🚀 Excited to present SIGMA at @eccvconf ! 🎉 We upgrade VideoMAE with Sinkhorn-Knopp on patch-level embeddings, pushing reconstruction to more semantic features. With @mdorkenw.
Let’s connect at today's poster session at 4:30 PM, poster number 256, or send us a DM.

[Michael Dorkenwald @mdorkenw]

📢SIGMA: Sinkhorn-Guided Masked Video Modeling got accepted to @eccvconf #ECCV2024

TL;DR: Instead of using pixel targets in Video Masked Modeling, we reconstruct jointly trained features using Sinkhorn guidance, achieving SOTA.

📝Project page: https://t.co/uV9SA7NbZK
🌐Paper: https://t.co/FYR2NERPft

Joint work with @MrzSalehi @fmthoker @egavves @cgmsnoek @y_m_asano

[Hazel Doughty @doughty_hazel]

Next Thursday at #ICCV2023, we'll present our work on self-supervised learning for motion-focused video representations.

Work w/ @fmthoker and @cgmsnoek

We learn similarities between videos with identical local motion dynamics but an otherwise different appearance.

1/6

[Mohammadreza Salehi @MrzSalehi]

How to do research:

https://t.co/hRLPmxTfAb

Summary :
1. Slow down to speed up.
2. Find why something does not work as much as possible.
3. Hard working is necessary .
4. Collaborate. Small piece of a big cake> Big piece of small cake.
5. Communicate effectively.
#icvss23

[Mohammad Mahdi (Medi) Derakhshani @mmderakhshani]

Enhanced version of this paper accepted to #ICCV2023. 🥳🥳

ps: my belated birthday gift!

[Hazel Doughty @doughty_hazel]

Happy our paper 'Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization' was accepted to #ICCV2023.

Congrats @fmthoker!

Preprint: https://t.co/U4cmValmcL

[#ICCV2025 @ICCVConference]

The list of paper IDs for accepted #ICCV2023 papers is now available at the following link:
https://t.co/A0mCH8gbOi

[#ICCV2025 @ICCVConference]

As soon as we hear about the decision release from our #ICCV2023 Program Chairs we will let you know!

In the meantime …

[Fida Mohammad @fmthoker]

@re5e1f @CVPR I along with many other students from Netherlands have been waiting since march. It seems the effort to expedite the process didn’t reach anywhere.

[Kosta Derpanis (sabbatical in Zurich) @CSProfKGD]

Check out our EXCITING lineup of invited speakers for the @CVPR #CVPR2023 2nd Workshop on Learning with Limited Labelled Data for Image and Video Understanding 🤗

https://t.co/bZC2h50H00

[Fida Mohammad @fmthoker]

@noahzn2077 @CVPR @avinab_saha Yes, in background check since March

[Fida Mohammad @fmthoker]

@CVPR @avinab_saha @CVPR any of those from Europe? We applied in February and haven’t received any response yet?