Competitions and Challenges

Short description:
Large Language Models (LLMs) have demonstrated significant capabilities in understanding and reasoning, gradually reshaping people’s lifestyles and work patterns.With the powerful support of large language models (LLMs), we are delighted to announce the launch of a recommendation system and knowledge Q&A competition. We cordially invite researchers from around the world to participate and challenge the boundaries of innovation in this field. The competition aims to drive advancements in recommendation systems and knowledge Q&A by leveraging state-of-the-art artificial intelligence technology to explore new frontiers in personalized recommendations and intelligent Q&A. Whether you are an expert in the field or a newcomer, your participation is welcomed as we jointly shape the future of learning and knowledge exchange. Let’s work together to propel the application and development of artificial intelligence technology in recommendation systems and knowledge Q&A.

Website link: https://challenge.ai.mgtv.com/#/home?locale=en

Competition timeline:
Competition announcement date: 2024-05-27
Competition start date: 2024-05-27
Submission deadline: 2024-07-27

Short description:
Multimodal emotion recognition is an active research topic in artificial intelligence. Its main goal is to integrate multi-modalities to identify human emotional states. Current works generally assume accurate emotion labels for benchmark datasets and focus on developing more effective architectures. However, existing technologies are difficult to meet the demand for practical applications. To this end, we organize MER series challenges. We hope to bring together researchers around the world to further discuss recent research and future directions for robust multimodal emotion recognition.

Website link: https://zeroqiaoba.github.io/MER2024-website

Competition timeline:
April 30, 2024: Data, baseline paper & code available
June 30, 2024: Results submission start
July 10, 2024: Results submission deadline

Short description:
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!

Website link: https://sites.google.com/view/ipacompetitionijcai24/home

Competition timeline:
* May 18th, 2024: Call for participation open
* May 20th, 2024: Registration open
* July 15 th, 2024: Final submission deadline
* August 5th, 2024: Announcement of the results at IJCAI 2024 AutoMates workshop

Short description:
The goal of the competition is to advance research in computational social choice by leveraging multi-agent simulations and machine learning techniques. The competition will focus on the principled evaluation and analysis of voting rules in competitive settings. Competitors will develop and submit code for their voting rules, which will then be compared in online tournaments.

Website link: https://compsoc.algocratic.org

Competition timeline:
* May 15th, 2024: Call for participation open.
* May 20th, 2024: Registration open.
* June 20th, 2024: Initial submission deadline.
* June 25th, 2024: Review and initial feedback.
* July 25th, 2024: Final submission deadline.
* August 3-9th, 2024: Announcement of the results at IJCAI 2024.

Short description:
Aerodynamic drag plays a pivotal role in shaping the performance and efficiency of vehicles, particularly within the automotive and aerospace industries. Traditionally, the prediction of aerodynamic drag relies on time-consuming and computationally intensive simulations, posing challenges for swift design iterations. However, recent strides in deep learning, especially in the realm of AI for Science, provide an innovative approach by directly learning from data.
To illustrate, consider a standard aerodynamics dataset featuring 3D vehicle geometries with Reynolds numbers reaching as high as five million. Traditional numerical methods demand O(10^3) seconds to compute vehicle surface pressure, a crucial parameter for calculating aerodynamic drag. In contrast, ML can discern relationships between design parameters (e.g., shape, surface features) and aerodynamic drag through training on simulation data. Once trained, the ML model can rapidly predict aerodynamic drag for new designs in O(10^-1) seconds, markedly curtailing computational resource requirements.

Website link: https://competition.atomgit.com/competitionInfo?id=7f3f276465e9e845fd3a811d2d6925b5

Competition timeline:
– April 23: Registration opens and initial data is released. Participants will use the initial data to familiarize themselves with the problem.
– May 1: Full data release. We will release all datasets, packages, and baseline code.
– May 21: Public leaderboard submission starts. All teams can try a demonstration submission to ensure a smooth final test submission.
– July 7: Registration and team merging close. Pravite leaderboard dataset will be open for team test submissions.
– July 14: Final submission deadline. Each team submits its final report and test predictions, which will be evaluated over the entire test data.
– July 21: Winners announced. The winning team will be invited to a conference to share their work!
Note: The specific deadline is set to “anytime on Earth”.

Short description:
Join the 2nd Scientific Figure Captioning (SciCap) Challenge! We will supply each team with approximately 400,000 scientific figure images from various arXiv papers, including their respective captions and relevant paragraphs. Teams will then use these data to build computational models to generate captions for these images. Whether you are working alone or as a team, we welcome researchers, AI/NLP/CV practitioners, and anyone interested in computational models for generating useful text for visuals to participate and submit their results. Check out the details of the challenge, including data, code, baselines, evaluation criteria, and important dates. We eagerly await your participation in the 2nd SciCap Challenge!
For questions about the challenge, email us at (scicap-challenge@googlegroups.com)

Website link: http://scicap.ai/

Competition timeline:
– SciCap Challenge launches: April 15, 2024
– Challenge ends: June 15, 2024, 23:59 PM (CST)
– Technical report submission deadline: June 22, 2024, 23:59 PM (CST)
– Challenge result notification: July 3, 2024

Short description:
The VRD-IU(Visually Rich Document Intelligence and Understanding) competition aims to tackle the obstacles presented by the diverse and complex nature of form-like documents, which frequently involve multiple stakeholders and contain essential information that is challenging to extract. This competition, based on the Form-NLU Dataset featuring digital, printed, and handwritten forms, offers two tracks catering to participants’ varying skill levels. Tasks range from extracting key information (Track A) to localising it within documents (Track B), ensuring engagement across proficiency levels in advancing visually rich document understanding technology. This initiative not only accelerates advancements in document understanding but also aims to draw increased interest and engagement in this field, presenting a prime opportunity for innovators to contribute to the evolution of efficient information extraction and analysis methodologies.

Website link: https://doc-iu.github.io/

Competition timeline:
– Data, baseline paper & code available: 29 April, 2024
– Track A Challenge Due: 10 July, 2024
– Track B Challenge Due: 15 July, 2024
– Announcement of Winners: 20 July, 2024
– Paper Submission Due: 27 July, 2024
– Competition: 05 August, 2024
Note: All deadlines are Anywhere on Earth (UTC – 12) time.

Short description:
As voice synthesis technology continues to evolve, the line between cloned and genuine voices has become increasingly blurred, posing significant challenges to data security and asset protection.
The objective of this competition is to inspire innovation among AI algorithm enthusiasts and experts worldwide, fostering collaborative efforts to elevate awareness of voice cloning and fight scams using deepfakes. Contenders are required to employ deep learning technologies to train models and algorithms based on the test dataset provided by FinVolution.
This challenge not only tests technical prowess but also underscores contenders’ ethical responsibilities. Through this competition, they will have the opportunity to demonstrate their technical skills, striking a balance between technological advances and user data protection.
Moreover, this competition seeks to deter individuals or groups attempting to misuse AI for fraudulent activities. FinVolution has long championed the role of AI as a force for good and encourages industry practitioners to abide by Isaac Asimov’s Three Laws, ensuring responsible use of AI within legal boundaries and ethical frameworks.

Website link:
https://ai.ppdai.com/mirror/show

Competition timeline:
* May 10th, 2024: Call for registration and participation, and dataset for Preliminary is released
* June 12nd, 2024: Preliminary review and feedback, to release the results and ranking
* June 13rd, 2024: Dataset for Semi-final is released and to do second round evaluation
* June 28th, 2024: Semi-final review and feedback, to release the results and ranking
* June 29th-July 15th, 2024: Materials submission and review for the Final
* July 23rd, 2024: Announcement of the final results
* August 3-9th, 2024: Presentation at IJCAI 2024