Welcome to Indoor Location Competition 2.0!
\nAccurate indoor localization has the potential to transform our lives indoors in a similar way that GPS transformed the way people live, work and play outdoors. Despite significant advances in indoor localization technologies over the past two decades, many problems still remain to be solved toward building cost-effective and scalable solutions.
\nAs a continuation of Microsoft Indoor Localization Competition, this competition aims to bring together indoor location technologies from both academia and industry, and compare their performance in the same space with the first-of-its-kind large-scale indoor location dataset. We hope the dataset released for the competition will also be of great value to research and development of indoor space beyond localization and navigation.
\nStay safe, healthy, and hope you enjoy the competition!
\nBest,
\nYour Competition Organizing Committee
\nJie Liu, Yuanchao Shu, Niki Trigoni, Romit Roy Choudhury, Qiang Xu
Welcome to Indoor Location Competition 2.0!
\nAccurate indoor localization has the potential to transform our lives indoors in a similar way that GPS transformed the way people live, work and play outdoors. Despite significant advances in indoor localization technologies over the past two decades, many problems still remain to be solved toward building cost-effective and scalable solutions.
\nAs a continuation of Microsoft Indoor Localization Competition, this competition aims to bring together indoor location technologies from both academia and industry, and compare their performance in the same space with the first-of-its-kind large-scale indoor location dataset. We hope the dataset released for the competition will also be of great value to research and development of indoor space beyond localization and navigation.
\nStay safe, healthy, and hope you enjoy the competition!
\nBest,
\nYour Competition Organizing Committee
\nJie Liu, Yuanchao Shu, Niki Trigoni, Romit Roy Choudhury, Qiang Xu
Hi. can you answer this query about the data set?
\nhttps://www.kaggle.com/c/indoor-location-navigation/discussion/218074
Hello,
\nI have 2 questions :
Hello,
\nI am new to competition. kindly help me.
Hi @juliaelliott @addisonhoward, and @yuanchaoshu.
\nA serious concern about hand-labeling is raised in this discussion page.
\nWould you give us any comments or answers here?
\nIt would be not good for everyone if the decision is made after the end of this competition.
@tomooinubushi I have responded on that discussion that it is prohibited by the rules to hand label test data (this includes the public and private test set). However, it is permitted to relabel or handlabel the training set.
", "rawMarkdown": "tomooinubushi I have responded on that discussion that it is prohibited by the rules to hand label test data (this includes the public and private test set). However, it is permitted to relabel or handlabel the training set.", "votes": null }, { "id": "1296844", "postDate": "05/07/2021 14:26:15", "content": "Thank you for your quick reply!
", "rawMarkdown": "Thank you for your quick reply!", "votes": null }, { "id": "1297047", "postDate": "05/07/2021 17:31:43", "content": "It would be good to clear the remaining confusion: my interpretation of your response is that we are allowed to hand label likely test waypoint locations on the map, since that type of hand labeling only relies on the train data.
", "rawMarkdown": "It would be good to clear the remaining confusion: my interpretation of your response is that we are allowed to hand label likely test waypoint locations on the map, since that type of hand labeling only relies on the train data.", "votes": null }, { "id": "1309395", "postDate": "05/15/2021 22:40:21", "content": "Tom, I think has been addressed in the other thread (the answer was that this is ok if it's automated), but I think the issue here is that it would be impossible to verify whether the team manually picked a point by looking only at the map, or whether they peaked at their test paths, and then claimed that the point seemed to them like a \"likely\" waypoint.
", "rawMarkdown": "Tom, I think has been addressed in the other thread (the answer was that this is ok if it's automated), but I think the issue here is that it would be impossible to verify whether the team manually picked a point by looking only at the map, or whether they peaked at their test paths, and then claimed that the point seemed to them like a \"likely\" waypoint.", "votes": null }, { "id": "1312192", "postDate": "05/17/2021 22:24:24", "content": "That makes sense, we rely on an automated approach.
", "rawMarkdown": "That makes sense, we rely on an automated approach.", "votes": null } ], "comments": [ { "id": 1193777, "author_name": "nigelhenry", "author_url": "", "post_date": "02/09/2021 21:11:15", "content": "Hi. can you answer this query about the data set?
\nhttps://www.kaggle.com/c/indoor-location-navigation/discussion/218074
Hello,
\nI have 2 questions :
Hello,
\nI am new to competition. kindly help me.
Hi @juliaelliott @addisonhoward, and @yuanchaoshu.
\nA serious concern about hand-labeling is raised in this discussion page.
\nWould you give us any comments or answers here?
\nIt would be not good for everyone if the decision is made after the end of this competition.
@tomooinubushi I have responded on that discussion that it is prohibited by the rules to hand label test data (this includes the public and private test set). However, it is permitted to relabel or handlabel the training set.
", "votes": null, "replies": [] }, { "id": 1296844, "author_name": "tomooinubushi", "author_url": "", "post_date": "05/07/2021 14:26:15", "content": "Thank you for your quick reply!
", "votes": null, "replies": [] }, { "id": 1297047, "author_name": "tvdwiele", "author_url": "", "post_date": "05/07/2021 17:31:43", "content": "It would be good to clear the remaining confusion: my interpretation of your response is that we are allowed to hand label likely test waypoint locations on the map, since that type of hand labeling only relies on the train data.
", "votes": null, "replies": [] }, { "id": 1309395, "author_name": "paulfornia", "author_url": "", "post_date": "05/15/2021 22:40:21", "content": "Tom, I think has been addressed in the other thread (the answer was that this is ok if it's automated), but I think the issue here is that it would be impossible to verify whether the team manually picked a point by looking only at the map, or whether they peaked at their test paths, and then claimed that the point seemed to them like a \"likely\" waypoint.
", "votes": null, "replies": [] }, { "id": 1312192, "author_name": "tvdwiele", "author_url": "", "post_date": "05/17/2021 22:24:24", "content": "That makes sense, we rely on an automated approach.
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "1181997": "Welcome to [Indoor Location Competition 2.0](https://aka.ms/location20)! \n\nAccurate indoor localization has the potential to transform our lives indoors in a similar way that GPS transformed the way people live, work and play outdoors. Despite significant advances in indoor localization technologies over the past two decades, many problems still remain to be solved toward building cost-effective and scalable solutions. \n\nAs a continuation of [Microsoft Indoor Localization Competition](https://www.microsoft.com/en-us/research/event/microsoft-indoor-localization-competition-ipsn-2018/), this competition aims to bring together indoor location technologies from both academia and industry, and compare their performance in the same space with the first-of-its-kind large-scale indoor location dataset. We hope the dataset released for the competition will also be of great value to research and development of indoor space beyond localization and navigation. \n\nStay safe, healthy, and hope you enjoy the competition!\n\nBest, \nYour Competition Organizing Committee \n[Jie Liu](https://scholar.google.com/citations?user=AJKK2ikAAAAJ&hl=en), [Yuanchao Shu](https://aka.ms/yuanchao), [Niki Trigoni](https://www.cs.ox.ac.uk/people/niki.trigoni/), [Romit Roy Choudhury](https://croy.web.engr.illinois.edu/), [Qiang Xu](https://www.linkedin.com/in/qiang-xu-698724a/)", "1193777": "Hi. can you answer this query about the data set?\nhttps://www.kaggle.com/c/indoor-location-navigation/discussion/218074", "1197784": "Hello,\nI have 2 questions :\n- how were the ground truth waypoints obtained ?\n- is there any new sites or new floors in test data which are not in train data ?", "1200065": "Hello,\nI am new to competition. kindly help me.", "1296712": "Hi @juliaelliott @addisonhoward, and @yuanchaoshu.\nA serious concern about hand-labeling is raised in [this discussion page](https://www.kaggle.com/c/indoor-location-navigation/discussion/235813).\nWould you give us any comments or answers here?\nIt would be not good for everyone if the decision is made after the end of this competition.", "1296829": "tomooinubushi I have responded on that discussion that it is prohibited by the rules to hand label test data (this includes the public and private test set). However, it is permitted to relabel or handlabel the training set.", "1296844": "Thank you for your quick reply!", "1297047": "It would be good to clear the remaining confusion: my interpretation of your response is that we are allowed to hand label likely test waypoint locations on the map, since that type of hand labeling only relies on the train data.", "1309395": "Tom, I think has been addressed in the other thread (the answer was that this is ok if it's automated), but I think the issue here is that it would be impossible to verify whether the team manually picked a point by looking only at the map, or whether they peaked at their test paths, and then claimed that the point seemed to them like a \"likely\" waypoint.", "1312192": "That makes sense, we rely on an automated approach." }, "source": "meta" }