{"id":37180246,"url":"https://github.com/cocoxili/cmpc","last_synced_at":"2026-01-14T20:57:25.141Z","repository":{"id":170199924,"uuid":"486233090","full_name":"Cocoxili/CMPC","owner":"Cocoxili","description":"[IJCAI2022] Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast","archived":false,"fork":false,"pushed_at":"2023-10-25T03:21:28.000Z","size":9823,"stargazers_count":20,"open_issues_count":1,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-28T10:11:40.140Z","etag":null,"topics":["biometric-matching","crossmodal-retrieval","deep-learning","multimodal-learning","representation-learning","voice-face-association","voxceleb"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Cocoxili.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,"governance":null}},"created_at":"2022-04-27T14:45:31.000Z","updated_at":"2025-01-12T14:34:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"244a2ccd-834c-4510-b16d-3bc01a09d923","html_url":"https://github.com/Cocoxili/CMPC","commit_stats":null,"previous_names":["cocoxili/cmpc"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/Cocoxili/CMPC","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cocoxili%2FCMPC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cocoxili%2FCMPC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cocoxili%2FCMPC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cocoxili%2FCMPC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Cocoxili","download_url":"https://codeload.github.com/Cocoxili/CMPC/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cocoxili%2FCMPC/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28434500,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T18:57:19.464Z","status":"ssl_error","status_checked_at":"2026-01-14T18:52:48.501Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["biometric-matching","crossmodal-retrieval","deep-learning","multimodal-learning","representation-learning","voice-face-association","voxceleb"],"created_at":"2026-01-14T20:57:24.643Z","updated_at":"2026-01-14T20:57:25.132Z","avatar_url":"https://github.com/Cocoxili.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast\n\nThis is the PyTorch implementation for CMPC, as described in our paper:\n\n\n**[Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast](https://arxiv.org/abs/2204.14057)**\n\n```angular2html\n@inproceedings{zhu2022unsupervised,\n  title={Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast},\n  author={Zhu, Boqing and Xu, Kele and Wang, Changjian and Qin, Zheng and Sun, Tao and Wang, Huaimin and Peng, Yuxing},\n  booktitle={Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI-22}},\n  pages={3787--3794},\n  year={2022},\n  month={7}\n}\n```\n\n\n![Framework](img/fig_pipeline.png)\n\n\nWe also provide the [pretrained model](#unsupervised-training) and [testing resources](#testing-data).\n\n\n### Requirments:\n\n* torch==1.7.0+cu110\n* matplotlib==3.4.3\n* pykeops==1.5\n* pandas==1.1.3\n* librosa==0.6.2\n* Pillow==9.0.1\n* PyYAML==6.0\n* scikit_learn==1.0.2\n\n### Download Pre-trained Models\n\n\u003ca href=\"https://github.com/Cocoxili/CMPC/releases/download/v1.0.0/checkpoint_CID.pth.tar\"\u003eCID\u003c/a\u003e| \u003ca href=\"https://github.com/Cocoxili/CMPC/releases/download/v1.0.0/checkpoint_CMPC.pth.tar\"\u003eCMPC\u003c/a\u003e\n------ | ------\n\n### Data Pre-processing\n\nIn order to speed up the iteration of training, we extract the logmel features of voice data through pre-processing.\n\n```bash\n\u003e\u003e cd experiments/cmpc\n\u003e\u003e python data_transform.py --wav_dir {directory-of-the-wav-file} --logmel_dir {destination-path}\n```\n\n\n### Unsupervised Training\n\nThe configurations are written in the CONFIG.yaml file, which can be changed according to your needs, \nsuch as the path information. The unsupervised training process can begin as:\n```bash\n\u003e\u003e python train.py CONFIG.yaml\n```\n\n### Evalution on our trained model\nExperiments on three evalution protocals: matching, verification and retrieval. The '--ckp_path' could be\nthe path of downloaded model or your trained model.\n\n```bash\n\u003e\u003e python matching.py CONFIG.yaml --ckp_path {checkpoint path}\n\u003e\u003e python verification.py CONFIG.yaml --ckp_path {checkpoint path}\n\u003e\u003e python retrieval.py CONFIG.yaml --ckp_path {checkpoint path}\n```\n\n### Testing data\n\n[Matching](./data/matching), [verification](./data/veriflist) and [retrieval](./data/retrieval) testing data is released at [./data](./data) directory.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcocoxili%2Fcmpc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcocoxili%2Fcmpc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcocoxili%2Fcmpc/lists"}