{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"ViTAE-Transformer-Remote-Sensing","owner":"ViTAE-Transformer","isFork":false,"description":"A comprehensive list [SAMRS@NeurIPS'23, RVSA@TGRS'22, RSP@TGRS'22] of our research works related to remote sensing, including papers, codes, and citations. Note: The repo for [TGRS'22] \"An Empirical Study of Remote Sensing Pretraining\" has been moved to: <a href=\"https://github.com/ViTAE-Transformer/RSP\">https://github.com/ViTAE-Transformer/RSP</a>","allTopics":["deep-learning","remote-sensing","classification","object-detection","transfer-learning","semantic-segmentation","change-detection","self-supervised-learning","vision-transformer"],"primaryLanguage":{"name":"TeX","color":"#3D6117"},"pullRequestCount":0,"issueCount":9,"starsCount":428,"forksCount":53,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-06T01:15:00.759Z"}},{"type":"Public","name":"MTP","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [JSTARS'24] \"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining\"","allTopics":["deep-learning","remote-sensing","classification","object-detection","transfer-learning","semantic-segmentation","change-detection","pre-training","foundation-models"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":112,"forksCount":6,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-06T01:08:54.388Z"}},{"type":"Public","name":"DeepSolo","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [CVPR'23] \"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting\" &amp; [ArXiv'23] \"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting\"","allTopics":["detection-transformer","scene-text-spotting","chinese-text-spotting","multilingual-text-spotting","explicit-point-query"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":4,"issueCount":28,"starsCount":231,"forksCount":27,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-27T03:26:10.147Z"}},{"type":"Public","name":"LeMeViT","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [IJCAI'24] \"LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation\"","allTopics":["deep-learning","remote-sensing","attention","object-detection","semantic-segmentation","scene-classification","vision-transformer"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":30,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-22T12:07:19.375Z"}},{"type":"Public","name":"SimDistill","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [AAAI 2024] \"SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection\"\"","allTopics":["deep-learning","simulation","distillation","3d-object-detection","bird-view-image"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":5,"starsCount":23,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T03:39:34.977Z"}},{"type":"Public","name":"APTv2","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for the extension of [NeurIPS'22] \"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking\": <a href=\"https://github.com/pandorgan/APT-36K\">https://github.com/pandorgan/APT-36K</a>","allTopics":["benchmark","deep-learning","dataset","transfer-learning","pose-estimation","few-shot-learning","pre-training","pose-tracking","animal-pose-estimation","vision-transformer"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":7,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-15T07:51:46.060Z"}},{"type":"Public","name":"ViTAE-Transformer-Scene-Text-Detection","owner":"ViTAE-Transformer","isFork":false,"description":"A comprehensive list [I3CL@IJCV'22, DPText-DETR@AAAI'23, DeepSolo(++)@ CVPR'23] of our research works related to scene text detection and spotting, including papers, codes. Note: The official repo for \"I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped ...\" has been moved to: <a href=\"https://github.com/ViTAE-Transformer/I3CL\">https://github.com/ViTAE-Transformer/I3CL</a>","allTopics":["ocr","deep-learning","pytorch","scene-text-detection","vision-transformer","scene-text-spotting"],"primaryLanguage":{"name":"TeX","color":"#3D6117"},"pullRequestCount":0,"issueCount":0,"starsCount":71,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-28T04:19:54.142Z"}},{"type":"Public","name":"QFormer","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [TPAMI'23] \"Vision Transformer with Quadrangle Attention\"","allTopics":["deep-learning","backbone","classification","object-detection","attention-mechanism","semantic-segmentation","pose-estimation","vision-transformer"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":128,"forksCount":7,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-10T23:27:50.174Z"}},{"type":"Public","name":"P3M-Net","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [IJCV'23] \"Rethinking Portrait Matting with Privacy Preserving\"","allTopics":["image-matting","vision-transformer","deep-learning","pytorch"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":6,"starsCount":79,"forksCount":6,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-30T18:11:25.658Z"}},{"type":"Public","name":"SAMRS","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [NeurIPS'23] \"SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model\"","allTopics":["deep-learning","sam","transfer-learning","semantic-segmentation","pre-training","segment-anything-model","dataset","remote-sensing"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":17,"starsCount":242,"forksCount":13,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-25T01:48:42.343Z"}},{"type":"Public","name":"RSP","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [TGRS'22] \"An Empirical Study of Remote Sensing Pretraining\"","allTopics":["deep-learning","remote-sensing","classification","imagenet","object-detection","transfer-learning","semantic-segmentation","change-detection","pre-training","foundation-models"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":11,"starsCount":126,"forksCount":6,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-15T10:26:23.164Z"}},{"type":"Public","name":"Remote-Sensing-RVSA","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [TGRS'22] \"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model\"","allTopics":["deep-learning","remote-sensing","object-detection","transfer-learning","semantic-segmentation","self-supervised-learning","foundation-model"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":18,"starsCount":389,"forksCount":29,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-20T21:15:11.022Z"}},{"type":"Public","name":"ViTPose","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [NeurIPS'22] \"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation\" and [TPAMI'23] \"ViTPose++: Vision Transformer for Generic Body Pose Estimation\"","allTopics":["deep-learning","pytorch","pose-estimation","mae","distillation","self-supervised-learning","vision-transformer"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":5,"issueCount":80,"starsCount":1226,"forksCount":172,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-03T04:43:09.112Z"}},{"type":"Public","name":"SAMText","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for the technical report \"Scalable Mask Annotation for Video Text Spotting\"","allTopics":["deep-learning","sam","dataset","scene-text-spotting","segment-anything-model","video-text-spotting"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":1,"starsCount":17,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-03T02:19:52.647Z"}},{"type":"Public","name":"I3CL","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [IJCV'22] \"I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection\"","allTopics":["scene-text-detection","vision-transformer","deep-learning","pytorch"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":7,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-12T05:16:25.728Z"}},{"type":"Public","name":"ViTAE-Transformer-Matting","owner":"ViTAE-Transformer","isFork":false,"description":"A comprehensive list [AIM@IJCAI'21, P3M@MM'21, GFM@IJCV'22, RIM@CVPR'23, P3MNet@IJCV'23] of our research works related to image matting, including papers, codes, datasets, demos, and citations. Note: The repo for [IJCV'23] \"Rethinking Portrait Matting with Privacy Preserving\" has been moved to: <a href=\"https://github.com/ViTAE-Transformer/P3M-Net\">https://github.com/ViTAE-Transformer/P3M-Net</a>","allTopics":["computer-vision","deep-learning","survey","privacy-preserving","image-matting","vision-transformer"],"primaryLanguage":{"name":"TeX","color":"#3D6117"},"pullRequestCount":0,"issueCount":1,"starsCount":227,"forksCount":24,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-11T05:48:56.400Z"}},{"type":"Public","name":"ViTAE-Transformer","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [NeurIPS'21] \"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias\" and [IJCV'22] \"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond\"","allTopics":["imagenet","object-detection","semantic-segmentation","mscoco","ade20k","imagenet-classification","vision-transformer","vitae-transformer","deep-learning"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":10,"starsCount":245,"forksCount":28,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-05T02:02:47.792Z"}},{"type":"Public","name":"ViTAE-VSA","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [ECCV'22] \"VSA: Learning Varied-Size Window Attention in Vision Transformers\"","allTopics":["deep-learning","backbone","classification","attention-mechanism","vision-transformer","object-detection","instance-segmentation"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":8,"starsCount":151,"forksCount":9,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-17T01:44:18.430Z"}},{"type":"Public","name":"VOS-LLB","owner":"ViTAE-Transformer","isFork":false,"description":"The official repo for [AAAI'23] \"Learning to Learn Better for Video Object Segmentation\"","allTopics":["video-object-segmentation","vos","vision-transformer","deep-learning"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":11,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-02-17T04:06:27.674Z"}},{"type":"Public","name":"ViTDet","owner":"ViTAE-Transformer","isFork":false,"description":"Unofficial implementation for [ECCV'22] \"Exploring Plain Vision Transformer Backbones for Object Detection\"","allTopics":["vision-transformer","deep-learning","pytorch","object-detection"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":17,"starsCount":517,"forksCount":46,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-04-24T06:11:54.759Z"}}],"repositoryCount":20,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}