Papers › A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer

A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer

17 May 2020arXiv:2005.08271archive 2025-07-28

Vladimir Iashin, Esa Rahtu

Dense video captioning aims to localize and describe important events in untrimmed videos. Existing methods mainly tackle this task by exploiting only visual features, while completely neglecting the audio track. Only a few prior works have utilized both modalities, yet they show poor results or demonstrate the importance on a dataset with a specific domain. In this paper, we introduce Bi-modal Transformer which generalizes the Transformer architecture for a bi-modal input. We show the effectiveness of the proposed model with audio and visual modalities on the dense video captioning task, yet the module is capable of digesting any two modalities in a sequence-to-sequence task. We also show that the pre-trained bi-modal encoder as a part of the bi-modal transformer can be used as a feature extractor for a simple proposal generation module. The performance is demonstrated on a challenging ActivityNet Captions dataset where our model achieves outstanding performance. The code is available: v-iashin.github.io/bmt

PaperPDFCodeCode 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="2005.08271")

Code

Syntology Ran 0 of 7 code samples harvested from 1 repository linked to this paper; 7 have no recorded run.

By repository: official repository: 7 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

v-iashin/BMT officialmentioned on GitHubpytorchMIT report
v-iashin/video_features mentioned 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

7 samples harvested; 0 ran; 0 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.

7unverified

Licence: 0 of the 7 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 v-iashin/BMT. “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.

attention v-iashin/BMT/model/multihead_attention.py official repository unverified MIT (permissive) · c695e53ea4b93d41 · report
clone v-iashin/BMT/model/blocks.py official repository unverified MIT (permissive) · ef3fdeeb802b1518 · report
crop_a_segment v-iashin/BMT/datasets/load_features.py official repository unverified MIT (permissive) · 451d121f2b589006 · report
fill_missing_features v-iashin/BMT/datasets/load_features.py official repository unverified MIT (permissive) · ab36dd74263d9df3 · report
mask v-iashin/BMT/model/masking.py official repository unverified MIT (permissive) · 05c96f6971669d61 · report
pad_segment v-iashin/BMT/datasets/load_features.py official repository unverified MIT (permissive) · 609f389f389b3641 · report
subsequent_mask v-iashin/BMT/model/masking.py official repository unverified MIT (permissive) · 34de23e6c8ad136c · report

Tasks

Dense Video CaptioningTemporal Action Proposal GenerationVideo Captioning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dense Video Captioning ActivityNet Captions BMT BLEU-3 3.84 #9 of 12 Archive leaderboard report
Dense Video Captioning ActivityNet Captions BMT BLEU-4 1.88 #9 of 12 Archive leaderboard report
Dense Video Captioning ActivityNet Captions BMT METEOR 8.44 #9 of 12 Archive leaderboard report
Temporal Action Proposal Generation ActivityNet Captions BMT Average F1 60.27 #1 of 1 Archive leaderboard report
Temporal Action Proposal Generation ActivityNet Captions BMT Average Precision 48.23 #1 of 1 Archive leaderboard report
Temporal Action Proposal Generation ActivityNet Captions BMT Average Recall 80.31 #1 of 1 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.

Methods

Absolute Position EncodingsAdamAttentionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformer

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