{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/revisiting-feature-prediction-for-learning-1","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","arxiv_id":"2404.08471","date":"2024-02-15","proceeding":"arXiv preprint 2024 2","authors":["Adrien Bardes","Quentin Garrido","Jean Ponce","Xinlei Chen","Michael Rabbat","Yann Lecun","Mahmoud Assran","Nicolas Ballas"],"abstract":"This paper explores feature prediction as a stand-alone objective for unsupervised learning from video and introduces V-JEPA, a collection of vision models trained solely using a feature prediction objective, without the use of pretrained image encoders, text, negative examples, reconstruction, or other sources of supervision. The models are trained on 2 million videos collected from public datasets and are evaluated on downstream image and video tasks. Our results show that learning by predicting video features leads to versatile visual representations that perform well on both motion and appearance-based tasks, without adaption of the model's parameters; e.g., using a frozen backbone. Our largest model, a ViT-H/16 trained only on videos, obtains 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet1K.","url_abs":"https://arxiv.org/abs/2404.08471v1","url_pdf":"https://arxiv.org/pdf/2404.08471v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"revisiting-feature-prediction-for-learning-1","repo_url":"https://github.com/facebookresearch/jepa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.08471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08471"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/jepa","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"bf083ed6ad81d69e","entry":"apply_masks","repo":"facebookresearch/jepa","repo_kind":"official","path":"src/masks/utils.py","file_url":"https://github.com/facebookresearch/jepa/blob/HEAD/src/masks/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf083ed6ad81d69e"}},{"code_sha256_prefix":"7efb9fc5ff1c1200","entry":"init_data","repo":"facebookresearch/jepa","repo_kind":"official","path":"src/datasets/data_manager.py","file_url":"https://github.com/facebookresearch/jepa/blob/HEAD/src/datasets/data_manager.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7efb9fc5ff1c1200"}},{"code_sha256_prefix":"2004d0e6ae873f2e","entry":"main","repo":"facebookresearch/jepa","repo_kind":"official","path":"app/scaffold.py","file_url":"https://github.com/facebookresearch/jepa/blob/HEAD/app/scaffold.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2004d0e6ae873f2e"}},{"code_sha256_prefix":"16d0113b5f3ab648","entry":"main","repo":"facebookresearch/jepa","repo_kind":"official","path":"evals/scaffold.py","file_url":"https://github.com/facebookresearch/jepa/blob/HEAD/evals/scaffold.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"16d0113b5f3ab648"}},{"code_sha256_prefix":"133b0c3541547057","entry":"make_imagedataset","repo":"facebookresearch/jepa","repo_kind":"official","path":"src/datasets/image_dataset.py","file_url":"https://github.com/facebookresearch/jepa/blob/HEAD/src/datasets/image_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"133b0c3541547057"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}