{"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/tavis-text-bridged-audio-visual-segmentation","title":"TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models","arxiv_id":"2506.11436","date":"2025-06-13","proceeding":null,"authors":["Ziyang Luo","Nian Liu","Xuguang Yang","Salman Khan","Rao Muhammad Anwer","Hisham Cholakkal","Fahad Shahbaz Khan","Junwei Han"],"abstract":"Audio-Visual Segmentation (AVS) faces a fundamental challenge of effectively aligning audio and visual modalities. While recent approaches leverage foundation models to address data scarcity, they often rely on single-modality knowledge or combine foundation models in an off-the-shelf manner, failing to address the cross-modal alignment challenge. In this paper, we present TAViS, a novel framework that \\textbf{couples} the knowledge of multimodal foundation models (ImageBind) for cross-modal alignment and a segmentation foundation model (SAM2) for precise segmentation. However, effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision. To address these challenges, we introduce a text-bridged design with two key components: (1) a text-bridged hybrid prompting mechanism where pseudo text provides class prototype information while retaining modality-specific details from both audio and visual inputs, and (2) an alignment supervision strategy that leverages text as a bridge to align shared semantic concepts within audio-visual modalities. Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.","url_abs":"https://arxiv.org/abs/2506.11436v1","url_pdf":"https://arxiv.org/pdf/2506.11436v1.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":[],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.11436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.11436"}},"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":"deterministic:regex_extraction","url":"https://github.com/Sssssuperior/TAViS","reach":null}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"found_in_text":{"samples":8,"ran":4,"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":"a4d9fce50aea89ac","entry":"MLP","repo":"Sssssuperior/TAViS","repo_kind":"found_in_text","path":"models/sam_avs.py","file_url":"https://github.com/Sssssuperior/TAViS/blob/HEAD/models/sam_avs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4d9fce50aea89ac"}},{"code_sha256_prefix":"eabd6c2f33339219","entry":"VGG","repo":"Sssssuperior/TAViS","repo_kind":"found_in_text","path":"models/sam_avs.py","file_url":"https://github.com/Sssssuperior/TAViS/blob/HEAD/models/sam_avs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eabd6c2f33339219"}},{"code_sha256_prefix":"1bb22134c20c522c","entry":"_iou_loss","repo":"Sssssuperior/TAViS","repo_kind":"found_in_text","path":"models/sam_avs.py","file_url":"https://github.com/Sssssuperior/TAViS/blob/HEAD/models/sam_avs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1bb22134c20c522c"}},{"code_sha256_prefix":"01db1d2b39bc49cc","entry":"make_layers","repo":"Sssssuperior/TAViS","repo_kind":"found_in_text","path":"models/sam_avs.py","file_url":"https://github.com/Sssssuperior/TAViS/blob/HEAD/models/sam_avs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01db1d2b39bc49cc"}},{"code_sha256_prefix":"001b516a7d122395","entry":"AVS_SAM2","repo":"Sssssuperior/TAViS","repo_kind":"found_in_text","path":"models/sam_avs.py","file_url":"https://github.com/Sssssuperior/TAViS/blob/HEAD/models/sam_avs.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":"001b516a7d122395"}},{"code_sha256_prefix":"a4ea19d7d4dbb57a","entry":"Postprocessor","repo":"Sssssuperior/TAViS","repo_kind":"found_in_text","path":"models/sam_avs.py","file_url":"https://github.com/Sssssuperior/TAViS/blob/HEAD/models/sam_avs.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":"a4ea19d7d4dbb57a"}},{"code_sha256_prefix":"904b66c61dd9cc1f","entry":"VGGish","repo":"Sssssuperior/TAViS","repo_kind":"found_in_text","path":"models/sam_avs.py","file_url":"https://github.com/Sssssuperior/TAViS/blob/HEAD/models/sam_avs.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":"904b66c61dd9cc1f"}},{"code_sha256_prefix":"f567946ade226705","entry":"audio_extractor","repo":"Sssssuperior/TAViS","repo_kind":"found_in_text","path":"models/sam_avs.py","file_url":"https://github.com/Sssssuperior/TAViS/blob/HEAD/models/sam_avs.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":"f567946ade226705"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}