{
"fetched_at": "2026-10-19T07:18:50Z",
"source_url": "https://www.kaggle.com/competitions/aaai-25-visually-rich-document-vrd-iu-leaderboard/data",
"pages": [
{
"name": "data-description",
"content": "Each report consists of a collection of detected semantic entities (such as *section*, *paragraph*, *table*, *caption*, etc.), though these entities are only labelled with semantic categories in the training set. The task is to predict the logical structure by defining hierarchical relationships between the semantic entities within each report. Specifically:\n\n**Hierarchical Relation Prediction**: Determine the parent-child relationships between document entities. For instance, if an entity “Section” is found to be the parent of a “Paragraph” entity, it indicates that the paragraph belongs to that section.\n\n**Directional Relation:** Relationships are unidirectional, meaning if \"Section\" is the parent of \"Paragraph,\" the reverse does not hold.\n\n**Non-Bidirectional Relationships:** For each document, the aim is to construct a hierarchical tree where each entity only points upward to its parent entity, not downward to child entities.\n\nThis task requires participants to use available training data to model these logical relationships, which will help in accurate hierarchical structure prediction in the test set, where entity categories are recognized, but relationships need to be inferred.\n\nNote: We provide the official tutorials (Data Exploration, Baseline Model) to assist participants in understanding the data structure and starting this competition easily. You can also find the tutorial links under the Code menu.\n## Files\n\nIn this competition, participants can use the training dataset to develop their model, and the original validation and testing dataset will be used for leaderboard evaluation. We offer an official tutorial to help users quickly understand the dataset format and structure, making it easier for participants to get started with the competition. Link for [**dataset exploration tutorial**](https://colab.research.google.com/drive/1L3ADDnZMpPiTa_RlHgnpb_7Hdhbn5G94?usp=sharing) can be found here: (url). This dataset consists of three main splits: training, validation, and testing. For each split, we provide two types of files:\n\n\n###PKL files\nWe've provided detailed pkl files containing essential information about document splits. The pkl file is a valuable resource as it contains essential document information, including the detected entities within each document with their responding IDs, parent-child relationship, labels, bounding boxes, textual contents inside each bounding box and the image ID of the document. This information is crucial for understanding the hierarchical structure of the visually rich documents. \n\n\n###Image Files\nWe provide the document images for each data split. Participants can use the information provided by the PKL file to locate the document images of each target document. Image files can provide additional layouts and visual cues to make the feature representation more comprehensive.\n\nWe also provide a default baseline using the multimodal transform where the feature extraction is based on BERT for textual feature and RoI for image feature, separately. The link can be found here:\n\n[https://colab.research.google.com/drive/1CiQriTC7EVsEzROm_oIPTCvq208550Dz?usp=sharing](url)\n[https://colab.research.google.com/drive/17QHaJ8ZaJAANkMl2lxQQ5d9dx_2gkafQ](url)\n[https://colab.research.google.com/drive/1OUoq5vdGl_uAhf4E42Gx4Blcvg7L0Q-M?usp=sharing](url)\nWith this dataset, you can explore the challenging task of training your model to predict the parent-child relationship for each of the detected entities.. The provided files are meant to assist you in building a robust and accurate model for this competition. We hope this dataset will inspire creative solutions and foster progress in this data, Happy modelling!\n\n",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Description",
"content": "Welcome to the Visually-Rich Document(VRD) Intelligence and Understanding Kaggle competition! This competition is the sub-activity of **The Third Competition on Visually Rich Document Intelligence and Understanding (VRDIU)** in conjunction with the **39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025)** in **Philadelphia, Pennsylvania, USA**. Please visit the [VRDIU competition] (https://sites.google.com/view/docui-aaai25/cfp?authuser=0) for a detailed competition schedule and important dates. \n\n### Task Background \nDocument parsing aims to build a structured, hierarchical understanding of visually rich documents by identifying and recognizing logical relationships between semantic entities. This structured understanding is crucial in various domains, such as academic papers, business reports, and government documents, where semantic entities like sections, subsections, tables, and figures contribute to an organized document flow. Document parsing follows document layout analysis as a downstream task, leveraging the layout structure to infer parent-child relationships between entities. For example, in an academic paper, a “Section” entity can contain multiple “Subsections,” and captions are directly associated with their corresponding figure or table bodies.\n\nIn this competition, the objective is to perform document structure parsing on mining reports provided by various companies. The complexity arises as many of these reports are unstructured or scanned, presenting a unique challenge in achieving a consistent and accurate parsing outcome. Understanding the logical structure in these documents is fundamental for downstream content understanding tasks, such as key information extraction, question answering, and hierarchical organization of document content.\n\n\n\n\n\n### Task Definition\nEach report comprises a collection of detected semantic entity bounding boxes in the format (x, y, w, h), where (x, y) represents the coordinates of the top-left corner, and (w, h) denotes the width and height of the semantic entity. These entities, such as *section*, *paragraph*, *table*, and *caption*, are labelled with semantic categories in the training set. The objective is to predict the logical structure of each report by establishing hierarchical relationships between these semantic entities. This involves defining how the entities are organized and nested to accurately represent the document's logical flow and structure. \nSpecifically:\n\n**Hierarchical Relation Prediction:** Determine the parent-child relationships between document entities. For instance, if an entity “Section” is found to be the parent of a “Paragraph” entity, it indicates that the paragraph belongs to that section.\n**Directional Relation:** Relationships are unidirectional, meaning if \"Section\" is the parent of \"Paragraph,\" the reverse does not hold.\n**Non-Bidirectional Relationships:** For each document, the aim is to construct a hierarchical tree where each entity only points upward to its parent entity, not downward to child entities.\n\nThis task requires participants to use available training data to model these logical relationships, which will help in accurate hierarchical structure prediction in the test set, where entity categories are recognized, but relationships need to be inferred. For example, given a document with *N* detected entities, the desired output format should be a list containing the parent entity for each of the *N* entities. ***The evaluation metric is F1.***\n\nBefore conducting this competition, please ensure you read and understand the **Rules** of this competition first. Please get in touch with us anytime if you get confused about this competition. **Note a strong baseline model is provided for starting this competition!**\n\nTherefore, gather your expertise in computer vision, natural language processing, and deep learning, and join us in this competition. Engage with a vibrant community of like-minded individuals, exchange ideas, and strive for the top spot on the leaderboard. Together, let's push the boundaries of document structure parsing and shape the future of intelligent document analysis.\n\nYou can scan the following QR code for more details:\n\n\nCOMPETITION SPONSOR: Google Research\n![](\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F5589143%2F63363ecec589e9174bf34746116c85b6%2Fsponsor.png?generation=1712029907388272&alt=media\")
\n\n\nIf you have more questions or inquiries about this competition, feel free to fill out this competition QA form. Our organising teams will answer your questions within three working days.\n\n",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Evaluation",
"content": "The accuracy score is calculated as the ratio of correctly predicted samples to the total number of samples. It can be defined as:\n\n \\[ \\text{Accuracy} = \\frac{\\sum_{i=1}^{N} \\mathbb{1}(\\hat{y}_i = y_i)}{N} \\]
\n\nWhere \\( N \\) is the number of samples, \n\n\nN is the total number of samples. y_hat_i is the predicted label for the i-th sample. y_i is the true label for the i-th sample. 1(y_hat_i = y_i) is an indicator function that returns 1 if the predicted label (y_hat_i) matches the true label (y_i) (correct prediction) and 0 otherwise.\n",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "rules",
"content": "##**One account per participant**\nYou cannot sign up to Kaggle from multiple accounts and, therefore, cannot submit from multiple accounts.\n##**No private sharing outside teams**\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n##**Team Mergers**\nTeam mergers are allowed and can be performed by the team leader. To merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the Team Merger Deadline. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.\n##**Team Limits**\nThe maximum team size is **4**.\n##**Submission Limits**\nYou may submit a maximum of 5 entries per day.\nYou can only select up to 2 final submissions for judging.\n##**Competition Timeline**\nCompetition Timeline dates (including Entry Deadline, Final Submission Deadline, Start Date, and Team Merger Deadline, as applicable) are reflected on the competition’s Overview > Timeline page.\n\n##**COMPETITION-SPECIFIC TERMS**\n- COMPETITION TITLE: The Third Competition on Visually Rich Document Intelligence and Understanding (VRDIU)\n\n- COMPETITION SPONSOR: Google Research\n\n\n- COMPETITION WEBSITE: https://www.kaggle.com/competitions/vrd-iu2024-trackA\n\n- HOSTED WORKSHOP WEBSITE: https://doc-iu.github.io/\n\n- TOTAL PRIZES AVAILABLE:\n**WINNER LICENSE TYPE**: Non-Exclusive\n\n**DATA ACCESS AND USE**: Custom - Competition Use Only\n\nCompetitions are open to world residents, **except if you are a resident of the United Nations Security Council (UNSC) and Australian autonomous sanctions regimes**, you **may not** enter the Competition. Other local rules and regulations may apply to you, so please check your local laws to ensure you are eligible to participate in skills-based competitions. The Competition Sponsor reserves the right to award alternative Prizes where needed to comply with local laws.\n\nThe Competition named above is a skills-based competition to promote and further the field of natural language processing and computer vision. You must register via the Competition Website to enter. Your competition submissions (\"Submissions\") must conform to the requirements stated on the Competition Website. Your Submissions will be scored based on the evaluation metric described on the Competition Website. Subject to compliance with the Competition Rules, Prizes, if any, will be awarded to participants with the best scores based on the merits of the data science models submitted. See below for the complete Competition Rules.\n\n**ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.**\n\n# **A. COMPETITION-SPECIFIC RULES**\nIn addition to the provisions of the General Competition Rules below, you understand and agree to these Competition-Specific Rules required by the Competition Sponsor:\n\n## EXTERNAL DATA\nThe following provision supersedes General Rules Section 7.C. below: “Unless otherwise expressly stated on the Competition Website, you may not use data other than the Competition Data to develop and test your models and Submissions. Competition Sponsor reserves the right to disqualify any Participant who Competition Sponsor discovers has undertaken or attempted to undertake the use of data other than the Competition Data, or who uses the Competition Data other than as permitted by the Competition Website and these Rules.\"\n\n## **1. WINNER LICENSE.**\nUnder Section 11 (Winners Obligations) of the General Rules below, you hereby grant and will grant Competition Sponsor the following license(s) for your Submission if you are a Competition winner:\n\nNon-Exclusive: You hereby grant and will grant to Competition Sponsor and its designees a worldwide, non-exclusive, sub-licensable, transferable, fully paid-up, royalty-free, perpetual, irrevocable right to use, reproduce, distribute, create derivative works of, publicly perform, publicly display, digitally perform, make, have made, sell, offer for sale and import your winning Submission and the source code used to generate the Submission, in any media now known or developed in the future, for any purpose whatsoever, commercial or otherwise, without further approval by or payment to you. To the extent your Submission makes use of generally commercially available software not owned by you that you used to generate your Submission, but the Competition Sponsor can procure that without undue expense, you do not grant the license in the preceding sentence to that software.\n\n## **2. AUTOMATED MACHINE LEARNING TOOLS (AMLT).**\nIndividual participants and Teams may use automated machine learning tool(s) (“AMLT”) (e.g., Google AutoML, H2O Driverless AI, etc.) to create a Submission, provided that the participant or Team ensures that they have an appropriate license to the AMLT such that they can comply with the Competition Rules.\n\nThe following provision is added to the end of Section 11 of the General Competition Rules below: “Individual participants and Teams who create a Submission using an AMLT may win a Prize. However, for clarity, the potential winner’s Submission must still meet the requirements of these Rules, including but not limited to Section A.1 (Winners License), Section B.11 (Winners Obligations), and Section B.17 (Warranty, Indemnity, and Release).”\n\n# **B. GENERAL COMPETITION RULES**\n## **1. BINDING AGREEMENT.**\nTo enter the Competition, you must agree to these Official Competition Rules, which incorporate by reference the provisions and content of the Competition Website and any Specific Competition Rules above (collectively, the \"Rules\"). Please read these Rules carefully before entry to ensure you understand and agree. You further agree that submitting an entry in the Competition constitutes agreement to these Rules. You may not submit an entry to the Competition and are not eligible to receive the prizes associated with this Competition (“Prizes”) unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor concerning the Competition.\n\n## 2. ELIGIBILITY. \nA. To be eligible to enter the Competition, you must be:\n(i) a registered account holder at Kaggle.com;\n(ii) the older of 18 years old or the age of majority in your jurisdiction of residence (unless otherwise agreed to by Competition Sponsor and appropriate parental/guardian consents have been obtained by Competition Sponsor);\n(iii) not a resident of Crimea, the so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, or North Korea; and\n(iv) not a person or representative of an entity under U.S. export controls or sanctions (see https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx).\n\nSuppose you are entering as a representative of a company, educational institution or other legal entity or on behalf of your employer. In that case, these rules are binding on you, individually, and the entity you represent or are an employee. Suppose you act within the scope of your employment as an employee, contractor, or agent of another party. In that case, you warrant that such party has full knowledge of your actions and consent, including your potential receipt of a Prize. You warrant that your actions do not violate your employer's or entity's policies and procedures.\n\nThe Competition Sponsor reserves the right to verify eligibility and to adjudicate on any dispute at any time. Suppose you provide any false information relating to the Competition concerning your identity, residency, mailing address, telephone number, email address, ownership of right, or information required for entering the Competition. In that case, you may be immediately disqualified from the Competition.\n\nB. Unless otherwise stated in the Specific Competition Rules above or prohibited by internal policies of the Competition Entities, employees, interns, contractors, officers and directors of Competition Entities may enter and participate in the Competition but are not eligible to win any Prizes. \"Competition Entities\" means the Competition Sponsor, Kaggle Inc., and their respective parent companies, subsidiaries and affiliates. If you are such a participant from a Competition Entity, you are subject to all applicable internal policies of your employer to your participation.\n\n## **3. SPONSOR AND HOSTING PLATFORM.**\nThe Competition is sponsored by Competition Sponsor named above. The Competition is hosted by the Competition Sponsor, Kaggle Inc. (\"Kaggle\"). Kaggle is an independent contractor of the Competition Sponsor and is not a party to this or any agreement between you and Competition Sponsor. You understand that Kaggle has no responsibility for selecting the potential Competition winner(s) or awarding any Prizes. Kaggle will perform certain administrative functions relating to hosting the Competition, and you agree to abide by the provisions relating to Kaggle under these Rules. As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at www.kaggle.com/terms in addition to these Rules.\n\n## 4. COMPETITION PERIOD.\nFor the purposes of Prizes, the Competition will run from the Start Date and time to the Final Submission Deadline (such duration the “Competition Period”). The Competition Timeline is subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.\n\n## 5. COMPETITION ENTRY. \nNO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website before the Entry Deadline and follow the instructions for developing and entering your Submission through the Competition Website. Your Submissions must be made in the manner and format and in compliance with all other requirements stated on the Competition Website (the \"Requirements\"). Submissions must be received before any Submission deadlines stated on the Competition Website. Submissions not received by the stated deadlines will not be eligible to receive a Prize.\n\nSubmissions may not use or incorporate information from hand labelling or human prediction of the validation dataset or test data records.\n\nIf the Competition is a multi-stage competition with temporally separate training and/or test data, one or more valid Submissions may be required during each Competition stage in the manner described on the Competition Website for the Submissions to be Prize eligible.\n\nSubmissions are void if they are in whole or part illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. Competition Sponsor reserves the right to disqualify any entrant who does not follow these Rules, including making a Submission that does not meet the Requirements.\n\n## 6. INDIVIDUALS AND TEAMS.\nA. Individual Account. You may make Submissions only under one unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of daily Submissions as specified on the Competition Website.\n\nB. Teams. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a team (a \"Team\"); however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size on the Competition Website.\n\nC. Team Merger. Teams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules.\n\n## 7. COMPETITION DATA.\n\"Competition Data\" means the data or datasets available from the Competition Website for use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to participants.\n\nA. Data Access and Use.\nCompetition Use Only: You may access and use the Competition Data only for participating in the Competition and on Kaggle.com forums. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.\n\nB. Data Security. You agree to use reasonable and suitable measures to prevent persons who have not formally agreed to these Rules from gaining access to the Competition Data. You agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Competition Data to any party not participating in the Competition. You agree to notify Kaggle immediately upon learning of any possible unauthorized transmission of or unauthorized access to the Competition Data and agree to work with Kaggle to rectify any unauthorized transmission or access.\n\nC. External Data. (Please refer to the \"External Data\" under \"COMPETITION-SPECIFIC RULES\") You may use data other than the Competition Data (“External Data”) to develop and test your Submissions. However, you will ensure the External Data is publicly available and equally accessible to all participants of the Competition for purposes of the competition at no cost to the other participants. The ability to use External Data under Section 7.C (External Data) does not limit your other obligations under these Competition Rules, including but not limited to Section 11 (Winners Obligations).\n\n## 8. SUBMISSION CODE REQUIREMENTS.\nA. Private Code Sharing. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition Period, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data or other source or executable code relevant to the Competition (“Competition Code”). This prohibition includes sharing Competition Code between separate Teams unless a Team merger occurs. Any such sharing of the Competition Code breaches these Competition Rules and may result in disqualification.\n\nB. Public Code Sharing. You are permitted to share Competition Code publicly, provided that such public sharing does not violate the intellectual property rights of any third party. If you do choose to share Competition Code or other such code, you are required to share it on Kaggle.com on the discussion forum or notebooks associated specifically with the Competition for the benefit of all competitors. By so sharing, you are deemed to have licensed the shared code under an Open Source Initiative-approved license (see www.opensource.org) that in no event limits commercial use of such Competition Code or model containing or depending on such Competition Code.\n\nC. Use of Open Source. Unless otherwise stated in the Specific Competition Rules above, if open source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see www.opensource.org) that in no event limits commercial use of such code or model containing or depending on such code.\n\n## 9. DETERMINING WINNERS. \nEach Submission will be scored and ranked by the evaluation metric on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's public leaderboard. The potential winner(s) are determined solely by the leaderboard ranking on the private leaderboard, subject to compliance with these Rules. The public leaderboard will be based on the public test set, and the private leaderboard will be based on the private test set.\n\nIn the event of a tie, the Submission entered first into the Competition will be the winner. If a potential winner is disqualified, the Submission that received the next highest score rank will be chosen as the potential winner.\n\n## 10. NOTIFICATION OF WINNERS & DISQUALIFICATION.\nThe potential winner(s) will be notified by email.\n\nIf a potential winner (i) does not respond to the notification attempt within one (1) week from the first notification attempt or (ii) notifies Kaggle within one week after the Final Submission Deadline that the potential winner does not want to be nominated as a winner or does not want to receive a Prize, then, in each case (i) and (ii) such potential winner will not receive any Prize, and an alternate potential winner will be selected from among all eligible entries received based on the Competition’s judging criteria.\n\nIn case (i) and (ii) above, Kaggle may disqualify the participant. However, in case (ii) above, if requested by Kaggle, such potential winner may provide code and documentation to verify the participant’s compliance with these Rules. If the potential winner provides code and documentation to the satisfaction of Kaggle, the participant will not be disqualified under this paragraph.\n\nCompetition Sponsor reserves the right to disqualify any participant from the Competition if the Competition Sponsor reasonably believes that the participant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other participants, Competition Sponsor or Kaggle.\n\nA disqualified participant may be removed from the Competition leaderboard at Kaggle's discretion. If a Participant is removed from the Competition Leaderboard, additional winning features associated with the Kaggle competition platform, for example, Kaggle points or medals, may also not be awarded.\n\nThe final leaderboard list will be publicly displayed at Kaggle.com. Determinations of the Competition Sponsor are final and binding.\n\n## 11. WINNERS OBLIGATIONS.\nAs a condition to being awarded a Prize, a Prize winner must fulfil the following obligations:\n\n(a) deliver to the Competition Sponsor the final model's software code to generate the winning Submission and associated documentation. The delivered software code should follow these documentation guidelines, must be capable of generating the winning Submission, and contain a description of resources required to build and/or run the executable code successfully. To the extent that the final model’s software code includes generally commercially available software that is not owned by you, but the Competition Sponsor can procure that without undue expense, then instead of delivering the code for that software to the Competition Sponsor, you must identify that software, method for procuring it, and any parameters or other information necessary to replicate the winning Submission;\n\n(b) grant to the Competition Sponsor the license to the winning Submission stated in the Competition Specific Rules above, and represent that you have the unrestricted right to grant that license;\n\n(c) sign and return all Prize acceptance documents as may be required by Competition Sponsor or Kaggle, including without limitation: (i) eligibility certifications; (ii) licenses, releases and other agreements required under the Rules; and (iii) U.S. tax forms (such as IRS Form W-9 if U.S. resident, IRS Form W-8BEN if foreign resident, or future equivalents).\n\n## 12. PRIZES. \nPrize(s) are as described on the Competition Website and are only available for winning during the period described on the Competition Website. The odds of winning any Prize depend on the number of eligible Submissions received during the Competition Period and the participants' skills.\n\nAll Prizes are subject to the Competition Sponsor's review and verification of the participant’s eligibility and compliance with these Rules and the compliance of the winning Submissions with the Submissions Requirements. If the Submission demonstrates non-compliance with these Competition Rules, Competition Sponsor may at its discretion take either of the following actions: (i) disqualify the Submission(s); or (ii) require the potential winner to remediate within one week after notice all issues identified in the Submission(s) (including, without limitation, the resolution of license conflicts, the fulfilment of all obligations required by software licenses, and the removal of any software that violates the software restrictions).\n\nA potential winner may decline to be nominated as a Competition winner by Section 10.\n\nPotential winners must return all required Prize acceptance documents within two (2) weeks following notification of such required documents, or such potential winner will be deemed to have forfeited the prize, and another potential winner will be selected. Prize(s) will be awarded within approximately 30 days after receipt by the Competition Sponsor or Kaggle of the required Prize acceptance documents. Transfer or assignment of a Prize is not allowed.\n\nYou are not eligible to receive any Prize if you do not meet the Eligibility requirements in Section 2 above.\n\nIf a Team wins a monetary Prize, the Prize money will be allocated in even shares between the eligible Team members unless the Team unanimously opts for a different Prize split and notifies Kaggle before Prizes are issued.\n\n## 13. TAXES.\nALL TAXES IMPOSED ON PRIZES ARE THE SOLE RESPONSIBILITY OF THE WINNERS. Payments to potential winners are subject to the express requirement that they submit all documentation requested by Competition Sponsor or Kaggle for compliance with applicable state, federal, local and foreign (including provincial) tax reporting and withholding requirements. Prizes will be net of any taxes that the Competition Sponsor must legally withhold. If a potential winner fails to provide any required documentation or comply with applicable laws, the Prize may be forfeited and Competition Sponsor may select an alternative potential winner. Any winners who are U.S. residents will receive an IRS Form-1099 in the amount of their Prize.\n\n## 14. GENERAL CONDITIONS. \nAll federal, state, provincial and local laws and regulations apply.\n\n## 15. PUBLICITY.\nYou agree that Competition Sponsor, Kaggle and its affiliates may use your name and likeness for advertising and promotional purposes without additional compensation unless prohibited by law.\n\n## 16. PRIVACY.\nYou acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to name, mailing address, phone number, and email address (“Personal Information”). Kaggle acts as an independent controller about the collection, storage, sharing, and other use of this Personal Information. It will use this Personal Information by its Privacy Policy , including for administering the Competition. As a Kaggle.com account holder, you have the right to request access to, review, rectification, portability or deletion of any personal data held by Kaggle about you by logging into your account and/or contacting Kaggle Support at .\n\nAs part of the Competition Sponsor performing this contract between you and the Competition Sponsor, Kaggle will transfer your Personal Information to the Competition Sponsor, which acts as an independent controller of this Personal Information. As a controller of such Personal Information, Competition Sponsor agrees to comply with all U.S. and foreign data protection obligations about your Personal Information. Kaggle will transfer your Personal Information to Competition Sponsor in the country specified in the Competition Sponsor Address listed above, which may be outside your residence. Such a country may not have privacy laws and regulations similar to those of the country of your residence.\n\n## 17. WARRANTY, INDEMNITY AND RELEASE.\nYou warrant that your Submission is your original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses. You agree not to make any Submission that: (i) infringes any third-party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; or (ii) otherwise violates any applicable U.S. or foreign state or federal law.\n\nTo the maximum extent permitted by law, you indemnify and agree to keep indemnified Competition Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any of your acts, defaults or omissions and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the Competition Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules or any applicable U.S. or foreign state or federal law; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the Competition; and (e) your acceptance, possession, misuse or use of any Prize, or your participation in the Competition and any Competition-related activity.\n\nYou hereby release Competition Entities from any liability associated with (a) any malfunction or other problem with the Competition Website; (b) any error in the collection, processing, or retention of any Submission; or (c) any typographical or other error in the printing, offering or announcement of any Prize or winners.\n\n## 18. INTERNET.\nCompetition Entities are not responsible for any malfunction of the Competition Website or any late, lost, damaged, misdirected, incomplete, illegible, undeliverable, or destroyed Submissions or entry materials due to system errors, failed, incomplete or garbled computer or other telecommunication transmission malfunctions, hardware or software failures of any kind, lost or unavailable network connections, typographical or system/human errors and failures, technical malfunction(s) of any telephone network or lines, cable connections, satellite transmissions, servers or providers, or computer equipment, traffic congestion on the Internet or at the Competition Website, or any combination thereof, which may limit a participant’s ability to participate.\n\n## 19. RIGHT TO CANCEL, MODIFY OR DISQUALIFY.\nIf, for any reason, the Competition is not capable of running as planned, including infection by computer viruses, bugs, tampering, unauthorized intervention, fraud, technical failures, or any other causes which corrupt or affect the administration, security, fairness, integrity, or proper conduct of the Competition, Competition Sponsor reserves the right to cancel, terminate, modify or suspend the Competition. The competition Sponsor reserves the right to disqualify any participant who tampers with the submission process or any other part of the Competition or Competition Website. Any attempt by a participant to deliberately damage any website, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws. Should such an attempt be made, Competition Sponsor and Kaggle each reserve the right to seek damages from any such participant to the fullest extent of the applicable law.\n\n## 20. NOT AN OFFER OR CONTRACT OF EMPLOYMENT.\nUnder no circumstances will the entry of a Submission, the awarding of a Prize, or anything in these Rules be construed as an offer or contract of employment with the Competition Sponsor or any of the Competition Entities. You acknowledge that you have submitted your Submission voluntarily and not in confidence or trust. You acknowledge that no confidential, fiduciary, agency, employment or other similar relationship is created between you and the Competition Sponsor or any of the Competition Entities by your acceptance of these Rules or your entry of your Submission.\n\n## 21. GOVERNING LAW.\nUnless otherwise provided in the Competition Specific Rules above, all claims arising from or relating to these Rules will be governed by California law, excluding its conflict of laws rules, and litigated exclusively in the Federal or State courts of Santa Clara County, California, USA. The parties consent to personal jurisdiction in those courts. If any provision of these Rules is invalid or unenforceable, all remaining provisions will remain in full force and effect.\n\n",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Kaggle Competition Submission Guidelines",
"content": "****Thank you for participating in our exciting competition! We are delighted to see the enthusiasm and dedication from all of you. To ensure that the competition runs smoothly and that everyone has a fair chance, we have outlined the submission guidelines below. Please follow these guidelines carefully to submit your entries successfully.\n\nThe submit button is at the right corner of the competition main page.\n\n**There should be a image**\n\n\n\n\n\n\n\n\n## Submission Components:\n\n\n\n\n\n1. **Leaderboard(submission.csv)**\nWhen submitting your predictions for the Kaggle competition, please make sure to adhere to the following guidelines:\n\n - Submission File Name: The file containing your prediction results must be named \"submission.csv\".\n\n - Format: Your submission file MUST use the 'component_id' of the prediction layout components (RoIs). P\n\n - Evaluation: Ensure that the format of your submission file matches the sample submission file provided, \"submission.csv.\" This will allow us to evaluate your performance correctly.\n\n2. **Code (Notebook):**\n\n\n\n\n\n - The code should be well-documented, organized, and self-explanatory.\n - Use Jupyter Notebook/Kaggle Notebook/Colab Notebook as the preferred format for code submission.\n - Include all necessary libraries and dependencies required to run the code.\n - Ensure your code can be executed end-to-end without any errors.\n - Make sure to handle any external data dependencies and include instructions on how to download and use them, if applicable.\n - The code should be structured to allow your results to be reproducible.\n - Submissions to this competition must be made through Notebooks. For the \"Submit\" button to be active after a commit, the following conditions must be met:\n - CPU Notebook <= 9 hours run-time\n - GPU Notebook <= 9 hours run-time\n\n\n3. **Abstract (AAAI format):**\n\n\n\n\n\n - Prepare a one-page abstract in the AAAI (Association for the advancement of Artificial Intelligence) format to accompany your code submission.\n - The abstract should follow the AAAI guidelines for formatting and describe the results and methods.\n - The results section should present your findings, experiments, and any evaluation metrics used.\n - The methods section should describe the approach and algorithms employed in your solution.\n - Make sure to highlight the strengths and limitations of your approach.\n - Aim for a paper length of one page.\n\n## Submission Process:\n\n### During the competition\n\n - Submit the \"submission.csv\" file to evaluate your model's performance.\n\n\n\n### Final Evaluation. \n - Compress your submission.csv, code (Notebook) and the Abstract into a single zip file. The zip file should be named appropriately, e.g., \"YourTeamName_Submission.zip.\"\n - Upload your submission to the Kaggle competition platform under the \"Submit\" tab. Participants can submit up to two zip files, which will count towards their final leaderboard score.\n - Select the two zip submissions in the Submissions page. If you submit fewer than two zip files, Kaggle will automatically select from your best-scoring submissions for this competition. Note that for the final evaluation, only teams that submit at least one comprehensive zip file will be considered.\n\n - Provide a brief description of your submission and the key highlights in the \"Description\" field.\n - Ensure your submission whether the three submission components are included and that the code runs without errors.\n - Submit your entry before the competition deadline. Late submissions will not be considered.\n\n\n## Evaluation:\n\n - Submissions will be evaluated based on the performance on a hidden test dataset using relevant evaluation metrics, as defined in the competition guidelines.\n - Additionally, the clarity, innovation, and quality of the one-page abstract will also be taken into account during the evaluation process.\n\n\n## Note:\n\n - Plagiarism and copying from other participants or external sources will not be tolerated. Any such action will lead to disqualification.\n - Participate in the competition with honesty and integrity, following the competition rules and guidelines.\n\n\n\nGood luck with your submissions! We are eager to see the remarkable work you all have done. If you have any questions or face any issues during the submission process, feel free to contact our support team",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Timeline",
"content": "Key Dates:\n- 18 November 2024: Competition Start Date.\n- 31 January 2025: Competition End Date.\n- 2 February 2025: Announcement of Winners.\n- 10 February 2025: Paper Submission Due.\n\nAll time is AoE (Anywhere on Earth) time",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "List of Organisation Members",
"content": "Competition Organisers\n- Competition Chair: Shuo Yang, The University of Melbourne, Australia\n- Competition Chair: Yihao Ding, The University of Melbourne, Australia\n\nCompetition Advisory Committee\n- Caren Han, The University of Melbourne, Australia\n- Josiah Poon, The University of Sydney, Australia\n- Anita de Waard, Elsevier, Netherlands\n- Eduard Hovy, The University of Melbourne, Australia",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Prize",
"content": "- The top 3 teams in the private leaderboard will be granted the Official Certificate from Google.\n- A USD $2000 prize and an Official Certification from Google will be awarded to the Top-1 team in the private leaderboard.\n- The teams that secure positions within the top 3 in the final evaluation will be invited to submit a paper detailing their research and methodologies.\n",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "FAQ",
"content": "You can find the list of common questions for this competition: FAQ_GoogleDoc.\n**（Note that the FAQ_GoogleDoc link will be shared from 1 December 2024.）**\n\nIf you have further questions about this competition, feel free to fill out this competition QA form. The organising teams will answer your questions within three (3) working days.\n\n\n\n\n",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Citation",
"content": "ADNLP, VRD IU Competition, aaai-25-visually-rich-document-vrd-iu-leaderboard",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
}
]
}