Browse State-of-the-Art › Dense Video Captioning
Dense Video Captioning
39 papers with code · 4 benchmarks · 9 datasets archive 2025-07-28
Most natural videos contain numerous events. For example, in a video of a “man playing a piano”, the video might also contain “another man dancing” or “a crowd clapping”. The task of dense video captioning involves both detecting and describing events in a video.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): YouCook2 (2 judged, 0 placed), ViTT (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| ActivityNet Captions (12 rows) | Vid2Seq | Vid2Seq: Large-Scale Pretraining of a Visual Language Model for... | code | — | Compare |
| YouCook2 (7 rows) | HiCM² | HiCM²: Hierarchical Compact Memory Modeling for Dense Video Captioning | code | — | Compare |
| ViTT (4 rows) | Vid2Seq (VidChapters-7M PT) | — | — | — | Compare |
| VidChapters-7M (1 row) | Vid2Seq | — | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
9 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 76 · with a code link: 39 · where Syntology ran a sample: 16 (13 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (16 of 76 tagged: 13 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 76 of 76, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
17 Mar 2020 4 repositories listedWe apply automatic speech recognition (ASR) system to obtain a temporally aligned textual description of the speech (similar to subtitles) and treat it as a separate input alongside video frames and the corresponding…
-
27 Feb 2023 3 repositories listedIn this work, we introduce Vid2Seq, a multi-modal single-stage dense event captioning model pretrained on narrated videos which are readily-available at scale.
-
12 Sep 2023 2 repositories listedMore information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org.
-
10 Apr 2023 2 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)By providing broadcasters with a tool to summarize the content of their video with the same level of engagement as a live game, our method could help satisfy the needs of the numerous fans who follow their team but…
-
17 Aug 2021 2 repositories listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples)Dense video captioning aims to generate multiple associated captions with their temporal locations from the video.
-
17 May 2020 2 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)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.
-
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning12 Jan 2025 1 repository listedDespite the advancements of Video Large Language Models (VideoLLMs) in various tasks, they struggle with fine-grained temporal understanding, such as Dense Video Captioning (DVC).
-
19 Dec 2024 1 repository listedWith the growing demand for solutions to real-world video challenges, interest in dense video captioning (DVC) has been on the rise.
-
17 Dec 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 12 harvested samples)Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference.
-
29 Nov 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples) · 1 pointer-only (licence)Despite impressive advancements in video understanding, most efforts remain limited to coarse-grained or visual-only video tasks.
-
27 Nov 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)We construct MMDuetIT, a video-text training dataset designed to adapt VideoLLMs to video-text duet interaction format.
-
4 Oct 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding.
-
16 Sep 2024 1 repository listedThe SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team.
-
5 Aug 2024 1 repository listedWith this setup, we collected a diverse dataset by distributing smartphones to participants.
-
20 Jun 2024 1 repository listedIn this work we formally introduce the novel problem of LVC and propose new evaluation metrics tailored for the online scenario, demonstrating their superiority over traditional metrics.
-
13 Jun 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 8 pointer-only (licence)Building on the advances of language models, Large Multimodal Models (LMMs) have contributed significant improvements in video understanding.
-
22 May 2024 1 repository listed Syntology official (archive's flag): 15 ran · 15 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified (of 17 harvested samples)Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing.
-
14 Apr 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Traffic video description and analysis have received much attention recently due to the growing demand for efficient and reliable urban surveillance systems.
-
12 Apr 2024 1 repository listedOur solution mainly focuses on the following points: 1) To solve dense video captioning, we leverage the framework of dense video captioning with parallel decoding (PDVC) to model visual-language sequences and generate…
-
11 Apr 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video.
-
1 Apr 2024 1 repository listedAn ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs…
-
26 Mar 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples) · 11 pointer-only (licence)The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically detect objects or actions in a video and analyze their temporal evolution.
-
30 Nov 2023 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples) · 11 pointer-only (licence)Large language models (LLMs) have shown remarkable text understanding capabilities, which have been extended as Video LLMs to handle video data for comprehending visual details.
-
25 Sep 2023 1 repository listed Syntology 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples)To address this issue, we present VidChapters-7M, a dataset of 817K user-chaptered videos including 7M chapters in total.
-
3 May 2023 1 repository listedHumans can naturally reason from superficial state differences (e. g. ground wetness) to transformations descriptions (e. g. raining) according to their life experience.
-
11 Mar 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 1 pointer-only (licence)Our framework is easily extensible to tasks covering visually-grounded language understanding and generation.
-
5 Nov 2022 1 repository listedOur experiments show that it is possible to extract entities, their properties, relations between entities, and the video category from the generated captions.
-
18 Jul 2022 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified (of 13 harvested samples) · 13 pointer-only (licence)Dense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning.
-
15 Dec 2021 1 repository listedWe introduce a method to learn unsupervised semantic visual information based on the premise that complex events can be decomposed into simpler events and that these simple events are shared across several complex…
-
18 Jul 2021 1 repository listedRecently, many works are proposed on the generation of multi-sentence video descriptions.
-
23 Nov 2020 1 repository listed
-
10 Nov 2020 1 repository listed
-
1 Aug 2020 1 repository listed
-
21 Jun 2020 1 repository listed
-
8 Apr 2019 1 repository listed
-
3 Apr 2018 1 repository listed
-
31 Mar 2018 1 repository listed
-
28 Feb 2018 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
Dense Video Captioning using Graph-based Sentence Summarization25 Jun 2025 0 repositories listed
-
Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization25 Jun 2025 0 repositories listed
-
TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation24 Apr 2025 0 repositories listed
-
Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding14 Mar 2025 0 repositories listed
-
Event-Equalized Dense Video Captioning1 Jan 2025 0 repositories listed
-
Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-learning16 Dec 2024 0 repositories listed
-
Video LLMs for Temporal Reasoning in Long Videos4 Dec 2024 0 repositories listed
-
Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding25 Nov 2024 0 repositories listed
-
Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning22 Nov 2024 0 repositories listed
-
Technical Report for Soccernet 2023 -- Dense Video Captioning31 Oct 2024 0 repositories listed
-
15 Apr 2024 0 repositories listed
-
DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement3 Apr 2024 0 repositories listed
-
Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding24 Mar 2024 0 repositories listed
-
Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos28 Nov 2023 0 repositories listed
-
Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols5 Nov 2023 0 repositories listed
-
Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges25 Sep 2023 0 repositories listed
-
Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment5 Jul 2023 0 repositories listed
-
A Review of Deep Learning for Video Captioning22 Apr 2023 0 repositories listed
-
Exploiting Auxiliary Caption for Video Grounding15 Jan 2023 0 repositories listed
-
A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos30 Sep 2022 0 repositories listed
-
Recipe Generation from Unsegmented Cooking Videos21 Sep 2022 0 repositories listed
-
SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions24 Jul 2022 0 repositories listed
-
PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning6 Jul 2022 0 repositories listed
-
18 Apr 2022 0 repositories listed
-
Semantic-Aware Pretraining for Dense Video Captioning13 Apr 2022 0 repositories listed
-
End-to-end Dense Video Captioning as Sequence Generation16 Jan 2022 0 repositories listed
-
DVCFlow: Modeling Information Flow Towards Human-like Video Captioning19 Nov 2021 0 repositories listed
-
Sketch, Ground, and Refine: Top-Down Dense Video Captioning19 Jun 2021 0 repositories listed
-
Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching18 May 2021 0 repositories listed
-
16 Nov 2020 0 repositories listed
-
SACT: Self-Aware Multi-Space Feature Composition Transformer for Multinomial Attention for Video Captioning25 Jun 2020 0 repositories listed
-
14 Jun 2020 0 repositories listed
-
Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos11 Jul 2019 0 repositories listed
-
Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers6 Jun 2019 0 repositories listed
-
RUC+CMU: System Report for Dense Captioning Events in Videos22 Jun 2018 0 repositories listed
-
Jointly Localizing and Describing Events for Dense Video Captioning23 Apr 2018 0 repositories listed
-
Weakly Supervised Dense Video Captioning5 Apr 2017 0 repositories listed
Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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