Browse State-of-the-Art › Video Captioning

Video Captioning

211 papers with code · 13 benchmarks · 38 datasets archive 2025-07-28

Computer Vision

Video Captioning is a task of automatic captioning a video by understanding the action and event in the video which can help in the retrieval of the video efficiently through text.

Source: NITS-VC System for VATEX Video Captioning Challenge 2020

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

13 leaderboard tables shown for this task, 13 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. 10 shown of 13 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MSR-VTT (24 rows) mPLUG-2 mPLUG-2: A Modularized Multi-modal Foundation Model Across Text,... code Syntology community repositories only · 17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified Compare
MSVD (16 rows) MaMMUT MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks code Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
YouCook2 (14 rows) VAST VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model... code Syntology official (archive's flag): 12 ran · 35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified Compare
VATEX (10 rows) VALOR VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset code — Compare
ActivityNet Captions (5 rows) VideoCoCa VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from... — — Compare
MSRVTT-CTN (4 rows) CEN NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative — — Compare
MSVD-CTN (4 rows) CEN NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative — — Compare
Hindi MSR-VTT (2 rows) SBD_Keyframe An Efficient Keyframes Selection Based Framework for Video Captioning — — Compare
Shot2Story20K (2 rows) Shotluck-Holmes (3.1B) Shotluck Holmes: A Family of Efficient Small-Scale Large Language... code — Compare
TVC (2 rows) VAST VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model... code Syntology official (archive's flag): 12 ran · 35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified Compare
ChinaOpen-1k (1 row) GVT ChinaOpen: A Dataset for Open-world Multimodal Learning code — Compare
MSVD-Indonesian (1 row) VNS-GRU (Cross-Lingual) MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian code — 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

38 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 38 until expanded.

Subtasks archive 2025-07-28

6 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 473 · with a code link: 211 · where Syntology ran a sample: 64 (55 with a run with no instrument failure, 9 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (64 of 473 tagged: 55 with a run with no instrument failure, 9 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 473, 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.

Syntology lines on 47 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