{ "fetched_at": "2026-10-22T06:51:08Z", "source_url": "https://www.kaggle.com/competitions/2nd-miga-ijcai-challenge-track1/data", "pages": [ { "name": "data-description", "content": "Datasets for the proposed challenge are available. The MiGA challenge is planned as a continuous annual event. Two benchmark datasets published on IJCV 2023 and CVPR 2021 are available and will be used for the challenge. The first one is the SMG dataset published in IJCV 2023. The spontaneous Micro-Gesture (SMG) dataset consists of 3,692 samples of 17 MGs. The MG clips are annotated from 40 long video sequences (10-15 minutes) with 821,056 frames in total. The datasets were collected from 40 subjects while narrating a fake and real story to elicit emotional states. The participants are recorded and collected by Kinect resulting in four modalities, RGB, 3D skeletal joints, depth and silhouette. In this workshop, we allow participants to use the skeleton, RGB or both modalities. [Details about SMG dataset](https://www.oulu.fi/en/university/faculties-and-units/faculty-information-technology-and-electrical-engineering/center-machine-vision-and-signal-analysis)\n\nThe second dataset is iMiGUE published in CVPR2021. Micro-Gesture Understanding and Emotion analysis (iMiGUE) dataset consists of 32 MGs plus one non-MG class collected from post-match press conferences videos of famous tennis players. The dataset consists of 18,499 samples of MGs to detect negative and positive emotions. The MG clips are annotated from 359 long video sequences (0.5-26 minutes) with 3,765,600 frames in total. The dataset contains RGB modality and 2D skeletal joints collected from Open-Pose. In this workshop, we allow participants to use the skeleton, RGB or both modalities. [Details about iMiGUE dataset](https://www.oulu.fi/en/university/faculties-and-units/faculty-information-technology-and-electrical-engineering/center-machine-vision-and-signal-analysis)\n\n**The training and validation sets (skeleton + RGB modality) of the iMiGUE and SMG datasets will released for the competition on April 9th.**\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "News", "content": "- 03 June : Workshop paper notification date is extended to 07 June 2024\n- 17 May : **Final results are available**\nWe have examined all source code submitted and finalized the rankings of the MiGA challenge. Congratulations to the following competitors on their final rankings for Track 1: Micro-gesture Classification\n1.'**HFUT-VUT**'\n2.'**NPU-MUCIS**'\n3.'**ywww11**'\n\n- 12 May : The challenge has officially ended, please follow [these](https://drive.google.com/file/d/1A2H4y4m984Q-HxrgWF0COP8UxoHhe9wg/view?usp=sharing) instructions to submit your source code, deadline is **15 May**. Top-3 runners will present their work at IJCAI2024. You can submit papers to the MiGA2 [Workshop](https://cv-ac.github.io/MiGA2/) as well.\n- 02 May : Phase 2 skeleton data has been updated to fix an issue. Please check the data tab or download from [here](https://a3s.fi/iMiGUE_RGB/imigue_data_phase2.zip?AWSAccessKeyId=8c1f3f520cf1404889879b69e45fe546&Expires=1715923987&Signature=VaGGFGhRRK1EDDWi7HJgNdoiNfo%3D)\n- 02 May : Phase2 has officially started, the leaderboard will be rescored and only the results on the testing data from Phase2 will be counted. Please check the template for submitting to phase2: [submission_test.csv](https://drive.google.com/file/d/1CdJAtN4r8HvEz0D6oaxYeE1o2wXGzqmx/view?usp=sharing)\n- 02 May : Testing set for Track 1 is released. [Data](https://www.kaggle.com/competitions/2nd-miga-ijcai-challenge-track1/data) is from iMiGUE dataset and contains both skeleton and rgb videos.\n- 09 April : Training set and validation set for Track 1 are released. Data is from iMiGUE dataset and contains both skeleton and rgb videos\n- 29 March : The Kaggle website of MiGA challenge is available for the both tracks, the training data will be released in few days.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "## **Track 1 (micro-gesture classification) description** \nIn this track, we conduct skeleton-based micro-gesture classification from short video clips. The MG datasets were collected from in-the-wild settings (tennis players having postmatch interviews). Compared to ordinary action/gesture data, MGs concern more fine-grained and subtle body movements that occur spontaneously in practical interactions. Thus, learning those fine-grained body movement patterns, handling imbalanced sample distribution of MGs, and distinguishing the high heterogeneous MG samples of interclass are the big challenges to be addressed. In this year's challenge we also provide complementary RGB data and encourage competitors to find multi-modal solutions that leverage both skeleton and RGB.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "MiGA Challenge Rules for MiGA-IJCAI 2024\n\nCommon terms used in these rules:\n\nThese are the official rules that govern how the MiGA-IJCAI 2024 contest promotion will operate. This promotion will be simply referred to as the “contest” or the “challenge” throughout the rest of these rules and may be abbreviated on our website, in our documentation, and other publications as MiGA.\n\nIn these rules, “organizers”, “we,” “our,” and “us” refer to MiGA; \"participant”, “you,” and “yourself” refer to an eligible contest participant.\n\nSECTION 1: Contest description\n\nThis is a skill-based contest and chance plays no part in the determination of the winner(s). The goal of the contest is split into two competition tracks (with a shared schedule):\n\nTrack 1: Micro-gesture Classification:\n\nFocus of the Contest: Classifying micro-gestures within 33 MG categories recorded and manually labeled in continuous skeleton sequences of different people performing natural and spontaneous behaviors.\n\nTrack 2: Micro-gesture Online Recognition:\n\nFocus of the Contest: Recognizing micro-gestures from 33 categories that can spot continuous gesture among users' daily communication.\n\nAll eligible entries received for any of the two tracks will be judged using the criteria described in Section 7 to determine winners.\n\nSECTION 2: Tentative Contest Schedule\n\nThe tentative timeline for the Challenge will be organized as follows:\n\nMar 29, 2024. Call for Challenge online. Registration starts.\n\nApr 5, 2024. Release of training data.\n\nMay 2, 2024. Release of testing data.\n\nMay 12, 2024. Final testing data and result submission. Registration ends.\n\nMay 15, 2024. Release of challenge results.\n\nMay 30, 2024. Paper submission deadline (to workshop).\n\nJune 04, 2024. Notification to authors.\n\nJune 10, 2024. Camera-ready deadline.\n\nAugust, 2024. MiGA IJCAI 2024 Workshop, Jeju, Korea.\n\nSECTION 3: Eligibility\n\nYou are eligible to enter this contest if you meet the following requirements:\n\n(a) You are an individual or a team of people desiring to contribute to the tasks of the challenge and accepting to follow its rules; and\n\n(b) You are NOT a resident of any country constrained by US export regulations included in the OFAC sanction page. Therefore residents of these countries/regions are not eligible to participate; and\n\n(c) You are not an employee of MiGA; and\n\n(d) You are not involved in any part of the administration and execution of this contest; and\n\n(e) You are not an immediate family (parent, sibling, spouse, or child) or household member of an employee of MiGA, or a person involved in any part of the administration and execution of this contest.\n\nThis contest is void within the geographic area identified above and wherever else prohibited by law.\n\nIf you choose to submit an entry, but are not qualified to enter the contest, this entry is voluntary, and any entry you submit is governed by the remainder of these contest rules; MiGA reserves the right to evaluate it for scientific purposes.\n\nSECTION 4: Entry\n\nTo be eligible for judging, an entry must meet the following content/technical requirements:\n\n(a) Entry contents:\n\nThe participants are required to submit prediction results and code (see section 7). To be eligible for prizes, the top ranking participants are required to publicly release their code under a license of their choice, taken among one of the those: (Apache License 2.0, BSD 3-Clause \"New\" or \"Revised\" license, or BSD 2-Clause \"Simplified\" or \"FreeBSD\" license) and make their code accessible on-line for a period no less than three year following the end of the challenge, and permit the organizers to upload the code the the Kaggle experimental platform to make it available to Kaggle users, where it will remain available as long as the organizers wish. To be part of the final ranking the participants will be asked to fill out a survey (fact sheet) briefly describing their method. The top ranking participants will be invited to submit a maximum 8-page paper for the proceedings of the IJCAI MiGA workshop (pending acceptance), following the event publication guidelines.\n\n(b) Pre-requisite:\n\nThere is no pre-requisite to participate, including no requirement to have participated in previous challenges.\n\n(c) Use of data provided:\n\nAll data provided by MiGA is freely available to the participants from the website of the challenge (kaggle.com) under license terms provided with the data.\n\n(1) Test data (final evaluation data):\n\nThe organizers will use test data to perform the final evaluation, hence the participants’ final entry will be based on test data.\n\n(2) Training and validation data:\n\nThe contest organizers will make available to the participants a training dataset with truth values, and a validation set with no truth values. The validation data will be used by the participants for practice purposes to validate their systems. It will be similar in composition to the test set.\n\n(3) Post-challenge analyses:\n\nThe organizers may also perform additional post-challenge analyses using extra data, but the results will not affect the ranking of the challenge performed with the test data.\n\n(d) Submission:\n\nThe entries of the participants will be submitted on-line via the Kaggle web platform. During the development period, the participants will receive immediate feed-back on validation data released for practice purpose. For the final evaluation, the results will be computed automatically on test data submissions. The performances on test data will not be released until the challenge is over.\n\n(e) Original work, permissions:\n\nIn addition, by submitting your entry into this contest you confirm that, to the best of your knowledge:\n\n(1) Your entry is your own original work; and\n\n(2) Your entry only includes material that you own, or that you have permission from the copyright/trademark owner to use.\n\nSECTION 5: Potential use of entry\n\nOther than what is set forth below, we are not claiming any ownership rights to your entry. However, by submitting your entry, you:\n\n(a) Are granting us an irrevocable, worldwide right and license, in exchange for your opportunity to participate in the contest and potential prize awards, for the duration of the protection of the copyrights to:\n\n(1) Use, review, assess, test and otherwise analyze results submitted or produced by your code and other material submitted by you in connection with this contest and any future research or contests sponsored by MiGA; and\n\n(2) Feature your entry and all its content in connection with the promotion of this contest in all media (now known or later developed);\n\n(b) Agree to sign any necessary documentation that may be required for us and our designees to make use of the rights you granted above;\n\n(c) Understand and acknowledge that sponsors and other entrants may have developed or commissioned materials similar or identical to your submission and you waive any claims you may have resulting from any similarities to your entry;\n\n(d) Understand that we cannot control the incoming information you will disclose to our representatives or our co-sponsor’s representatives in the course of entering, or what our representatives will remember about your entry. You also understand that we will not restrict work assignments of representatives or our co-sponsor’s representatives who have had access to your entry. By entering this contest, you agree that use of information in our representatives’ or our co-sponsor’s representatives unaided memories in the development or deployment of our products or services does not create liability for us under this agreement or copyright or trade secret law;\n\n(e) Understand that you will not receive any compensation or credit for use of your entry, other than what is described in these official rules.\n\nIf you do not want to grant us these rights to your entry, please do not enter this contest.\n\nSECTION 6: Submission of entries\n\n(a) Follow the instructions on the Kaggle website (kaggle.com) to submit entries. You must register to the track or tracks you want to participate in.\n\n(b) The participants will be registered as mutually exclusive teams. For final entries, the team leader will be responsible to make the submission. Each team may submit only one single final entry. We are not responsible for entries that we do not receive for any reason, or for entries that we receive but are not functioning properly.\n\n(c) The participants must follow the instructions. We will automatically disqualify incomplete or invalid entries.\n\nSECTION 7: Submission of code\n\n(a) During the challenge, participants are encouraged to submit to Kaggle their predictions in a ZIP file containing the predictions in the requested format. A submission example for each track will be provided in the track submission section.\n\n(b) For the final evaluation, participants are required to submit a ZIP file following the instructions published with the validation labels, containing:\n\n(1) Executable or source code of their code, which allows to generate the predictions from the data. Although the use of Python is encouraged, any programming language can be used. The entry point must follow the provided format for each track.\n\n(2) All necessary libraries and dependencies to run their code.\n\n(3) Instructions on how to execute their code.\n\n(4) A form disclosing the list of team members.\n\nSECTION 8: Judging the entries\n\nThe board of MiGA will select a panel of judges to judge the entries; all judges will be forbidden to enter the contest and will be experts in causality, statistics, machine learning, or a related field, or experts in challenge organization. A list of the judges will be made available upon request. The judges will review all eligible entries received and select three winners for each of the three competition tracks based upon the prediction score on test data. The judges will verify that the winners complied with the rules, including that they documented their method by filling out a fact sheet that will be provided to the participants.\n\nEvaluation will be performed by submitting prediction results to the challenge track using the Kaggle platform.\n\nThe decisions of these judges are final and binding. The distribution of prizes according to the decisions made by the judges will be made within three (3) months after completion of the last round of the contest. If we do not receive a sufficient number of entries meeting the entry requirements, we may, at our discretion based on the above criteria, not award any or all of the contest prizes below. In the event of a tie between any eligible entries, the tie will be broken by giving preference to the earliest submission, using the time stamp of the submission platform.\n\nSECTION 9: Prizes and Awards\n\nAll three top ranked participants for each track will be invited to submit a paper of their winner method following the submission guidelines for IJCAI MiGA workshop (pending acceptance) or give a technique report on IJCAI MiGA Satellite event.\n\n(*) The amount will be based on need and availability. The travel award may be used for one of the workshops organized in conjunction with the challenge. The award money will be granted in reimbursement of expenses including airfare, ground transportation, hotel, or workshop registration. Reimbursement is conditioned on (i) attending the workshop, (ii) making an oral presentation of the methods used in the challenge, and (iii) presenting original receipts and boarding passes.\n\nSECTION 10: Notifications\n\nIf there is any change to data, schedule, instructions of participation, or these rules, the registered participants will be notified at the email they provided with the registration.\n\nIf you are a potential winner, we will notify you by sending a message to the e-mail address listed on your final entry within seven days following the determination of winners. If the notification that we send is returned as undeliverable, or you are otherwise unreachable for any reason, we may award the prize to an alternate winner, unless forbidden by applicable law.\n\nWinners who have entered the contest as a team will be responsible to share any prize among their members. The prize will be delivered to the registered team leader. If this person becomes unavailable for any reason, the prize will be delivered to be the authorized account holder of the e-mail address used to make the winning entry.\n\nIf you are a potential winner, we may require you to sign a declaration of eligibility, use, indemnity and liability/publicity release and applicable tax forms. If you are a potential winner and are a minor in your place of residence, and we require that your parent or legal guardian will be designated as the winner, and we may require that they sign a declaration of eligibility, use, indemnity and liability/publicity release on your behalf. If you, (or your parent/legal guardian if applicable), do not sign and return these required forms within the time period listed on the winner notification message, we may disqualify you (or the designated parent/legal guardian) and select an alternate selected winner.\n\nSECTION 11: On-line notification\n\nWe will post changes in the rules or changes in the data as well as the names of confirmed winners (after contest decisions are made by the judges) online on https://cv-ac.github.io/MiGA2/. Additionally, a forum has been included to each track in order to provide specific information. This list will remain posted for one year or will be made available upon request by sending email to chen.haoyu@oulu.fi.\n\nSECTION 12: Conditions\n\nBy entering this contest users, intended as who will make use of the database, agrees to the following terms.\n\nCommercial use\nThe user may not use the database for any commercial purpose. Commercial purposes include, but are not limited to:\n\nproving the efficiency of commercial systems,\n\ntesting commercial systems,\n\nusing screenshots of subjects from the database in advertisements,\n\nselling data from the database,\n\nbroadcasting data from the database.\n\nDistribution\nThe user may not distribute or broadcast the database in any form. Small portions (i.e.; sample images) may be used in academic publications and presentations by strictly abiding the following conditions:\n\nA. showing with necessity: only show the real face photo if a drawing or fake face won’t be enough for the illustration purpose.\n\nB. only use the least amount of face photos for you need.\n\nC. never link the used face photo with any possible trait of personal info (e.g., city, university, etc).\n\nAccess\nThe user may only use the database after this LA has been signed by his/her group leader or professor (who has fixed position in the data requiring institution), and returned to the Center for Machine Vision and Signal Analysis (CMVS). The user must send a scanned copy of the signed and dated LA by email, in PDF format to: chen.haoyu@oulu.fi, and if a student is sending the email, the email should be copied to the leader or professor who signed the LA.\n\nWith the group leader or professor signing the LA, we agree that all students and researchers that reported to the signer are eligible of using the data. The signer should get familiar with the latest EU General Data Protection Regulation (GDPR), and is responsible for controlling who in his/her group gets access to the data, and\n\nhow the data will be stored and used properly according to GDPR. The signer will be fully responsible if any issue rise in relation with the GDPR about the usage of shared data in his/her group.\n\nPublications and citations\nPublications include not only research papers, but also presentations for conferences or educational purposes.\n\nAll documents and research papers that report on research should include a citation to the corresponding publications:\n\nChen H., Shi H., Liu X., Li X., and Zhao G. SMG: A Micro-gesture Dataset Towards Spontaneous Body Gestures for Emotional Stress State Analysis. International Journal of Computer Vision (IJCV 2023), 2023: 1-21.\n\nLiu, X., Shi H., Chen H., Yu Z., Li X., and Zhao G. \"iMiGUE: An identity-free video dataset for micro-gesture understanding and emotion analysis.\" In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), pp. 10631-10642. 2021.\n\nChen H., Liu X., Li X., Shi H., & Zhao G. Analyze spontaneous gestures for emotional stress state recognition: A micro-gesture dataset and analysis with deep learning. 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019): 1-8.\n\nThe user will send an electronic copy of all papers that reference the database to: chen.haoyu@oulu.fi\n\nResearch\nFor users from non-academic organizations, the data is shared ONLY for participating the MiGA 2024 event (including training models for participating the challenge, writing a paper for the workshop, and presenting a paper on the workshop), but not for any other purpose. The user must delete the data immediately after the MiGA 2024 event ends (By 31.06.2024).\n\nThe user has to contact the data owner again, if he/she intends to use the data for other research purpose, e.g., for one academic paper not published on the MiGA 2024. A new license agreement will be needed, and the data owner has the right to agree or reject the request of any new usage. Any other usage of the data, e.g., publishing results in other paper, without noticing will be seen as violation of the LA.\n\nChanges\nThe Center for Machine Vision and Signal Analysis (CMVS) is allowed to change this LA at any time; users will be informed about changes beforehand and given the choice to opt out of the new LA. Opting out will render the previous LA void.\n\nWarranty\nThe database comes without any warranty, CMVS cannot be held accountable for any damage (physical, financial or otherwise) caused by the use of the database. CMVS will try to prevent any damage by keeping the database virus free.\n\nSECTION 13: Unforeseen event\n\nIf an unforeseen or unexpected event (including, but not limited to: someone cheating; a virus, bug, or catastrophic event corrupting data or the submission platform; someone discovering a flaw in the data or modalities of the challenge) that cannot be reasonably anticipated or controlled, (also referred to as force majeure) affects the fairness and / or integrity of this contest, we reserve the right to cancel, change or suspend this contest. This right is reserved whether the event is due to human or technical error. If a solution cannot be found to restore the integrity of the contest, we reserve the right to select winners based on the criteria specified above from among all eligible entries received before we had to cancel, change or suspend the contest subject to obtaining the approval from the Régie des Alcools, des Courses et des Jeux with respect to the province of Quebec.\n\nComputer “hacking” is unlawful. If you attempt to compromise the integrity or the legitimate operation of this contest by hacking or by cheating or committing fraud in any way, we may seek damages from you to the fullest extent permitted by law. Further, we may ban you from participating in any of our future contests, so please play fairly.\n\nSECTION 14: Organizers\n\nOrganizing Committee\n\nGuoying Zhao, University of Oulu, Finland.\n\nBjörn W. Schuller, University of Augsburg, Germany; Imperial College London, London/UK.\n\nEhsan Adeli, Stanford University, USA.\n\nHaoyu Chen (leading data chair), University of Oulu, Finland.\n\nData chairs\n\nAtif Shah, University of Oulu, Finland.\n\nMarkov Savic, University of Oulu, Finland.\n\nAbdelrahman Mostafa, University of Oulu, Finland.\n\nSECTION 15: Privacy\n\nDuring the development phase of the contest and when they submit their final entries, contest participants do not need to disclose their real identity, but must provide a valid email address where we can be deliver notifications to them regarding the contest. To be eligible for prizes, however, contest participants will need to disclose their real identity to contest organizers, informing them by email of their name, professional affiliation, and address. To enter the contest, the participants will need to become users of the Kaggle platform. Any profile information stored on this platform can be viewed and edited by the users. After the contest, the participants may cancel their account with the Kaggle and cease to be users of that platform. All personal information will then be destroyed. The Kaggle privacy policy will apply to contest information submitted by participants on the Kaggle. Otherwise, MiGA’s privacy policy will apply to this contest and to all information that we receive from your entry that we receive directly from you or which you have submitted as part of your contest entry on the Kaggle. Please read the privacy policy on the contest entry page before accepting the official rules and submitting your entry. Please note that by accepting the official rules you are also accepting the terms of the MiGA privacy policy.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "abstract", "content": "The Micro-gesture Analysis for Hidden Emotion Understanding (MiGA) challenge is planned as a continuous, annual event, and each year MiGA will include different (multiple) challenge tasks, with large-scale datasets with expanding size.\n\nBody gestures are an important form to reveal people’s emotions alongside facial expressions and speeches. For special occasions when people intend to control or hide their true feelings, e.g., for social etiquette or other reasons, body gestures are harder to control and thus the more revealing clues of actual feelings compared to the face and the voice. Micro-gestures (MG) are defined as a special category of body gestures that are indicative of humans’ emotional status. Representative instances include scratching the head, touching the nose, and rubbing hands, which are not intended to be shown when communicating with others, but occur spontaneously due to e.g., felt stress or discomfort. The MGs differ from indicative gestures which are performed on purpose for facilitating communications, e.g., using gestures to assist verbal expressions during a discussion. Although research on general body gestures is prevailing, it is largely about human’s macro body movement, lacking the finer level consideration such as the micro-gestures discussed above. As well the studies are mainly concerned with recognizing the movement performed expressively, and the link between gestures and hidden emotions is yet to be explored.\n\nAs the second year of MiGA, we plan to set two fundamental challenge tasks (Tracks): micro-gesture classification and micro-gesture online recognition, and participating teams can choose to compete on one or both tasks.\n\n# Official website of the challenge:\nhttps://cv-ac.github.io/MiGA2", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Schedule", "content": "Important Dates (might slightly adjust later)\n\n- Mar 29, 2024. Call for Challenge online. Registration starts.\n- Apr 9, 2024. Release of training data.\n- May 2, 2024. Release of testing data.\n- May 12, 2024. Final testing data and result submission. Registration ends.\n- May 17, 2024. Release of challenge results.\n- May 30, 2024. Paper submission deadline (workshop).\n- June 07, 2024. Notification to authors.\n- June 12, 2024. Camera-ready deadline.\n- August, 2024. MiGA IJCAI 2024 Workshop, Jeju, Korea.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Phases", "content": "**Phase 1: Development (29 March - 02 May)**\nDevelopment phase: create models and submit them or directly submit results on validation data, feedback is provided on the validation set only. In this phase the training and validation data are released, leaderboard is calculated on the submitted validation data results. \n**Phase 2: Final (02 May - 12 May)**\nFinal phase: test your models on the testing data and submit to the new leaderboard. In this phase the testing data (without labels) is released, the new and final leaderboard is calculated on the submitted testing data results.\n\nData can be found [here](https://www.kaggle.com/competitions/2nd-miga-ijcai-challenge-track1/data).", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "Training datasets and the testing dataset (without annotation released) are from iMiGUE. We deploy a cross-subject evaluation protocol by dividing the 72 subjects into a training group of 37 subjects and a testing group of 35 subjects. For the MG classification track, 13,936 and 3,692 MG clips from iMiGUE, and the remaining 4,563 MG clips from iMiGUE will be used for testing.\n\nMG classification track: We evaluate participants' methods based on **Top-1 accuracy** in the challenge, but we encourage participants to report their results when submitting papers to our MiGA workshop, on the following subsets of the test set: 1) Overall: All segments in the test split; 2) Tail Classes: Due to the long-tailed nature of the datasets, among a total 33 classes in iMiGUE dataset, 28 classes are tail classes (approx. 57.8 % of the data). \n\nSubmission format for classification track. Participants must submit their predictions following **the sample format below**. The results will be evaluated on the server and displayed on the ranking list in real-time. The organization team has the right to examine the participants' source code to ensure the reproducibility of the algorithms. The final results and ranking will be confirmed and announced by organizers.\n\n\n## Submission File\nParticipants must submit their predictions in the a single .csv file. Instructions and sample submission files will be released with the data.\n\n For each 'Id' in the validation set, you must predict a probability for the 'Target' variable. The file should contain a header (Id,Target) with and have the following format:\n\n Id , Target\n 0004_0,30\n 0004_1,30\n etc.\n\n\n**The phase 2 sample submission for the final testing phase (May 2nd to May 12th) can be found [here](https://drive.google.com/file/d/1CdJAtN4r8HvEz0D6oaxYeE1o2wXGzqmx/view?usp=sharing).**\n\nThe old phase1 sample submission for the evaluation phase (April 8th to May 2nd) can be found [here](https://drive.google.com/file/d/1PHBwudikSqjgxoXAW6n94A1-HgiRb1Jx/view?usp=drive_link).\n\nThe old leaderboard from phase1 is displayed below. Please submit your final results on the testing data to get your ranking on the final phase2 leaderboard.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F6355562%2Fda5dc2d1279660ee40f4fa809c24aacc%2FScreenshot%20from%202024-05-02%2016-04-57.png?generation=1714656107502546&alt=media)\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }