{"id":13704806,"url":"https://github.com/jizhu1023/DMAN_MOT","last_synced_at":"2025-05-05T12:32:37.279Z","repository":{"id":42352152,"uuid":"181193790","full_name":"jizhu1023/DMAN_MOT","owner":"jizhu1023","description":"Code for Online Multi-Object Tracking with Dual Matching Attention Network, ECCV 2018","archived":false,"fork":false,"pushed_at":"2019-07-10T15:54:01.000Z","size":19475,"stargazers_count":84,"open_issues_count":1,"forks_count":15,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-13T12:40:58.523Z","etag":null,"topics":["dman","dual-matching-attention-network","mot","multi-object-tracker","multi-object-tracking","multi-pedestrian-tracking","multi-person-tracking","object-tracking","online-mot"],"latest_commit_sha":null,"homepage":"https://jizhu1023.github.io/eccv18_mot/index.html","language":"MATLAB","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jizhu1023.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-04-13T15:49:37.000Z","updated_at":"2024-05-28T15:34:08.000Z","dependencies_parsed_at":"2022-08-28T05:52:46.011Z","dependency_job_id":null,"html_url":"https://github.com/jizhu1023/DMAN_MOT","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jizhu1023%2FDMAN_MOT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jizhu1023%2FDMAN_MOT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jizhu1023%2FDMAN_MOT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jizhu1023%2FDMAN_MOT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jizhu1023","download_url":"https://codeload.github.com/jizhu1023/DMAN_MOT/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252497665,"owners_count":21757656,"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":["dman","dual-matching-attention-network","mot","multi-object-tracker","multi-object-tracking","multi-pedestrian-tracking","multi-person-tracking","object-tracking","online-mot"],"created_at":"2024-08-02T22:00:17.493Z","updated_at":"2025-05-05T12:32:32.246Z","avatar_url":"https://github.com/jizhu1023.png","language":"MATLAB","funding_links":[],"categories":["算法论文"],"sub_categories":["**2018**"],"readme":"# Online Multi-Object Tracking with DMANs\n\nThis is the implementation of our ECCV 2018 paper [Online Multi-Object Tracking with Dual Matching Attention Networks](https://arxiv.org/abs/1902.00749). We integrate the ECO [1] for single object tracking. The code framework for MOT benefits from the MDP [2].\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"800\" src=\"DMAN.png\"\u003e\n\u003c/p\u003e\n\u003cp align=\"justify\"\u003e\n\n# Prerequisites\n- Cuda 8.0\n- Cudnn 5.1\n- Python 2.7\n- Keras 2.0.5\n- Tensorflow 1.1.0\n\nFor example:\n\u003cpre\u003e\u003ccode\u003econda create -n mot anaconda python=2.7\nconda activate mot\nconda install -c menpo opencv\npip install tensorflow-gpu==1.1.0\npip install keras==2.0.5\n\u003c/code\u003e\u003c/pre\u003e\n\n# Usage\n1. Download the [DMAN model](https://zhiyanapp-build-release.oss-cn-shanghai.aliyuncs.com/zhuji_file/spatial_temporal_attention_model.h5) and put it into the \"model/\" folder.\n2. Download the [MOT16 dataset](https://motchallenge.net/data/MOT16/), unzip it to the \"data/\" folder.\n3. Cd to the \"ECO/\" folder, run the script install.m to compile libs for the ECO tracker\n4. Run the socket server script:\n\u003cpre\u003e\u003ccode\u003epython calculate_similarity.py\n\u003c/code\u003e\u003c/pre\u003e\n5. Run the socket client script DMAN_demo.m in Matlab.\n# Citation\n\nIf you use this code, please consider citing:\n\n\u003cpre\u003e\u003ccode\u003e@inproceedings{zhu-eccv18-DMAN,\n    author    = {Zhu, Ji and Yang, Hua and Liu, Nian and Kim, Minyoung and Zhang, Wenjun and Yang, Ming-Hsuan},\n    title     = {Online Multi-Object Tracking with Dual Matching Attention Networks},\n    booktitle = {European Computer Vision Conference},\n    year      = {2018},\n}\n\u003c/code\u003e\u003c/pre\u003e\n\n# References\n[1] Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ECO: Efficient convolution operators for tracking. In: CVPR (2017)\n\n[2] Xiang, Y., Alahi, A., Savarese, S.: Learning to track: Online multi-object tracking by decision making. In: ICCV (2015)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjizhu1023%2FDMAN_MOT","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjizhu1023%2FDMAN_MOT","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjizhu1023%2FDMAN_MOT/lists"}