{"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/catr-combinatorial-dependence-audio-queried","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","arxiv_id":"2309.09709","date":"2023-09-18","proceeding":null,"authors":["Kexin Li","Zongxin Yang","Lei Chen","Yi Yang","Jun Xiao"],"abstract":"Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, such as identifying and segmenting a singing person in a video. However, existing methods exhibit two limitations: 1) they address video temporal features and audio-visual interactive features separately, disregarding the inherent spatial-temporal dependence of combined audio and video, and 2) they inadequately introduce audio constraints and object-level information during the decoding stage, resulting in segmentation outcomes that fail to comply with audio directives. To tackle these issues, we propose a decoupled audio-video transformer that combines audio and video features from their respective temporal and spatial dimensions, capturing their combined dependence. To optimize memory consumption, we design a block, which, when stacked, enables capturing audio-visual fine-grained combinatorial-dependence in a memory-efficient manner. Additionally, we introduce audio-constrained queries during the decoding phase. These queries contain rich object-level information, ensuring the decoded mask adheres to the sounds. Experimental results confirm our approach's effectiveness, with our framework achieving a new SOTA performance on all three datasets using two backbones. The code is available at \\url{https://github.com/aspirinone/CATR.github.io}","url_abs":"https://arxiv.org/abs/2309.09709v2","url_pdf":"https://arxiv.org/pdf/2309.09709v2.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":"catr-combinatorial-dependence-audio-queried","repo_url":"https://github.com/aspirinone/catr.github.io","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.09709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09709"}},"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/aspirinone/catr.github.io","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":"f093c01ac1ab72ed","entry":"F1_IoU_BCELoss","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/loss.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/loss.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":"f093c01ac1ab72ed"}},{"code_sha256_prefix":"a1f167f317a36162","entry":"IouSemanticAwareLoss","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/loss.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/loss.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":"a1f167f317a36162"}},{"code_sha256_prefix":"aa6da43d05cfaf65","entry":"all_gather","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/misc.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/misc.py","link_basis":"harvester_set","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":"aa6da43d05cfaf65"}},{"code_sha256_prefix":"050cda61d2798c04","entry":"dice_coef","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/matcher.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/matcher.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":"050cda61d2798c04"}},{"code_sha256_prefix":"2e405eca70ac9fb0","entry":"load_audio_lm","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/dataloader.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/dataloader.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":"2e405eca70ac9fb0"}},{"code_sha256_prefix":"fe732dcb1c93487d","entry":"load_image_in_PIL_to_Tensor","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/dataloader.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/dataloader.py","link_basis":"harvester_set","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":"fe732dcb1c93487d"}},{"code_sha256_prefix":"afb6efd87349dd80","entry":"nested_tensor_from_tensor_list","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/misc.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/misc.py","link_basis":"harvester_set","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":"afb6efd87349dd80"}},{"code_sha256_prefix":"05992505df9ef0cd","entry":"reduce_dict","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/misc.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/misc.py","link_basis":"harvester_set","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":"05992505df9ef0cd"}},{"code_sha256_prefix":"838086f242b600de","entry":"A_MaskedV_SimmLoss","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/loss.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"838086f242b600de"}},{"code_sha256_prefix":"89c58051dd53ba2c","entry":"compute_is_referred_cost","repo":"aspirinone/catr.github.io","repo_kind":"official","path":"CATR/matcher.py","file_url":"https://github.com/aspirinone/catr.github.io/blob/HEAD/CATR/matcher.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"89c58051dd53ba2c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}