Mango TV is a China leading high-quality video entertainment streaming platform, with a core focus on audio-visual interaction, integrating network characteristics and television characteristics to achieve a new media audio-visual integrated communication service platform that is unique, cross-screen, and self-produced. It is also the only internet video platform under Hunan Radio and Television.The Mango TV mobile app uses the latest AI technologies such as machine learning/deep learning to enhance personalized product experiences and provide better customized entertainment services for users. This competition we focus on LTV (lifetime value), or the lifetime value of a user, represents the total value a user creates for a business over their entire lifetime. The higher the LTV, the higher the monetization potential of the app’s traffic. Therefore, LTV is a key metric in the process of monetizing traffic. Retention and activity have a direct impact on LTV. The longer a user retains on the app, the more users will be retained, the more active they will be, the more resources will be available for consumption, and the more platform revenue will be created, and therefore the LTV will also be higher. So we want to build predictive models that accurately predict retention and activity over a period of time, and call that future user value.

Timeline of the competition:

1.April 15th,2023:Call for participation

2.April 25th,2023:Competition start date and open for submissions

3.June 23rd,2023:Team formation deadline

4.June 25th,2023:Deadline for submissions

5.July 2nd,2023:Winners will be announced officially and are contacted privately

6.19th-25th August 2023:Winners will be invited to present during a dedicated session at IJCAI 2023

Competition url: https://challenge.ai.mgtv.com/#/track/19?locale=en

Introducing the Resilient AI Challenge: an exciting competition where participants dive deep into the world of Intelligent Process Automation (IPA) systems. In this action-packed contest, you will gain hands-on experience with cutting-edge automation technologies. The focus is on robustness as you will design innovative solutions that can withstand the ever-changing landscape of automation tasks. Get ready to push the boundaries of AI-based algorithms, sharpen your problem-solving and critical thinking skills, and play an active role in shaping the future of IPA systems. Join the challenge and be part of the revolution in automation resiliency!

The competition goal: Gain practical experience with IPA technology by developing an AI bot that completes four automation tasks.

The timeline:

     April 2, 2023: Call for participation

     May 5, 2023: Deadline for registration

     July 1, 2023: Deadline for submission

     July 10, 2023: Winners will be announced officially (after they were contacted privately).
    Winners will be invited to present their solution at a special event in the IJCAI workshop AutoMate: 

Competition url: https://iparesiliency-ijcai23.github.io/

Developing a single agent that can master multiple games is an interesting and challenging task. The main difficulty is how the agent transfers the skills learned in a particular task to the other. In this competition, participants need to build a general AI that can perform well in different 2D sports games which shares similar elements in the map. These games are running, table-hockey, football, wrestling, billiards and curling. In addition, each game includes two adversarial players. This means that the participant needs to take the opponents into consideration and finish the task as quick as possible.

Timeline of the competition:

l  May 17th, 2023: The first phase of the warm-up round;

l  May 24th, 2023: The second phase of the warm-up round;

l  July 7th, 2023: The first phase of the final round;

l  July 21th, 2023:  the second phase of the final round;

 The results will be announced during IJCAI 2023

Competition url: http://jidiai.cn/ijcai_2023/

Badminton requires intense physical and tactical conditions to execute tactics and win the matches. However, applying intelligence technology to collect fine-grained badminton data and predict player performance remains unexplored due to the limited public badminton dataset. The goal of the competition consists of two tasks to stimulate effective solutions for badminton analytics. The automatic annotation of technical data for badminton match videos (Track 1) aims to design solutions with computer vision techniques to automatically annotate shot-by-shot data from match videos. The forecasting of future turn-based strokes in badminton rallies (Track 2) is to design predictive models that are able to forecast future strokes including shot types and locations based on past strokes. For more details, please feel free to visit our repo to check out our previous work.

Timeline:

April 1st, 2023 Call for participation

April 17th, 2023 Release the dataset and tutorial video

April 24th, 2023 Online submission release

May 10th, 2023 Registration deadline

June 13th, 2023 Testing data release

June 20th, 2023 Testing submission deadline (only prediction)

July 4th, 2023 Announce the winners

July 11th, 2023 Deadline for the paper submission (code and paper)

July 18th, 2023 Notification of the paper results

August 19th-25th, 2023 Winner presentations at IJCAI 2023

Competition URL: https://sites.google.com/view/coachai-challenge-2023/ 

The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further accelerate and foster research on detecting and analyzing deepfake speech utterances. Different from previous challenges (e.g. ADD 2022), ADD 2023 focuses on surpassing the constraints of binary real/fake classification, and actually localizing the manipulated intervals in a partially fake speech as well as pinpointing the source responsible for generating any fake audio. Five papers from the top-ranked teams in each track are invited to be submitted via the IJCAI paper submission system for review before final acceptance for presentation at the IJCAI 2023 Workshop on Deepfake Audio Detection and Analysis (DADA 2023, http://addchallenge.cn/dada2023).

Timeline of the competition:

March 13, 2023: The competition is open for registration

April 30, 2023: Deadline for submissions

May 5, 2023: Results and ranking release to participants

May 15, 2023: IJCAI Workshop paper submission deadline (by invitation)

June 5, 2023: JCAI 2023 DADA Workshop paper acceptance notification

Competition url: http://addchallenge.cn/add2023

The recent strides in robotics and artificial intelligence over the last decade have resulted in more and more robots sharing space and working together with humans in everyday life. This situation puts forth a lot of challenges and concerns that need to be addressed. Of these, understanding the interacting human’s mindset and their subjective satisfaction with the robot’s performance are very critical. One way to address these challenges is analysing the psychophysiological data of the interacting human. This competition encourages the participating teams to develop cutting-edge Signal Processing and/or Machine Learning approaches for the detection of erroneous behaviours using single-trial EEG data and test them on real hardware.

Timeline of the competition:

15 May 2023 Start of the competition & release of labelled training data sets

29 May 2023 Release of test data sets and additional information

25 June 2023 End of the offline stage & Deadline for submission*

24 July 2023 Announcement of selected teams for online stage, paper and poster presentations

06 Aug 2023 Deadline for online stage registration*

Aug 2023 IJCAI 2023 online competition (Exact date will be announced soon)

* All the deadlines are at 23:59 Anywhere on Earth

Competition URL: https://ijcai-23.dfki-bremen.de/competitions/inter-hri/ 

As artificial intelligence (AI) gains new capabilities, it becomes important to evaluate it on real-world tasks. While software such as ChatGPT has recently revolutionized certain areas of AI, athletic intelligence on real robotic systems seems to still be elusive in the AI community. To have better robots in the future which can perform a wide variety of dynamic tasks in uncertain environments, the physical or athletic intelligence of robots has to be improved. However, this is quite challenging since the fields of robotics and reinforcement learning (RL) lack standardized bench marking tasks on real hardware. To facilitate reproducibility and to stimulate algorithmic advancements, the AI Olympics competition is being held at IJCAI 2023 based on the RealAIGym project. The challenge will involve two stages: simulation and real-robot experiments where teams (and their agents) can compete to get the highest score on our leader boards and win some cool prizes! We invite people from all communities (AI, ML, RL, Optimal Control, Heuristics, or any combination of these approaches) to try this competition and submit their best efforts (in form of 2-4 page paper with accompanying code) in achieving very standard dynamic task (i.e. swingup and upright stabilization) on a canonical underactuated system known as acrobot or pendubot (double pendulum with single actuator).

The tentative challenge schedule is as follows:

31 March 2023      Website & Competition Release

1 June 2023           Paper and Controller Submission Deadline for Simulation Stage

15 June 2023         Selected Papers and Simulation Stage Winners Announcement, Start of the Real-Robot Stage Competition

30 July 2023           End of Remote Hardware Experiments

19-25 August          IJCAI 2023

* All the deadlines are at 23:59 Anywhere on Earth

Challenge URL: https://ijcai-23.dfki-bremen.de/competitions/ai_olympics/

The goal of the competition is to advance the research in computational social choice by leveraging multiagent simulations and machine learning techniques. The competition will focus on the principled evaluation and analysis of voting rules in a competitive setting. The competitors will develop and submit the code of their voting rules, which will then be compared in a tournament based on social welfare and axiomatic satisfiability.

Timeline:

  • April 15th, 2023: Call for participation.
  • July 1st, 2023: Submission deadline (code + report).
  • July 15th, 2023: Review and decision notifications.
  • August 1st, 2023: Final submission (code + report).

Competition URL:  https://compsoc.algocratic.org/

The 1st MiGA-IJCAI2023 Challenge is to explore using body gestures for hidden emotional state analysis. As an important non-verbal communicative fashion, human body gestures are capable of conveying emotional information during social communication. In previous works, efforts have been made mainly on facial expressions, speech, or expressive body gestures to interpret classical expressive emotions. Differently, we focus on a specific group of body gestures, called micro-gestures (MGs), used in the psychology research field to interpret inner human feelings. MGs are subtle and spontaneous body movements that are proven, together with micro-expressions, to be more reliable than normal facial expressions for conveying hidden emotional information. As it is the first year of MiGA, we will focus on two fundamental tasks of micro-gestures: classification on pre-segmented clips and online recognition MGs on long video sequences. As it is the 1st MiGA, we plan to set two fundamental challenge tasks (Tracks), and participating teams can choose to compete on one or both tasks. The challenge will be organized on the CodaLab website.

Timeline of the competition (might slightly adjust later):

Mar 27, 2023. Call for Challenge online. Registration starts.

Mar 31, 2023. Release of training data.

May 2, 2023. Release of testing data.

May 12, 2023. Final testing data and result submission. Registration ends.

May 15, 2023. Release of challenge results.

May 25, 2023. Paper submission deadline (to workshop).

June 05, 2023. Notification to authors.

June 10, 2023. Camera-ready deadline.

August, 2023. MiGA IJCAI 2023 Workshop, Macao, China.

Competition url: https://cv-ac.github.io/MiGA2023/

Description: The task of this competition is to develop a computer program to play Official International Mahjong. Participants can upload their agents to our online platform, Botzone, which has an ELO ranking system and a tournament system to evaluate their performance. In 2020 and 2022 we held the first two Mahjong AI competition in IJCAI, and algorithms using deep learning turned out to perform well in this game. However, the top agents submitted by participants still cannot beat the best humans. The long-term goal of this competition is to build an intelligent agent that can beat professional players in this game, and we will continue to hold it until this game is solved. 

Timeline: 

March 5th  –  Call for participation 

May 21st  –  Submission deadline for elimination round 

May 26th  –  Notification to finalists 

July 2nd  –  Submission deadline for the final 

July 9th  –  Notification of final results 

Competition url: https://botzone.org.cn/static/gamecontest2023a.html 

Research on 3D mapping plays a vital role in improving our quality of life through numerous smart city applications. However, acquiring 3D data can be expensive, rendering frequent or large-scale data updates impractical. To address this issue, AI technologies are explored to infer 3D information from easily accessible 2D images. Under this backdrop, AI Singapore, in collaboration with Singapore Land Authority, is launching a Visual Localisation Challenge, with an aim to address the problem of “How can AI be used to accurately extract camera pose data from 2D images?”. By leveraging advancements in visual odometry, we hope to push the boundaries of 3D learning and make it more affordable and sustainable for a broader range of real-world applications.

Challenge Timeline:

Start Date: 26 May 2023

Entry Deadline: 26 July 2023 (AoE)

Winner Announcement: 14-16 Aug 2023

Final Presentation and Award Ceremony: 19-25 August 2023 (hosted by IJCAI-23)

Competition url: https://aisingapore.org/technology/prize-based-challenges/aisg-sla-visual-localisation-challenge/

The goal of the competition is to build AI agents for a 2 player collaborative physics-based puzzle platformer game (Geometry Friends). Each agent controls a different character (circle or rectangle) with distinct characteristics. Their goal is to collaborate in order to collect all diamonds in a set of levels as fast as possible. The competition raises several problems for collaborative AI agents. For example, to successfully solve a GF level the AI agents need to: (1) deal with coordination at different layers: from motion control (e.g. achieving perfect timing) to level resolution (e.g. devising shared plans); deal with limited actuation situated in a simulated physics environment (with gravity and friction); (3) solve platform (skill) based puzzles, which involves discovering the proper order to collect the diamonds and identifying the points where collaboration is needed; and (4) do all the above in real-time.

Timeline of the competition:

April 15th, 2023: The competition is open for submissions
August 16th, 2023: Deadline for submissions

The results will be announced during IJCAI 2023

Competition url: https://geometryfriends.gaips.inesc-id.pt/

The task of this competition is to develop a computer program that can successfully play Angry Birds. The long term goal is to build an intelligent Angry Birds playing agent that can play new levels better than the best human players. This is a difficult problem as it requires agents to predict the outcome of physical actions without having complete knowledge of the world, and then to select a good action out of infinitely many possible actions. This is an essential capability of future AI systems that interact with the physical world. The Angry Birds AI competition provides a simplified and controlled environment for developing and testing these capabilities. In addition to the Standard Track, in 2023 we again run the Novelty Track where we introduce novel components to the game during the competition (e.g., new game objects, or changes in properties of existing game objects) and agents are tasked with detecting when novelty occurs and to adjust their strategies to the novelty accordingly.

Timeline of the competition:

·         July 10th, 2023: Early registration

·         August 11th, 2023: Late Registration

·         August 2nd, 2023: Agent submission for testing (Novelty Track)

·         August 11th, 2023: : Agent submission for testing (Standard Track)

·         August 15th, 2023: Final Agent submission (Novelty Track)

·         August 18th, 2023: Final Agent submission (Standard Track)Competition url: http://aibirds.org/