Stamatios Georgoulis

Research Engineer | 3D Computer Vision, Machine Learning, Computational Photography | Huawei, ETH Zurich

[Anpei Chen @AnpeiC]

📢 Our new paper GaVS – 3D-Grounded Video Stabilization is out!

Key idea: feed-forward Dynamic Gaussian Splatting + test-time optimization

Robust, consistent, and cropping-free 📹

🎥 Project: https://t.co/88XWoJozKn

@youzn99 @stam_g @SiyuTang3 Dengxin Dai
#SIGGRAPH25 #3DGS

[Dimitris Tzionas @dimtzionas]

Motivated MSc/BSc students & prospective PhD candidates can always reach out to me -- plz see the contact instructions on my website.

Plz help me spread the word: 🆘 🆘 🆘 We are actively hiring 1 PhD candidate together with @theogevers! Separate tweet coming soon 📢 📢 📢 (8/8)

[DeepAI @DeepAI]

Multi-Bracket High Dynamic Range Imaging with Event Cameras
https://t.co/7sURbFPUh8
by Nico Messikommer et al. including @stam_g
#ComputerVision #PatternRecognition

[Simon Vandenhende @svandenh1]

Excited to be hosting the DeepMTL workshop on multi-task learning at @ICCV_2021 tomorrow. We have an excellent group of speakers ready for you: @zamir_ar I. Kokkinos @judyfhoffman @RaquelUrtasun R. Caruana A. Rabinovich

https://t.co/aMQ339NB6B

[Anton Obukhov @AntonObukhov1]

Our #ICCV2021 paper on Adaptive Task-Relational Context, leveraging neural architecture search and attention mechanisms in the multi-task learning setting, is now paired with source code! @menelaoskanakis @stam_g

paper: https://t.co/JQDOGiT2YV
code: https://t.co/JrlNmmrThx

[Davide Scaramuzza @davsca1]

So honored that our #CVPR2021 on video frame interpolation with event cameras is on #twominutepapers! @DanielGehrig6 @StepanTulyakov

[Anton Obukhov @AntonObukhov1]

The source code of our #ICML 2020 paper "T-Basis: a Compact Representation for Neural Networks" is now on GitHub: https://t.co/clKGcletAQ

[Anton Obukhov @AntonObukhov1]

I will present our latest #AISTATS work about sparse and stable CNN parameterizations (pinned) in the sparsity workshop today in 4 hrs #SNN21

[Davide Scaramuzza @davsca1]

We release our newest work on event cameras: "Time Lens". We use events to upsample low-framerate RGB HD video by over 50 times with only 1/40th of the memory footprint! #CVPR2021 Paper, code, datasets: https://t.co/LK1vncrg0U
@DanielGehrig6 @MathiasGehrig

[Wouter Van Gansbeke @WGansbeke]

We study how biases in the dataset affect contrastive pretraining and explore additional invariances

What if we use non-curated data (COCO, OpenImages) vs ImageNet? Do we need priors to learn dense representations?

Paper: https://t.co/Q1D2XY0EB3
Code: https://t.co/dX2yGuma75
👇

[DeepAI @DeepAI]

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
https://t.co/3jQ4YE8xT6
by Suman Saha et al. including @menelaoskanakis, @stam_g
#Estimator #Statistics

[Anton Obukhov @AntonObukhov1]

1/ Our paper “Spectral Tensor Train Parameterization of Deep Learning Layers” about end-to-end neural network compression and stability of training in the GAN setting is live at #AISTATS2021 this week!
PDF: https://t.co/PGuEmFSDgc
Project page: https://t.co/LlE1zQuLk8

[DeepAI @DeepAI]

Spectral Tensor Train Parameterization of Deep Learning Layers
https://t.co/7phP4VonrT
by Anton Obukhov et al. including @stam_g
#NeuralNetwork #Tensor

[Anton Obukhov @AntonObukhov1]

Code packaging frenzy continues! Check out my latest python package, democratizing orthogonal transformations in #PyTorch. Goomba has nothing to do with the Householder transformation; your attention is all I need.
https://t.co/C9kxWVvWaI
https://t.co/ikftThfg9t

[Simon Vandenhende @svandenh1]

We have updated our survey on multi-task learning for dense prediction tasks. The paper features an extensive literature review, intuitive comparisons, thorough experiments, etc.
https://t.co/wjDpuPFEjN

Code can be found here 🥳: https://t.co/2pRMvpLtTM

[Menelaos Kanakis @menelaoskanakis]

The codebase from our #ECCV2020 paper titled "Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference" is now publicly available:
https://t.co/st7qMiwuE9

[Menelaos Kanakis @menelaoskanakis]

Check out our #BMVC2020 paper "Automated Search for Resource-Efficient Branched Multi-Task Networks". We propose an approach to automatically define branched multi-task networks, while using a resource-aware loss to control the model size
Paper: https://t.co/OtKScCtVrN

[Menelaos Kanakis @menelaoskanakis]

Join us today for the poster session of our work "Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference" at #ECCV2020 !

Session 1: Wednesday 26 August: 06:00 - 08:00 (UTC+1)
Session 2: Wednesday 26 August: 14:00 -16:00 (UTC+1)

[Menelaos Kanakis @menelaoskanakis]

Our paper "Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference" has been accepted to #ECCV2020. We reparameterize the convs to eliminate task interference and allow for the incremental learning of new tasks.
Paper: https://t.co/Iif8WRx8fs