{"id":17349134,"url":"https://github.com/lupin1998/adcf_2019","last_synced_at":"2025-06-13T23:41:15.930Z","repository":{"id":158470635,"uuid":"207212368","full_name":"Lupin1998/ADCF_2019","owner":"Lupin1998","description":"Adaptive Target Tracking Algorithm with Dynamic Weighted Hierarchical Convolutional Neural Network Feature (http://xwxt.sict.ac.cn/CN/abstract/abstract5795.shtml)","archived":false,"fork":false,"pushed_at":"2019-09-09T07:21:18.000Z","size":7893,"stargazers_count":3,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-08T09:05:46.916Z","etag":null,"topics":["convolutional-neural-networks","kcf-tracker","pytorch","visual-tracking"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Lupin1998.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-09-09T03:01:11.000Z","updated_at":"2022-06-14T21:37:37.000Z","dependencies_parsed_at":null,"dependency_job_id":"07d14f67-7ac8-4613-b827-f93bebd92be4","html_url":"https://github.com/Lupin1998/ADCF_2019","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Lupin1998/ADCF_2019","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lupin1998%2FADCF_2019","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lupin1998%2FADCF_2019/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lupin1998%2FADCF_2019/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lupin1998%2FADCF_2019/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Lupin1998","download_url":"https://codeload.github.com/Lupin1998/ADCF_2019/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lupin1998%2FADCF_2019/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259737638,"owners_count":22903843,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["convolutional-neural-networks","kcf-tracker","pytorch","visual-tracking"],"created_at":"2024-10-15T16:54:50.684Z","updated_at":"2025-06-13T23:41:15.900Z","avatar_url":"https://github.com/Lupin1998.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ADCF_2019\ncode for Adaptive Target Tracking Algorithm with Dynamic Weighted Hierarchical Convolutional Neural Network Feature.\n\n## 1. Intro\n - This project includes source code for first experience in our paper based on PyTorch and usage of CNN features.\n - For models, inlcuding mainstream models from torchvision [(PyTorch)](https://pytorch.org/docs/stable/torchvision/models.html) in \n CNNFeat. Models from tensorflow or caffe should perform better on visual tracking, such as [(pretrained-models)](https://github.com/ZhaoJ9014/face.evoLVe.PyTorch) or [(matconvnet)](https://github.com/vlfeat/matconvnet).\n## 2. Install\nnumpy==1.14.5 \ntorch==0.4.0 \ntorchvision==0.4.0 \nscipy==1.0.0 \nopencv_python==3.4.2 \nmatplotlib==2.1.2 \nnumba==0.43.1 \npillow==6.1.0 \n## 3. Usage\n- Download seqs [(Visual BenchMark)](http://cvlab.hanyang.ac.kr/tracker_benchmark/datasets.html) and save to Sequence. Change file path before running KCF with CNN features. Choose to run different CNN of single conv-layer or coarse-to-fine features in run.py. \n\n  ```\n  python run.py\n  ```\n- Visualize different CNN feature maps in CNNfeat. Downloads MobileNet_v3 models in [(mobilenetv3)](https://github.com/xiaolai-sqlai/mobilenetv3).\n  ```\n  from PIL import Image\n  from CNN_feat.LightWeight_cnn_feat import LightWeight_feat,LightCNN\n  net = LightWeight_feat(LightCNN.SqueezeNet.value,'1_1', 1)\n  # visualize SqueezeNet-1_1 conv1\n  img = Image.open('Seq/boy/img/0001.jpg')\n  feat = net.get_cnn_feat(img,True,False,False)\n  ```\n- Test old vision of KCF with hog features in 2015-KCF-DSST. Install 'numba' before if using hog features.\n  ```\n  python run.py\n  ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flupin1998%2Fadcf_2019","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flupin1998%2Fadcf_2019","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flupin1998%2Fadcf_2019/lists"}