{"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/distilling-audio-visual-knowledge-by","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","arxiv_id":"2104.10955","date":"2021-04-22","proceeding":"CVPR 2021 1","authors":["Yanbei Chen","Yongqin Xian","A. Sophia Koepke","Ying Shan","Zeynep Akata"],"abstract":"Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even though these data modalities may not be semantically correlated. Rather than directly aligning the representations of different modalities, we compose audio, image, and video representations across modalities to uncover richer multi-modal knowledge. Our main idea is to learn a compositional embedding that closes the cross-modal semantic gap and captures the task-relevant semantics, which facilitates pulling together representations across modalities by compositional contrastive learning. We establish a new, comprehensive multi-modal distillation benchmark on three video datasets: UCF101, ActivityNet, and VGGSound. Moreover, we demonstrate that our model significantly outperforms a variety of existing knowledge distillation methods in transferring audio-visual knowledge to improve video representation learning. Code is released here: https://github.com/yanbeic/CCL.","url_abs":"https://arxiv.org/abs/2104.10955v1","url_pdf":"https://arxiv.org/pdf/2104.10955v1.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":"distilling-audio-visual-knowledge-by","repo_url":"https://github.com/yanbeic/CCL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-tagging","task_name":"Audio Tagging"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"multimodal-activity-recognition","task_name":"Multimodal Activity Recognition"},{"task_slug":"multimodal-deep-learning","task_name":"Multimodal Deep Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"audio-visual-learning","task_name":"audio-visual learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"supervised-contrastive-loss","method_name":"Supervised Contrastive Loss"},{"method_slug":"teacher-tutor-student-knowledge-distillation","method_name":"Teacher-Tutor-Student Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.10955","atlas_url":"https://app.syntology.ai/?focus=2104.10955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10955"}},"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":"deterministic:regex_extraction","url":"https://github.com/yanbeic/CCL","reach":null}],"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":"07044a0cefe5c531","entry":"NCELoss","repo":"yanbeic/CCL","repo_kind":"official","path":"loss/nce_loss.py","file_url":"https://github.com/yanbeic/CCL/blob/HEAD/loss/nce_loss.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":"07044a0cefe5c531"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}