Several research positions in the following areas are available in our group(IPM, School of Computer Science, AI group). 
 Machine learning
computer vision
Natural language processing 
Medical Imaging 
Explanable AI 
The appointments can be made at the levels of research assistant, senior research assistant, and postdoctoral. Interested applicants may send their CVs to [email protected]

IPM School of Computer Science is seeking a Postdoctoral researcher with a strong track record of publication in the area of Artificial Intelligence. If you are interested in joining us, please drop an email to [email protected]

#آخرین_مهلت ثبت نام
اولین جلسه ی دوره ی آنلاین GAN نهم اسفند است و ثبت نام تا پنج شنبه 7 اسفند خواهد بود.

http://class.vision/product/deep-generative-tf2/

The submission website of the Second International Workshop on Holistic Video Understanding in Conjunction with #CVPR2021 is open. Accepted papers will be published via the Open Access versions, provided by the Computer Vision Foundation.
#LHVU
https://twitter.com/LSHVU/status/1366311041429352448?s=20
https://holistic-video-understanding.github.io/workshops/cvpr2021.html

HVU2021 Call for paper

We present the Second International Workshop On Large Scale Holistic Video Understanding in conjunction with CVPR 2021. Holistic Video Understanding is a joint project of the KU Leuven, University of Bonn, KIT, ETH, and the HVU team.
We hope that HVU workshop establishes a video benchmark integrating joint recognition of all the semantic concepts, as a single class label per task is often not sufficient to describe the holistic content of a video. Further we invite the community to help to extend the HVU dataset that will spur research in video understanding as a comprehensive, multi-faceted problem.
We welcome contributions fitting the following research topics: Large scale video understanding; Multi-Modal learning from videos; Multi concept recognition from videos; Multi task deep neural networks for videos; Learning holistic representation from videos; Weakly supervised learning from web videos; Object, scene and event recognition from videos; Unsupervised video visual representation learning; Unsupervised and self-supervised learning with videos. Paper Submission
• Paper submission begins, Fabuary 20
• Paper submission deadline, March 31
• For more information visit: https://holistic-video-understanding.github.io/workshops/cvpr2021.html
• CMT submission website: https://cmt3.research.microsoft.com/HVU2021
Important dates
• Full Paper Deadline: March 31
• Notification of Acceptance: April 14
• Camera-ready Version: April 18
• Workshop date: TBA
Keynote Speakers
• Cordelia Schmid (Google AI)
• Joao Carreira (Google DeepMind)
• Carl Vondrick (Columbia University)
• Dima Damen (University of Bristol)
• Sanja Fidler (University of Toronto)
• Kristen Grauman (University of Texas at Austin)
Highlights
• TBD
If you have any questions, please contact us at https://twitter.com/LSHVU, over at https://github.com/holistic-video-understanding, or write to [email protected].
Please feel free to forward this email to those who might be interested. We are looking forward to your HVU submissions!
Sincerely, The HVU 2021 Chairs
• Mohsen Fayyaz (University of Bonn)
• Vivek Sharm (MIT and Harvard)
• Ali Diba (KU Leuven)
• Luc Van Gool (ETH Zurich)
• Juergen Gall (University of Bonn)
• Ehsan Adeli (Stanford Vision and Learning)
• David Ross (Google AI)
• Rainer Stiefelhagen (Karlsruher Institut for Technology)
• Manohar Paluri (Facebook)

Holistic Video Understanding Challenge @CVPR ‘21

https://competitions.codalab.org/competitions/29546

CHALLENGE IS OPEN!


Submission deadlines:

- With a CVF publication: date of workshop
- Without: week before date of workshop

Please submit submissions via: https://competitions.codalab.org/competitions/29546#participate-submit_results

In the last years, we have seen tremendous progress in the capabilities of computer systems to classify video clips taken from the Internet or to analyze human actions in videos. There are lots of works in video recognition field focusing on specific video understanding tasks, such as action recognition, scene understanding, etc. There have been great achievements in such tasks, however, there has not been enough attention toward the holistic video understanding task as a problem to be tackled.
Therefore, we issue this challenge, to tackle this problem on our dataset. For more information on the HVU dataset check the link below. The challenge focuses on the recognition of scenes, objects, actions, attributes, concepts and events in real-world user-generated videos. We expect you to annotate each video in our dataset with labels from a set of tags we provide, that have been sorted in the aforementioned categories. The results should be submitted in a CSV file on our submission sever, where it will be evaluated and ranked according to an assigned score, further information in the links below.
The top 10 scoring submissions will be asked to submit their code, further terms in the links below. The winning group must also submit an arXiv preprint report about their method.

Links:
- HVU workshop: https://holistic-video-understanding.github.io/workshops/cvpr2021.html

- On the dataset: https://holistic-video-understanding.github.io/

- Submission details: https://competitions.codalab.org/competitions/29546#learn_the_details-submission-format

- Evaluation details: https://competitions.codalab.org/competitions/29546#learn_the_details-evaluation

- Terms and Conditions: https://competitions.codalab.org/competitions/29546#learn_the_details-terms_and_conditions

For questions about the HVU challenge or the workshop, please contact [email protected]. Also, follow HVU on Twitter for the latest news: https://twitter.com/LSHVU or https://holistic-video-understanding.github.io/

Organizers:

- Mohsen Fayyaz, University of Bonn
- Ali Diba, KU Leuven
- Vivek Sharma, Harvard, MIT
- Luc Van Gool, ETH Zurich & KU Leuven
- Juergen Gall, University of Bonn
-Ehsan Adeli, Stanford
-David Ross, Google AI
- Rainer Stiefelhagen, KIT
- Manohar Paluri, Facebook AI

#PhD position at Inria (France):

"Robust and generalizable deep learning-based audio-visual speech enhancement"

Deadline to apply: 25/4/2021
Starting date: 1/10/2021
Duration: 3 years

More information:

https://jobs.inria.fr/public/classic/en/offres/2021-03399

The IPM AI group, is looking for a self-motivated research assistant to work on Explainable Artificial Intelligence. Send a message to "[email protected]" if you are interested.

#آموزش
دوره تخصصی بازشناسی چهره عمیق در تنسرفلو / کراس

ای دوره در سال 99 به صورت اختصاصی برای چالش فیس‌کاپ برگزار شد و پس از فیدبکهای شرکت کنندگان مجدد برای استفاده آفلاین ضبط و تدوین گردید و هم اکنون برای عموم در دسترس است.

ویدیوهای رایگان جهت ارزیابی دوره:
https://www.aparat.com/playlist/907750

کدهای دوره:
https://github.com/alireza-akhavan/deep-face-recognition

لینک خرید دوره:
http://class.vision/downloads/deep-face-recognition/


سرفصل های کلی دوره:
Face detection
Separable features vs Discriminative features
One-shot & low-shot learning
Siamese network
What is metric learning & Face embedding?
Face Verification and Identification Challenges and datasets: Lfw, Megaface, …
Facenet Triplet Loss, Center Loss, Sphere Face, Am-softmax, Arc-face, …
How align a face with Landmarks

کد تخفیف 20 درصدی دوره‌ی تخصصی بازشناسی چهره مخصوص اعضای کانال:

irandeeplearning

اعتبار کد بالا تا انتهای فروردین ماه است.

https://twitter.com/csprofkgd/status/1385353348539428867?s=21

Full talk (free registration): https://t.co/ngS1jX7Z9e?amp=1

یه دیتاست 10 هزارتایی پرسش و پاسخ (برای اولین بار در) فارسی تهیه کردیم که به طور متن باز روی گیت هاب قرار گرفته.
دوتا مدلBERTهم ترین کردیم که به سوالات به خوبی پاسخ میدن (مدل ها هم دردسترس اند)
برای اطلاعات بیشتر یا اگه میخوان مدلی توسعه بدین به لینک زیر سر بزنید و با استار ما رو حمایت کنید.
همه میدونیم جمع اوری دیتاست چقدر هزینه بر هست.
https://github.com/sajjjadayobi/PersianQA

A wide collection of video datasets for a wide variety of tasks:
https://github.com/xiaobai1217/Awesome-Video-Datasets