{"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/localizing-visual-sounds-the-hard-way","title":"Localizing Visual Sounds the Hard Way","arxiv_id":"2104.02691","date":"2021-04-06","proceeding":"CVPR 2021 1","authors":["Honglie Chen","Weidi Xie","Triantafyllos Afouras","Arsha Nagrani","Andrea Vedaldi","Andrew Zisserman"],"abstract":"The objective of this work is to localize sound sources that are visible in a video without using manual annotations. Our key technical contribution is to show that, by training the network to explicitly discriminate challenging image fragments, even for images that do contain the object emitting the sound, we can significantly boost the localization performance. We do so elegantly by introducing a mechanism to mine hard samples and add them to a contrastive learning formulation automatically. We show that our algorithm achieves state-of-the-art performance on the popular Flickr SoundNet dataset. Furthermore, we introduce the VGG-Sound Source (VGG-SS) benchmark, a new set of annotations for the recently-introduced VGG-Sound dataset, where the sound sources visible in each video clip are explicitly marked with bounding box annotations. This dataset is 20 times larger than analogous existing ones, contains 5K videos spanning over 200 categories, and, differently from Flickr SoundNet, is video-based. On VGG-SS, we also show that our algorithm achieves state-of-the-art performance against several baselines.","url_abs":"https://arxiv.org/abs/2104.02691v1","url_pdf":"https://arxiv.org/pdf/2104.02691v1.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":"localizing-visual-sounds-the-hard-way","repo_url":"https://github.com/hche11/localizing-visual-sounds-the-hard-way","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[{"slug":"vgg-ss","name":"VGG-SS","full_name":"VGG-Sound Source"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.02691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02691"}},"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/hche11/localizing-visual-sounds-the-hard-way","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"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":"97f7a0beef17542b","entry":"AVENet","repo":"hche11/localizing-visual-sounds-the-hard-way","repo_kind":"listed","path":"model.py","file_url":"https://github.com/hche11/localizing-visual-sounds-the-hard-way/blob/HEAD/model.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":"97f7a0beef17542b"}},{"code_sha256_prefix":"653beda9f9b5bd69","entry":"ResNet","repo":"hche11/localizing-visual-sounds-the-hard-way","repo_kind":"listed","path":"model.py","file_url":"https://github.com/hche11/localizing-visual-sounds-the-hard-way/blob/HEAD/model.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":"653beda9f9b5bd69"}},{"code_sha256_prefix":"69844ddf700f4735","entry":"_resnet","repo":"hche11/localizing-visual-sounds-the-hard-way","repo_kind":"listed","path":"model.py","file_url":"https://github.com/hche11/localizing-visual-sounds-the-hard-way/blob/HEAD/model.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":"69844ddf700f4735"}},{"code_sha256_prefix":"ee93ca42aee52b14","entry":"resnet18","repo":"hche11/localizing-visual-sounds-the-hard-way","repo_kind":"listed","path":"model.py","file_url":"https://github.com/hche11/localizing-visual-sounds-the-hard-way/blob/HEAD/model.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":"ee93ca42aee52b14"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}