{"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/uniav-unified-audio-visual-perception-for","title":"UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization","arxiv_id":"2404.03179","date":"2024-04-04","proceeding":null,"authors":["Tiantian Geng","Teng Wang","yanfu Zhang","Jinming Duan","Weili Guan","Feng Zheng","Ling Shao"],"abstract":"Video localization tasks aim to temporally locate specific instances in videos, including temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods over-specialize on each task, overlooking the fact that these instances often occur in the same video to form the complete video content. In this work, we present UniAV, a Unified Audio-Visual perception network, to achieve joint learning of TAL, SED and AVEL tasks for the first time. UniAV can leverage diverse data available in task-specific datasets, allowing the model to learn and share mutually beneficial knowledge across tasks and modalities. To tackle the challenges posed by substantial variations in datasets (size/domain/duration) and distinct task characteristics, we propose to uniformly encode visual and audio modalities of all videos to derive generic representations, while also designing task-specific experts to capture unique knowledge for each task. Besides, we develop a unified language-aware classifier by utilizing a pre-trained text encoder, enabling the model to flexibly detect various types of instances and previously unseen ones by simply changing prompts during inference. UniAV outperforms its single-task counterparts by a large margin with fewer parameters, achieving on-par or superior performances compared to state-of-the-art task-specific methods across ActivityNet 1.3, DESED and UnAV-100 benchmarks.","url_abs":"https://arxiv.org/abs/2404.03179v2","url_pdf":"https://arxiv.org/pdf/2404.03179v2.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":"uniav-unified-audio-visual-perception-for","repo_url":"https://github.com/ttgeng233/UniAV","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"sound-event-detection","task_name":"Sound Event Detection"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"audio-visual-event-localization","task_name":"audio-visual event localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.03179","atlas_url":"https://app.syntology.ai/?focus=2404.03179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03179"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ttgeng233/UniAV","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":7,"ran_fixture":1,"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":15,"ran":10,"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":"10865bbb99140edd","entry":"Linear","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/modeling/blocks.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/blocks.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":"10865bbb99140edd"}},{"code_sha256_prefix":"be1ca95e264f135e","entry":"ctr_diou_loss_1d","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/modeling/losses.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/losses.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":"be1ca95e264f135e"}},{"code_sha256_prefix":"a34c005ba2203f35","entry":"drop_path","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/modeling/blocks.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/blocks.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"code_sha256_prefix":"3531df7b0c9b0791","entry":"get_sinusoid_encoding","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/modeling/blocks.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/blocks.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3531df7b0c9b0791"}},{"code_sha256_prefix":"91a965d8ba54bf18","entry":"label_points","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/datasets/data_utils.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/datasets/data_utils.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":"91a965d8ba54bf18"}},{"code_sha256_prefix":"723915877968278d","entry":"load_config","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/core/config.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/core/config.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":"723915877968278d"}},{"code_sha256_prefix":"e85f9ec07f7d587b","entry":"register_multimodal_backbone","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/modeling/models.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/models.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":"e85f9ec07f7d587b"}},{"code_sha256_prefix":"0fc8e74a8c092f28","entry":"register_multimodal_meta_arch","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/modeling/models.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/models.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":"0fc8e74a8c092f28"}},{"code_sha256_prefix":"54293ea22bd4f952","entry":"sigmoid_focal_loss","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/modeling/losses.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/losses.py","link_basis":"harvester_set","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":"54293ea22bd4f952"}},{"code_sha256_prefix":"65864282f76b5575","entry":"truncate_feats","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/datasets/data_utils.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/datasets/data_utils.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":"65864282f76b5575"}},{"code_sha256_prefix":"ffebfbb8094c0dcc","entry":"make_dataset","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/datasets/datasets.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/datasets/datasets.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":"ffebfbb8094c0dcc"}},{"code_sha256_prefix":"80bc46d5a1acbb10","entry":"make_multimodal_backbone","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/modeling/models.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/models.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":"80bc46d5a1acbb10"}},{"code_sha256_prefix":"2ee0df0825339a6e","entry":"register_dataset","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/datasets/datasets.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/datasets/datasets.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":"2ee0df0825339a6e"}},{"code_sha256_prefix":"3db1c5ab5f3f0198","entry":"register_generator","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/datasets/datasets.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/datasets/datasets.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":"3db1c5ab5f3f0198"}},{"code_sha256_prefix":"0c250bf03b8c9311","entry":"trivial_batch_collator","repo":"ttgeng233/UniAV","repo_kind":"official","path":"libs/datasets/data_utils.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/datasets/data_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":"0c250bf03b8c9311"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}