Papers › Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline

Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline

22 Mar 2023CVPR 2023 1arXiv:2303.12930archive 2025-07-28

Tiantian Geng, Teng Wang, Jinming Duan, Runmin Cong, Feng Zheng

Existing audio-visual event localization (AVE) handles manually trimmed videos with only a single instance in each of them. However, this setting is unrealistic as natural videos often contain numerous audio-visual events with different categories. To better adapt to real-life applications, in this paper we focus on the task of dense-localizing audio-visual events, which aims to jointly localize and recognize all audio-visual events occurring in an untrimmed video. The problem is challenging as it requires fine-grained audio-visual scene and context understanding. To tackle this problem, we introduce the first Untrimmed Audio-Visual (UnAV-100) dataset, which contains 10K untrimmed videos with over 30K audio-visual events. Each video has 2.8 audio-visual events on average, and the events are usually related to each other and might co-occur as in real-life scenes. Next, we formulate the task using a new learning-based framework, which is capable of fully integrating audio and visual modalities to localize audio-visual events with various lengths and capture dependencies between them in a single pass. Extensive experiments demonstrate the effectiveness of our method as well as the significance of multi-scale cross-modal perception and dependency modeling for this task.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2303.12930")

Code

Syntology Ran 6 of 13 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ttgeng233/UnAV officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 6 ran; 1 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · fixture could not drive it
4ran
7unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ttgeng233/UnAV. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

ctr_diou_loss_1d ttgeng233/UnAV/libs/modeling/losses.py official repository ran MIT (permissive) · be1ca95e264f135e · report
drop_path ttgeng233/UnAV/libs/modeling/blocks.py official repository ran · fixture could not drive it MIT (permissive) · a34c005ba2203f35 · report
get_sinusoid_encoding ttgeng233/UnAV/libs/modeling/blocks.py official repository ran · honoured contract fingerprinted MIT (permissive) · 3531df7b0c9b0791 · report
register_multimodal_backbone ttgeng233/UnAV/libs/modeling/models.py official repository ran MIT (permissive) · e85f9ec07f7d587b · report
register_multimodal_meta_arch ttgeng233/UnAV/libs/modeling/models.py official repository ran MIT (permissive) · 0fc8e74a8c092f28 · report
sigmoid_focal_loss ttgeng233/UnAV/libs/modeling/losses.py official repository ran MIT (permissive) · 54293ea22bd4f952 · report
load_config ttgeng233/UnAV/libs/core/config.py official repository unverified MIT (permissive) · 157c518e791fca20 · report
make_dataset ttgeng233/UnAV/libs/datasets/datasets.py official repository unverified MIT (permissive) · ffebfbb8094c0dcc · report
register_dataset ttgeng233/UnAV/libs/datasets/datasets.py official repository unverified MIT (permissive) · 2ee0df0825339a6e · report
register_dependency_block ttgeng233/UnAV/libs/modeling/models.py official repository unverified MIT (permissive) · d8a13c98d784c121 · report
register_generator ttgeng233/UnAV/libs/datasets/datasets.py official repository unverified MIT (permissive) · 3db1c5ab5f3f0198 · report
trivial_batch_collator ttgeng233/UnAV/libs/datasets/data_utils.py official repository unverified MIT (permissive) · 0c250bf03b8c9311 · report
truncate_feats ttgeng233/UnAV/libs/datasets/data_utils.py official repository unverified MIT (permissive) · 0187c7d2e60afe31 · report

Tasks

audio-visual event localization

Datasets

Introduced by this paper, per the archive.

UnAV-100

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
audio-visual event localization UnAV-100 UnAV mAP 47.8 #1 of 2 Archive leaderboard report
audio-visual event localization UnAV-100 UnAV AP@IOU0.5 50.6 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections