{"id":31060841,"url":"https://github.com/rehglab/tracking_objectness","last_synced_at":"2025-09-15T10:48:40.661Z","repository":{"id":253015100,"uuid":"842200513","full_name":"RehgLab/tracking_objectness","owner":"RehgLab","description":null,"archived":false,"fork":false,"pushed_at":"2024-12-06T23:21:05.000Z","size":1150,"stargazers_count":2,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-07T00:25:18.494Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/RehgLab.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":"2024-08-13T22:02:07.000Z","updated_at":"2024-12-06T23:21:09.000Z","dependencies_parsed_at":"2024-08-14T01:02:08.406Z","dependency_job_id":"c7fce07e-8c54-4bb9-985b-4e26438bcda3","html_url":"https://github.com/RehgLab/tracking_objectness","commit_stats":null,"previous_names":["rehglab/tracking_objectness"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/RehgLab/tracking_objectness","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RehgLab%2Ftracking_objectness","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RehgLab%2Ftracking_objectness/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RehgLab%2Ftracking_objectness/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RehgLab%2Ftracking_objectness/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RehgLab","download_url":"https://codeload.github.com/RehgLab/tracking_objectness/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RehgLab%2Ftracking_objectness/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":275245998,"owners_count":25430803,"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","status":"online","status_checked_at":"2025-09-15T02:00:09.272Z","response_time":75,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2025-09-15T10:48:35.220Z","updated_at":"2025-09-15T10:48:40.640Z","avatar_url":"https://github.com/RehgLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# tracking_objectness\n\nCode for ECCV-ILR 2024 Workshop paper **Leveraging Object Priors for Point Tracking**\n\n# Requirements\n\nCreate conda environment for this code base:\n```\nconda create -n mask_pips python=3.8\nconda activate mask_pips\nconda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia\npip install -r requirements.txt\n\n```\n# Training\n\nUse `export_mp4_dataset.py` file to generate clips from the PointOdyssey training set following [Pips++](https://github.com/aharley/pips2) and then run `python train.py` to start training.\n\n# Testing\n\nTo evaluate the performance on the datasets reported in the paper, use testing scripts in the pips2 directory with the saved model. \n\nFor **TAP-VID-DAVIS**: `pip2/test_on_tap.py`  \nFor **CroHD**: `pips2/test_on_cro.py`  \nFor **PointOdyssey**: `pips2/test_on_pod.py`   \n\nTo replicate the performance from the paper use our [trained weights](https://drive.google.com/drive/folders/1NStVTvo3iMRKcA3vaat7yFjwKHgpGrIH?usp=sharing) for the reference model. For TAP-VID-DAVIS, we load full sequence into memory at once, for others we use `S=36`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frehglab%2Ftracking_objectness","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frehglab%2Ftracking_objectness","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frehglab%2Ftracking_objectness/lists"}