Papers for the top 3 teams :\n- 1st : JL -> https://storage.googleapis.com/kaggle-forum-message-attachments/549732/13471/Team%20JL%20Solution%20to%20Google%20Landmark%20Recognition%202019.pdf \n- 2nd : GLRunner -> https://arxiv.org/abs/1906.03990\n- 3rd : smlyaka -> https://arxiv.org/abs/1906.04087
\n\nSlides for some top-10 teams -> https://drive.google.com/open?id=14PdHtRBXE3DTYxu5fpoDtTZUTm0Z9MXr
\n\n1st place writeup -> https://www.kaggle.com/c/landmark-recognition-2019/discussion/94523
\n\n2nd place code -> https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/Research/landmark
\n\n8th place writeup -> https://www.kaggle.com/c/landmark-recognition-2019/discussion/94512
", "messages": [ { "id": 951098, "postDate": "2020-07-29T21:55:14.527Z", "content": "Papers for the top 3 teams :\n- 1st : JL -> https://storage.googleapis.com/kaggle-forum-message-attachments/549732/13471/Team%20JL%20Solution%20to%20Google%20Landmark%20Recognition%202019.pdf \n- 2nd : GLRunner -> https://arxiv.org/abs/1906.03990\n- 3rd : smlyaka -> https://arxiv.org/abs/1906.04087
\n\nSlides for some top-10 teams -> https://drive.google.com/open?id=14PdHtRBXE3DTYxu5fpoDtTZUTm0Z9MXr
\n\n1st place writeup -> https://www.kaggle.com/c/landmark-recognition-2019/discussion/94523
\n\n2nd place code -> https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/Research/landmark
\n\n8th place writeup -> https://www.kaggle.com/c/landmark-recognition-2019/discussion/94512
", "rawMarkdown": "Papers for the top 3 teams :\n- 1st : JL -> https://storage.googleapis.com/kaggle-forum-message-attachments/549732/13471/Team%20JL%20Solution%20to%20Google%20Landmark%20Recognition%202019.pdf \n- 2nd : GLRunner -> https://arxiv.org/abs/1906.03990\n- 3rd : smlyaka -> https://arxiv.org/abs/1906.04087\n\n\nSlides for some top-10 teams -> https://drive.google.com/open?id=14PdHtRBXE3DTYxu5fpoDtTZUTm0Z9MXr\n\n1st place writeup -> https://www.kaggle.com/c/landmark-recognition-2019/discussion/94523\n\n2nd place code -> https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/Research/landmark\n\n8th place writeup -> https://www.kaggle.com/c/landmark-recognition-2019/discussion/94512", "votes": 75 }, { "id": 951608, "postDate": "2020-07-30T08:58:56.547Z", "content": "@theoviel thank you! also I would like to add some helpful urls:
\n\n2019: https://www.kaggle.com/c/landmark-recognition-2019/\n2018: https://www.kaggle.com/c/landmark-recognition-challenge/
", "rawMarkdown": "@theoviel thank you! also I would like to add some helpful urls:\n\n2019: https://www.kaggle.com/c/landmark-recognition-2019/\n2018: https://www.kaggle.com/c/landmark-recognition-challenge/", "votes": 6 }, { "id": 951294, "postDate": "2020-07-30T03:42:16.900Z", "content": "Thanks for your post.\n\"1st place writeup\" is incorrect, so the following URL is correct?
\n\nhttps://www.kaggle.com/c/landmark-recognition-2019/discussion/94523
", "rawMarkdown": "Thanks for your post.\n\"1st place writeup\" is incorrect, so the following URL is correct?\n\nhttps://www.kaggle.com/c/landmark-recognition-2019/discussion/94523", "votes": 3, "replies": [ { "id": 951544, "postDate": "2020-07-30T07:50:41.040Z", "content": "Fixed, thanks :)
", "rawMarkdown": "Fixed, thanks :)" } ] }, { "id": 951951, "postDate": "2020-07-30T14:13:40.323Z", "content": "Can someone explain what Image Descriptors mean in the 1st place paper??
", "rawMarkdown": "Can someone explain what **Image Descriptors** mean in the 1st place paper??", "votes": 2, "replies": [ { "id": 953863, "postDate": "2020-08-01T07:34:30.647Z", "content": "output from the last convolution layer for an image. this output contains the features that are important to classify
", "rawMarkdown": "output from the last convolution layer for an image. this output contains the features that are important to classify ", "votes": 2 }, { "id": 960182, "postDate": "2020-08-06T07:49:20.267Z", "content": "Thank you!
", "rawMarkdown": "Thank you!" } ] }, { "id": 958041, "postDate": "2020-08-04T18:06:01.127Z", "content": "2nd place code does not seem to be available.
", "rawMarkdown": "2nd place code does not seem to be available.", "replies": [ { "id": 962742, "postDate": "2020-08-08T11:57:19.857Z", "content": "Seems that authors moved source code somewhere else, but you can always retrieve it from git history. Here, original commit for landmark models: https://github.com/PaddlePaddle/models/tree/cc473ce799f3f612156d5086814d9750eb012d2a/PaddleCV/Research/landmark
", "rawMarkdown": "Seems that authors moved source code somewhere else, but you can always retrieve it from git history. Here, original commit for landmark models: https://github.com/PaddlePaddle/models/tree/cc473ce799f3f612156d5086814d9750eb012d2a/PaddleCV/Research/landmark", "votes": 2 }, { "id": 962830, "postDate": "2020-08-08T13:16:57.620Z", "content": "Good to know. Thank you!
", "rawMarkdown": "Good to know. Thank you!" } ] }, { "id": 953534, "postDate": "2020-07-31T21:33:36.820Z", "content": "When looking at the papers, I see they stated the public/private score on every steps? how to make this? are there any function to acquire score in the notebook? or it has to be obtained by new notebooks on every step?
", "rawMarkdown": "When looking at the papers, I see they stated the public/private score on every steps? how to make this? are there any function to acquire score in the notebook? or it has to be obtained by new notebooks on every step? " }, { "id": 953170, "postDate": "2020-07-31T15:21:11Z", "content": "Indeed Helpful !!! Thanks for sharing @theoviel
", "rawMarkdown": "Indeed Helpful !!! Thanks for sharing @theoviel " }, { "id": 952629, "postDate": "2020-07-31T05:16:47.137Z", "content": "Thanks for the post! Sounds like the challenge in this competition will be figuring out how to optimize the training data set curation and confidence score estimation within the constraints of Kaggle notebooks.
", "rawMarkdown": "Thanks for the post! Sounds like the challenge in this competition will be figuring out how to optimize the training data set curation and confidence score estimation within the constraints of Kaggle notebooks." }, { "id": 952239, "postDate": "2020-07-30T18:28:35.773Z", "content": "Thought about making this thread but you were faster. Thanks for the collection. :)
", "rawMarkdown": "Thought about making this thread but you were faster. Thanks for the collection. :)" }, { "id": 951558, "postDate": "2020-07-30T08:01:29.367Z", "rawMarkdown": "", "isDeleted": true }, { "id": 965296, "postDate": "2020-08-10T14:28:35.227Z", "content": "Thanks for sharing :)
", "rawMarkdown": "Thanks for sharing :)\n", "votes": 3 }, { "id": 964515, "postDate": "2020-08-10T00:46:03.480Z", "content": "Thanks for sharing!
", "rawMarkdown": "Thanks for sharing!" }, { "id": 951869, "postDate": "2020-07-30T13:16:05.123Z", "content": "Thank you!!
", "rawMarkdown": "Thank you!!\n" } ], "comments": [ { "id": 951608, "author_name": "Alex Shonenkov", "author_url": "", "post_date": "2020-07-30T08:58:56.547000", "content": "@theoviel thank you! also I would like to add some helpful urls:
\n\n2019: https://www.kaggle.com/c/landmark-recognition-2019/\n2018: https://www.kaggle.com/c/landmark-recognition-challenge/
", "votes": 6, "replies": [] }, { "id": 951294, "author_name": "Shota Nakano", "author_url": "", "post_date": "2020-07-30T03:42:16.900000", "content": "Thanks for your post.\n\"1st place writeup\" is incorrect, so the following URL is correct?
\n\nhttps://www.kaggle.com/c/landmark-recognition-2019/discussion/94523
", "votes": 3, "replies": [ { "id": 951544, "author_name": "Theo Viel", "author_url": "", "post_date": "2020-07-30T07:50:41.040000", "content": "Fixed, thanks :)
", "votes": 0, "replies": [] } ] }, { "id": 951951, "author_name": "sayantan", "author_url": "", "post_date": "2020-07-30T14:13:40.323000", "content": "Can someone explain what Image Descriptors mean in the 1st place paper??
", "votes": 2, "replies": [ { "id": 953863, "author_name": "TEnsorSAge", "author_url": "", "post_date": "2020-08-01T07:34:30.647000", "content": "output from the last convolution layer for an image. this output contains the features that are important to classify
", "votes": 2, "replies": [] }, { "id": 960182, "author_name": "sayantan", "author_url": "", "post_date": "2020-08-06T07:49:20.267000", "content": "Thank you!
", "votes": 0, "replies": [] } ] }, { "id": 958041, "author_name": "Tolga", "author_url": "", "post_date": "2020-08-04T18:06:01.127000", "content": "2nd place code does not seem to be available.
", "votes": 0, "replies": [ { "id": 962742, "author_name": "Alexander Zarichkovyi", "author_url": "", "post_date": "2020-08-08T11:57:19.857000", "content": "Seems that authors moved source code somewhere else, but you can always retrieve it from git history. Here, original commit for landmark models: https://github.com/PaddlePaddle/models/tree/cc473ce799f3f612156d5086814d9750eb012d2a/PaddleCV/Research/landmark
", "votes": 2, "replies": [] }, { "id": 962830, "author_name": "Tolga", "author_url": "", "post_date": "2020-08-08T13:16:57.620000", "content": "Good to know. Thank you!
", "votes": 0, "replies": [] } ] }, { "id": 953534, "author_name": "Yu S.C. 2020", "author_url": "", "post_date": "2020-07-31T21:33:36.820000", "content": "When looking at the papers, I see they stated the public/private score on every steps? how to make this? are there any function to acquire score in the notebook? or it has to be obtained by new notebooks on every step?
", "votes": 0, "replies": [] }, { "id": 953170, "author_name": "Shaitender Singh", "author_url": "", "post_date": "2020-07-31T15:21:11", "content": "Indeed Helpful !!! Thanks for sharing @theoviel
", "votes": 0, "replies": [] }, { "id": 952629, "author_name": "Nikita Butakov", "author_url": "", "post_date": "2020-07-31T05:16:47.137000", "content": "Thanks for the post! Sounds like the challenge in this competition will be figuring out how to optimize the training data set curation and confidence score estimation within the constraints of Kaggle notebooks.
", "votes": 0, "replies": [] }, { "id": 952239, "author_name": "Yassine Alouini", "author_url": "", "post_date": "2020-07-30T18:28:35.773000", "content": "Thought about making this thread but you were faster. Thanks for the collection. :)
", "votes": 0, "replies": [] }, { "id": 951558, "author_name": "", "author_url": "", "post_date": "2020-07-30T08:01:29.367000", "content": "", "votes": 0, "replies": [] }, { "id": 965296, "author_name": "Chandan Verma", "author_url": "", "post_date": "2020-08-10T14:28:35.227000", "content": "Thanks for sharing :)
", "votes": 3, "replies": [] }, { "id": 964515, "author_name": "Connor Shorten", "author_url": "", "post_date": "2020-08-10T00:46:03.480000", "content": "Thanks for sharing!
", "votes": 0, "replies": [] }, { "id": 951869, "author_name": "Shubham Baghe", "author_url": "", "post_date": "2020-07-30T13:16:05.123000", "content": "Thank you!!
", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "951098": "Papers for the top 3 teams :\n- 1st : JL -> https://storage.googleapis.com/kaggle-forum-message-attachments/549732/13471/Team%20JL%20Solution%20to%20Google%20Landmark%20Recognition%202019.pdf \n- 2nd : GLRunner -> https://arxiv.org/abs/1906.03990\n- 3rd : smlyaka -> https://arxiv.org/abs/1906.04087\n\n\nSlides for some top-10 teams -> https://drive.google.com/open?id=14PdHtRBXE3DTYxu5fpoDtTZUTm0Z9MXr\n\n1st place writeup -> https://www.kaggle.com/c/landmark-recognition-2019/discussion/94523\n\n2nd place code -> https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/Research/landmark\n\n8th place writeup -> https://www.kaggle.com/c/landmark-recognition-2019/discussion/94512", "951608": "@theoviel thank you! also I would like to add some helpful urls:\n\n2019: https://www.kaggle.com/c/landmark-recognition-2019/\n2018: https://www.kaggle.com/c/landmark-recognition-challenge/", "951294": "Thanks for your post.\n\"1st place writeup\" is incorrect, so the following URL is correct?\n\nhttps://www.kaggle.com/c/landmark-recognition-2019/discussion/94523", "951951": "Can someone explain what **Image Descriptors** mean in the 1st place paper??", "958041": "2nd place code does not seem to be available.", "953534": "When looking at the papers, I see they stated the public/private score on every steps? how to make this? are there any function to acquire score in the notebook? or it has to be obtained by new notebooks on every step? ", "953170": "Indeed Helpful !!! Thanks for sharing @theoviel ", "952629": "Thanks for the post! Sounds like the challenge in this competition will be figuring out how to optimize the training data set curation and confidence score estimation within the constraints of Kaggle notebooks.", "952239": "Thought about making this thread but you were faster. Thanks for the collection. :)", "951558": "", "965296": "Thanks for sharing :)\n", "964515": "Thanks for sharing!", "951869": "Thank you!!\n" } }