{"id":18696984,"url":"https://github.com/vra/action-recognition-using-3d-resnet","last_synced_at":"2025-04-12T07:31:49.736Z","repository":{"id":73652108,"uuid":"112016069","full_name":"vra/action-recognition-using-3d-resnet","owner":"vra","description":"Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.","archived":false,"fork":false,"pushed_at":"2018-11-25T13:13:03.000Z","size":170,"stargazers_count":41,"open_issues_count":3,"forks_count":12,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-26T02:51:14.527Z","etag":null,"topics":["3d-resnet","action-recognition","cnn","deep-learning","extract-features","hmdb51","ucf101"],"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/vra.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":"2017-11-25T15:57:42.000Z","updated_at":"2025-02-22T20:39:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"3d4a4cbc-3ab1-4f8d-8769-cb930e132f28","html_url":"https://github.com/vra/action-recognition-using-3d-resnet","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/vra%2Faction-recognition-using-3d-resnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vra%2Faction-recognition-using-3d-resnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vra%2Faction-recognition-using-3d-resnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vra%2Faction-recognition-using-3d-resnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vra","download_url":"https://codeload.github.com/vra/action-recognition-using-3d-resnet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248533861,"owners_count":21120179,"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":["3d-resnet","action-recognition","cnn","deep-learning","extract-features","hmdb51","ucf101"],"created_at":"2024-11-07T11:22:16.570Z","updated_at":"2025-04-12T07:31:49.730Z","avatar_url":"https://github.com/vra.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# action-recognition-using-3d-resnet\nUse [3D ResNet](https://github.com/kenshohara/video-classification-3d-cnn-pytorch) to extract features of UCF101 and HMDB51 and then classify them.\n\n# how to use\n\n 1. Clone this repo:\n ```bash\n\tgit clone https://github.com/vra/action-recognition-using-3d-resnet.git\n ```\n\n 2. Download [3D ResNet](https://github.com/kenshohara/video-classification-3d-cnn-pytorch)\n\n 3. Download its pretrained [models](https://github.com/kenshohara/3D-ResNets-PyTorch/releases), put these models to this repo's `data/models/`\n\n 4. run the script under `scripts` under to extract 3D resnet features of UCF101 and HMDB51:\n ```bash\n\tbash scripts/extract_resnet_3d_features.sh /path/to/video-classification/3d-cnn-pytorch ucf101 /path/to/ucf101/videos \n\tbash scripts/extract_resnet_3d_features.sh /path/to/video-classification/3d-cnn-pytorch hmdb51 /path/to/hmdb51/videos \n ```\nAlso, you can download my extracted features of ucf101 and hmdb51 at [here](https://drive.google.com/open?id=12BM8ibl5oFziM-59JqXmsqMjtx7_qthZ) and [here](https://drive.google.com/open?id=178U8N6dPBfpaHYMxdOCCWpLa4hl6kFjk). **Remember to put the first one to `data/jsons/ucf101` before you download the second one, otherwise the first one will be convered.**\n\n5. Run `main.py` to classify extracted 3D resnet features:\n ```bash\n\tpython main.py -dataset hmdb51\n ```\nResults:\n\nstrategy | dataset | accuracy\n-------- | ------- | -------\nmean\t | ucf101  | 0.8487\nmax\t     | ucf101  | 0.8667\nmean\t | hmdb51  | 0.5425\nmax\t     | hmdb51  | 0.5399\n\n\n\n  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvra%2Faction-recognition-using-3d-resnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvra%2Faction-recognition-using-3d-resnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvra%2Faction-recognition-using-3d-resnet/lists"}