{"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/can-clip-help-sound-source-localization","title":"Can CLIP Help Sound Source Localization?","arxiv_id":"2311.04066","date":"2023-11-07","proceeding":null,"authors":["Sooyoung Park","Arda Senocak","Joon Son Chung"],"abstract":"Large-scale pre-trained image-text models demonstrate remarkable versatility across diverse tasks, benefiting from their robust representational capabilities and effective multimodal alignment. We extend the application of these models, specifically CLIP, to the domain of sound source localization. Unlike conventional approaches, we employ the pre-trained CLIP model without explicit text input, relying solely on the audio-visual correspondence. To this end, we introduce a framework that translates audio signals into tokens compatible with CLIP's text encoder, yielding audio-driven embeddings. By directly using these embeddings, our method generates audio-grounded masks for the provided audio, extracts audio-grounded image features from the highlighted regions, and aligns them with the audio-driven embeddings using the audio-visual correspondence objective. Our findings suggest that utilizing pre-trained image-text models enable our model to generate more complete and compact localization maps for the sounding objects. Extensive experiments show that our method outperforms state-of-the-art approaches by a significant margin.","url_abs":"https://arxiv.org/abs/2311.04066v1","url_pdf":"https://arxiv.org/pdf/2311.04066v1.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":"can-clip-help-sound-source-localization","repo_url":"https://github.com/swimmiing/ACL-SSL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"sound-source-localization","task_name":"Sound Source Localization"},{"task_slug":"audio-visual-learning","task_name":"audio-visual learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.04066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04066"}},"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/swimmiing/ACL-SSL","reach":{"status":"ok"}}],"summary":{"ran":10},"by_repo_kind":{"official":{"samples":10,"ran":10,"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":10,"samples":[{"code_sha256_prefix":"b67c45c7d726ea8c","entry":"acl_i","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"loss_utils.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b67c45c7d726ea8c"}},{"code_sha256_prefix":"92bfac1ad774d076","entry":"area_reg","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"loss_utils.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"92bfac1ad774d076"}},{"code_sha256_prefix":"582088159ea8ce3c","entry":"bbox2gtmap","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"Flickr/Flickr_Dataset.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/Flickr/Flickr_Dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"582088159ea8ce3c"}},{"code_sha256_prefix":"151e59de90357e27","entry":"get_prompt_template","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"util.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"151e59de90357e27"}},{"code_sha256_prefix":"832166e6327d35fe","entry":"gumbel_sigmoid","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"modules/mask_utils.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/modules/mask_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"832166e6327d35fe"}},{"code_sha256_prefix":"df0e4565a582b04e","entry":"infonce","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"loss_utils.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df0e4565a582b04e"}},{"code_sha256_prefix":"3a74d833820ffe44","entry":"int_or_float","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"modules/arg_utils.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/modules/arg_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a74d833820ffe44"}},{"code_sha256_prefix":"c08be5b16052a3a3","entry":"int_or_int_list_or_none","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"modules/arg_utils.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/modules/arg_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c08be5b16052a3a3"}},{"code_sha256_prefix":"ae4779a24899a845","entry":"load_all_bboxes","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"Flickr/Flickr_Dataset.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/Flickr/Flickr_Dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae4779a24899a845"}},{"code_sha256_prefix":"eff7f84db1c99668","entry":"norm_img_tensor","repo":"swimmiing/ACL-SSL","repo_kind":"official","path":"modules/mask_utils.py","file_url":"https://github.com/swimmiing/ACL-SSL/blob/HEAD/modules/mask_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eff7f84db1c99668"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}