{"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/broaden-your-views-for-self-supervised-video","title":"Broaden Your Views for Self-Supervised Video Learning","arxiv_id":"2103.16559","date":"2021-03-30","proceeding":"ICCV 2021 10","authors":["Adrià Recasens","Pauline Luc","Jean-Baptiste Alayrac","Luyu Wang","Ross Hemsley","Florian Strub","Corentin Tallec","Mateusz Malinowski","Viorica Patraucean","Florent Altché","Michal Valko","Jean-bastien Grill","Aäron van den Oord","Andrew Zisserman"],"abstract":"Most successful self-supervised learning methods are trained to align the representations of two independent views from the data. State-of-the-art methods in video are inspired by image techniques, where these two views are similarly extracted by cropping and augmenting the resulting crop. However, these methods miss a crucial element in the video domain: time. We introduce BraVe, a self-supervised learning framework for video. In BraVe, one of the views has access to a narrow temporal window of the video while the other view has a broad access to the video content. Our models learn to generalise from the narrow view to the general content of the video. Furthermore, BraVe processes the views with different backbones, enabling the use of alternative augmentations or modalities into the broad view such as optical flow, randomly convolved RGB frames, audio or their combinations. We demonstrate that BraVe achieves state-of-the-art results in self-supervised representation learning on standard video and audio classification benchmarks including UCF101, HMDB51, Kinetics, ESC-50 and AudioSet.","url_abs":"https://arxiv.org/abs/2103.16559v3","url_pdf":"https://arxiv.org/pdf/2103.16559v3.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":"broaden-your-views-for-self-supervised-video","repo_url":"https://github.com/deepmind/brave","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-action-recognition","task_name":"Self-Supervised Action Recognition"},{"task_slug":"self-supervised-audio-classification","task_name":"Self-Supervised Audio Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"BraVe:V-FA (TSM-50x2)","rank_in_archive_order":6,"of":48,"metrics":{"Frozen":"false","Top-1 Accuracy":"70.5"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51-1","task":"Self-Supervised Action Recognition","dataset":"HMDB51 (finetuned)","model":"BraVe:V-FA (TSM-50x2)","rank_in_archive_order":1,"of":14,"metrics":{"Top-1 Accuracy":"77.8"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on","task":"Self-Supervised Action Recognition","dataset":"Kinetics-600","model":"BraVe:V-FA (TSM-50x2)","rank_in_archive_order":3,"of":5,"metrics":{"Top-1 Accuracy":"71.4"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101","task":"Self-Supervised Action Recognition","dataset":"UCF101","model":"BraVe:V-FA (TSM-50x2)","rank_in_archive_order":15,"of":53,"metrics":{"3-fold Accuracy":"93.1","Frozen":"false"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101-1","task":"Self-Supervised Action Recognition","dataset":"UCF101 (finetuned)","model":"BraVe:V-FA (TSM-50x2)","rank_in_archive_order":1,"of":14,"metrics":{"3-fold Accuracy":"95.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.16559","atlas_url":"https://app.syntology.ai/?focus=2103.16559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16559"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/deepmind/brave","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"d72aee9f7872a1f4","entry":"compute_linearly_spaced_sample_indices","repo":"deepmind/brave","repo_kind":"official","path":"brave/datasets/sampling.py","file_url":"https://github.com/deepmind/brave/blob/HEAD/brave/datasets/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d72aee9f7872a1f4"}},{"code_sha256_prefix":"8bd26bff58d47d3a","entry":"md5","repo":"deepmind/brave","repo_kind":"official","path":"brave/download_hmdb.py","file_url":"https://github.com/deepmind/brave/blob/HEAD/brave/download_hmdb.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8bd26bff58d47d3a"}},{"code_sha256_prefix":"e6ad315cfb7d7612","entry":"random_sample","repo":"deepmind/brave","repo_kind":"official","path":"brave/datasets/sampling.py","file_url":"https://github.com/deepmind/brave/blob/HEAD/brave/datasets/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e6ad315cfb7d7612"}},{"code_sha256_prefix":"ca07ab87c895635c","entry":"tf_record_shard_reader","repo":"deepmind/brave","repo_kind":"official","path":"brave/datasets/media_sequences.py","file_url":"https://github.com/deepmind/brave/blob/HEAD/brave/datasets/media_sequences.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ca07ab87c895635c"}},{"code_sha256_prefix":"4c090fcd18780345","entry":"write_tf_record_dataset_fixture","repo":"deepmind/brave","repo_kind":"official","path":"brave/datasets/fixtures.py","file_url":"https://github.com/deepmind/brave/blob/HEAD/brave/datasets/fixtures.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c090fcd18780345"}},{"code_sha256_prefix":"4e1f5f77cae09400","entry":"extend_sequence","repo":"deepmind/brave","repo_kind":"official","path":"brave/datasets/media_sequences.py","file_url":"https://github.com/deepmind/brave/blob/HEAD/brave/datasets/media_sequences.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e1f5f77cae09400"}},{"code_sha256_prefix":"315e821fb79e66f7","entry":"media_sequence_dataset","repo":"deepmind/brave","repo_kind":"official","path":"brave/datasets/media_sequences.py","file_url":"https://github.com/deepmind/brave/blob/HEAD/brave/datasets/media_sequences.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"315e821fb79e66f7"}},{"code_sha256_prefix":"f7f43698d451909c","entry":"pcm_to_log_mel_spectrogram","repo":"deepmind/brave","repo_kind":"official","path":"brave/datasets/spectrograms.py","file_url":"https://github.com/deepmind/brave/blob/HEAD/brave/datasets/spectrograms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7f43698d451909c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}