{"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/synchformer-efficient-synchronization-from","title":"Synchformer: Efficient Synchronization from Sparse Cues","arxiv_id":"2401.16423","date":"2024-01-29","proceeding":null,"authors":["Vladimir Iashin","Weidi Xie","Esa Rahtu","Andrew Zisserman"],"abstract":"Our objective is audio-visual synchronization with a focus on 'in-the-wild' videos, such as those on YouTube, where synchronization cues can be sparse. Our contributions include a novel audio-visual synchronization model, and training that decouples feature extraction from synchronization modelling through multi-modal segment-level contrastive pre-training. This approach achieves state-of-the-art performance in both dense and sparse settings. We also extend synchronization model training to AudioSet a million-scale 'in-the-wild' dataset, investigate evidence attribution techniques for interpretability, and explore a new capability for synchronization models: audio-visual synchronizability.","url_abs":"https://arxiv.org/abs/2401.16423v1","url_pdf":"https://arxiv.org/pdf/2401.16423v1.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":"synchformer-efficient-synchronization-from","repo_url":"https://github.com/v-iashin/synchformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"synchformer-efficient-synchronization-from","repo_url":"https://github.com/v-iashin/sparsesync","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-visual-synchronization","task_name":"Audio-Visual Synchronization"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.16423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16423"}},"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/v-iashin/sparsesync","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/v-iashin/synchformer","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":9},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":10,"ran":2,"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":"4e291c3ece372165","entry":"find_modules","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"model/modules/attn_recorder.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/model/modules/attn_recorder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e291c3ece372165"}},{"code_sha256_prefix":"221b2d116fdf1032","entry":"get_obj_from_str","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"221b2d116fdf1032"}},{"code_sha256_prefix":"dc2b0101b1568393","entry":"fix_prefix","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/utils/utils.py","link_basis":"harvester_set","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":"dc2b0101b1568393"}},{"code_sha256_prefix":"aa337657261e65dc","entry":"frames2sec","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"dataset/transforms.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/dataset/transforms.py","link_basis":"harvester_set","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":"aa337657261e65dc"}},{"code_sha256_prefix":"cce60c0658ef0856","entry":"get_resnet_layers","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"model/modules/feature_extractors.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/model/modules/feature_extractors.py","link_basis":"harvester_set","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":"cce60c0658ef0856"}},{"code_sha256_prefix":"eb8c91c2028ef79f","entry":"get_video_and_audio","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"dataset/dataset_utils.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/dataset/dataset_utils.py","link_basis":"harvester_set","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":"eb8c91c2028ef79f"}},{"code_sha256_prefix":"692c94009ed723bc","entry":"instantiate_from_config","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/utils/utils.py","link_basis":"harvester_set","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":"692c94009ed723bc"}},{"code_sha256_prefix":"b9f5bd895cf659b6","entry":"make_class_grid","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"dataset/transforms.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/dataset/transforms.py","link_basis":"harvester_set","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":"b9f5bd895cf659b6"}},{"code_sha256_prefix":"0987f89b2ed17dff","entry":"maybe_cache_file","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"dataset/dataset_utils.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/dataset/dataset_utils.py","link_basis":"harvester_set","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":"0987f89b2ed17dff"}},{"code_sha256_prefix":"5502057de77f4f87","entry":"patch_config","repo":"v-iashin/synchformer","repo_kind":"official","path":"example.py","file_url":"https://github.com/v-iashin/synchformer/blob/HEAD/example.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":"5502057de77f4f87"}},{"code_sha256_prefix":"97c346a30ab99199","entry":"sec2frames","repo":"v-iashin/sparsesync","repo_kind":"listed","path":"dataset/transforms.py","file_url":"https://github.com/v-iashin/sparsesync/blob/HEAD/dataset/transforms.py","link_basis":"harvester_set","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":"97c346a30ab99199"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}