{"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/mff-einv2-multi-scale-feature-fusion-across","title":"MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection","arxiv_id":"2406.08771","date":"2024-06-13","proceeding":null,"authors":["Da Mu","Zhicheng Zhang","Haobo Yue"],"abstract":"Sound Event Localization and Detection (SELD) involves detecting and localizing sound events using multichannel sound recordings. Previously proposed Event-Independent Network V2 (EINV2) has achieved outstanding performance on SELD. However, it still faces challenges in effectively extracting features across spectral, spatial, and temporal domains. This paper proposes a three-stage network structure named Multi-scale Feature Fusion (MFF) module to fully extract multi-scale features across spectral, spatial, and temporal domains. The MFF module utilizes parallel subnetworks architecture to generate multi-scale spectral and spatial features. The TF-Convolution Module is employed to provide multi-scale temporal features. We incorporated MFF into EINV2 and term the proposed method as MFF-EINV2. Experimental results in 2022 and 2023 DCASE challenge task3 datasets show the effectiveness of our MFF-EINV2, which achieves state-of-the-art (SOTA) performance compared to published methods.","url_abs":"https://arxiv.org/abs/2406.08771v2","url_pdf":"https://arxiv.org/pdf/2406.08771v2.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":"mff-einv2-multi-scale-feature-fusion-across","repo_url":"https://github.com/muuda/MFF-EINV2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sound-event-localization-and-detection","task_name":"Sound Event Localization and Detection"}],"methods":[{"method_slug":"mff","method_name":"MFF"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.08771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08771"}},"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/muuda/MFF-EINV2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"d61918091ec1d259","entry":"collate_fn","repo":"muuda/MFF-EINV2","repo_kind":"official","path":"code/methods/data.py","file_url":"https://github.com/muuda/MFF-EINV2/blob/HEAD/code/methods/data.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":"d61918091ec1d259"}},{"code_sha256_prefix":"e4ec083d3e00b43f","entry":"nCr","repo":"muuda/MFF-EINV2","repo_kind":"official","path":"code/methods/feature.py","file_url":"https://github.com/muuda/MFF-EINV2/blob/HEAD/code/methods/feature.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":"e4ec083d3e00b43f"}},{"code_sha256_prefix":"57e1cbd986847dd6","entry":"reshape_3Dto2D","repo":"muuda/MFF-EINV2","repo_kind":"official","path":"code/compute_seld_metrics.py","file_url":"https://github.com/muuda/MFF-EINV2/blob/HEAD/code/compute_seld_metrics.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57e1cbd986847dd6"}},{"code_sha256_prefix":"9087ae0da774d108","entry":"jackknife_estimation","repo":"muuda/MFF-EINV2","repo_kind":"official","path":"code/compute_seld_metrics.py","file_url":"https://github.com/muuda/MFF-EINV2/blob/HEAD/code/compute_seld_metrics.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":"9087ae0da774d108"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}