#cvpr2020 The program is now online cvpr2020.thecvf.com/program/main-c…... wondering whether best to start "watching" 6pm UK time all night, or 6am all day :-) Virtual + time diff and alternate times of sessions is going to be a difficult act to balance.

Excited to share our work at #CVPR2020: Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior Paper: arxiv.org/abs/2006.04700… Short Demo: youtu.be/4zbFwGjwtDk Code: github.com/lmb-freiburg/F…

Does anyone experience slowness in navigating #CVPR2020

If you are curious about how deep learning predicts the future, come and visit us at #CVPR2020 cvpr20.com/event/multimod…

Feel free to join us in few minutes with @ThomasBrox at #CVPR2020 to know more about our work in future prediction for autonomous driving. cvpr20.com/event/multimod…

I still think #CVPR2020 is still biased to the Seattle time. It is not 24h a day, there are no active sessions during the time between 6 AM and 9/10 AM PDT which is in the middle of a working day in Europe.

For specialized topics in #CVPR2020, they are usually organized under one category and presented in one session (two times). This makes exploring many papers in two hours a challenging task. Wondering if there is a more efficient way!!

Our doctoral program in Intelligent Systems is unique and attracts top students from arouythe globe. Check it out and apply.

Excited to be talking today in the afternoon about probabilistic future prediction at the pattern forecasting workshop icpr2020milan. See you there.

When is the deadline for finalizing the rating/discussions after the rebuttal for #CVPR2021? Also would it be better to send an email to all reviewers to encourage them to discuss and set a deadline for that, so people could plan accordingly.

Is there any system that score reviewers positively/negatively based on their contributions on conferences like #CVPR2021? This can be done by ACs. Then a small notification email could be sent to all reviewers after making a decision to show if their score increase/decrease.

8 Feb (today) is the deadline for submitting the final rate and justification #CVPR2021 #reviewers, help AC to make better decisions.

23 days to paper registration deadline ICCV2021. Paper should be registered by *Mar 10* 30 days for paper submission deadline. Please consider only submitting completed and ready-to-publish papers to #ICCV2021. Do not submit early drafts only for feedback - save reviewers time!

This may be a good starting point for people thinking about how causality can help tackle some of the open problems of machine learning. It discusses core assumptions such as "independent causal mechanisms" and "sparse mechanism shift".

Very excited to start an internship with Amazon. Looking forward to work/learn with intelligent/inspiring people. #proudamazonian #bepeculiar

[DECISIONS] List of accepted papers is now publicly available at: docs.google.com/spreadsheets/u… 1617 papers accepted - 25.9% acceptance rate. Nothing yet on CMT... hang on for meta-reviews soon.

Happy to share with you that our paper "On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors" got accepted at #iccv2021. arxiv.org/abs/2103.12474

We’re looking for Applied Scientists to join our Causal Representation Learning team at Amazon Web Services Tübingen - especially with either experience in representation learning and interest in causality or vice versa. See the link or reach out to me directly. amazon.jobs/en/jobs/164182…

Excited to share that our paper "You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction" got accepted to #iclr2022. More details to follow...

Ever wondered what to do with ambiguous samples in contrastive learning? Check out the recent #AAAI2022 paper "Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives" from David Hoffmann and Nadine Behrmann! arxiv.org/abs/2201.11736