1. DEEP-AD: A Multimodal Temporal Video Segmentation Framework for Online Video Advertising:

– Shot boundary detection

– Automatic video abstraction

– Multimodal scene segmentation using: low/high level visual descriptors, audio patterns and semantic description

– Thumbnail selection from video scenes

– Ads insertion based on semantic criterion

2. Automatic subtitle synchronization and positioning:

– Text pre-processing and automatic speech recognition

– Anchor word identification and token matching

– Phrases alignment

– Subtitle/Close Caption positioning

3. DEEP-HEAR: A Multimodal Subtitle Positioning System Dedicated to Deaf and Hearing-Impaired People:

– Face detection, tracking and recognition

– Video temporal segmentation into stories

– Active speaker detection

– Subtitle positioning

LECTURER: – Prof. Ruxandra Țapu, email: ruxandra_tapu@comm.pub.ro

HOST INSTITUTION/ORGANIZER: Politehnica University of Bucharest

REGISTRATION: Free of charge

WHEN: 16-17 June 2022 from 11:00 to 13:00 CET (4 hours)

WHERE: Online (Microsoft Teams link will be provided)

HOW TO REGISTER and ENROLL: 

Both AIDA and non-AIDA students are encouraged to participate in this short course.

If you are an AIDA Student* already, please:

Step (a): Register in the course, please send fill the Registration form.

AND

Step (b): Enroll in the same course in the AIDA system using “Enroll on this Course”, so that this course enters your AIDA Certificate of Course Attendance.

If you are not an AIDA Student, do only step (a).

*AIDA Students should have been registered in the AIDA system already (they are PhD students or PostDocs that belong only to the AIDA Members listed in this page: https://www.i-aida.org/about/members/)

Prof. Ruxandra Țapu,

Email ruxandra_tapu@comm.pub.ro

Dear members of AI Inference and Machine Learning Communities,

After several years of slumber, we are pleased to announce the resurrection of the UAI inference competition. This year we introduce a new machine learning component to the competition (read more below). 

The goal of this competition is to explore our communities’ various approaches to approximating quantities of graphical models such as the partition function or probability of evidence,  the MAP and the  marginal MAP values, evaluating the algorithms on an array of problems with varying difficulties. As alluded to, this year we also include a new category that hosts the machine learning challenge: multi-label classification (MLC), extending the competition to exploring various learning algorithms.  We hope this event will continue to stimulate algorithms development and especially assess the state of the art in solvers for inference and learning  in graphical models. 

The timeline for the competition is as follows:

June, 2022

·       sample benchmarks to be released

·       solver submission opens (June 15th)

July, 2022

·       solver evaluations begin

August, 2022

·       mid-competition update (to be announced at UAI-2022)

            October, 2022

·       solver submissions close

·       final competition results announced!

More information can be found on this year’s competition website: https://uaicompetition.github.io/uci-2022/

We encourage anyone interested – whether new to the field or veterans – to join!  Please reach out to us via uaicompetition@gmail.com with any questions.

We look forward to hearing from you and including your solvers in the competition!

UAI-2022 Competition Organizers

Rina Dechter (University of California, Irvine)
Vibhav Gogate (University of Texas, Dallas)

Alexander Ihler (University of California, Irvine)

Junkyu Lee (IBM Research)

Bobak Pezeshki (University of California, Irvine)