{"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/self-supervised-learning-by-cross-modal-audio","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","arxiv_id":"1911.12667","date":"2019-11-28","proceeding":"NeurIPS 2020 12","authors":["Humam Alwassel","Dhruv Mahajan","Bruno Korbar","Lorenzo Torresani","Bernard Ghanem","Du Tran"],"abstract":"Visual and audio modalities are highly correlated, yet they contain different information. Their strong correlation makes it possible to predict the semantics of one from the other with good accuracy. Their intrinsic differences make cross-modal prediction a potentially more rewarding pretext task for self-supervised learning of video and audio representations compared to within-modality learning. Based on this intuition, we propose Cross-Modal Deep Clustering (XDC), a novel self-supervised method that leverages unsupervised clustering in one modality (e.g., audio) as a supervisory signal for the other modality (e.g., video). This cross-modal supervision helps XDC utilize the semantic correlation and the differences between the two modalities. Our experiments show that XDC outperforms single-modality clustering and other multi-modal variants. XDC achieves state-of-the-art accuracy among self-supervised methods on multiple video and audio benchmarks. Most importantly, our video model pretrained on large-scale unlabeled data significantly outperforms the same model pretrained with full-supervision on ImageNet and Kinetics for action recognition on HMDB51 and UCF101. To the best of our knowledge, XDC is the first self-supervised learning method that outperforms large-scale fully-supervised pretraining for action recognition on the same architecture.","url_abs":"https://arxiv.org/abs/1911.12667v3","url_pdf":"https://arxiv.org/pdf/1911.12667v3.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":"self-supervised-learning-by-cross-modal-audio","repo_url":"https://github.com/HumamAlwassel/XDC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"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/audio-classification-on-dcase","task":"Audio Classification","dataset":"DCASE","model":"XDC","rank_in_archive_order":3,"of":5,"metrics":{"PRE-TRAINING DATASET":"IG-Random","Top-1 Accuracy":"95"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-dcase","task":"Audio Classification","dataset":"DCASE","model":"XDC","rank_in_archive_order":4,"of":5,"metrics":{"PRE-TRAINING DATASET":"AudioSet","Top-1 Accuracy":"95"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-esc-50","task":"Audio Classification","dataset":"ESC-50","model":"XDC","rank_in_archive_order":26,"of":29,"metrics":{"PRE-TRAINING DATASET":"IG-Random","Top-1 Accuracy":"85.4"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-esc-50","task":"Audio Classification","dataset":"ESC-50","model":"XDC","rank_in_archive_order":27,"of":29,"metrics":{"PRE-TRAINING DATASET":"AudioSet","Top-1 Accuracy":"84.8"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"XDC","rank_in_archive_order":9,"of":48,"metrics":{"Frozen":"false","Pre-Training Dataset":"IG-Kinetics","Top-1 Accuracy":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"XDC","rank_in_archive_order":13,"of":48,"metrics":{"Frozen":"false","Pre-Training Dataset":"IG-Random","Top-1 Accuracy":"66.5"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"XDC","rank_in_archive_order":21,"of":48,"metrics":{"Frozen":"false","Pre-Training Dataset":"AudioSet","Top-1 Accuracy":"63.7"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"XDC","rank_in_archive_order":32,"of":48,"metrics":{"Frozen":"false","Pre-Training Dataset":"Kinetics400","Top-1 Accuracy":"52.6"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51-1","task":"Self-Supervised Action Recognition","dataset":"HMDB51 (finetuned)","model":"XDC","rank_in_archive_order":4,"of":14,"metrics":{"Top-1 Accuracy":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101-1","task":"Self-Supervised Action Recognition","dataset":"UCF101 (finetuned)","model":"XDC","rank_in_archive_order":2,"of":14,"metrics":{"3-fold Accuracy":"95.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.12667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12667"}},"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/HumamAlwassel/XDC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":0,"samples":[{"code_sha256_prefix":"1790d320db15d598","entry":"r2plus1d_18","repo":"HumamAlwassel/XDC","repo_kind":"official","path":"model/r2plus1d_18.py","file_url":"https://github.com/HumamAlwassel/XDC/blob/HEAD/model/r2plus1d_18.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1790d320db15d598"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}