Browse › Computer Vision › Image Captioning › COCO Captions

Image Captioning archive 2025-07-28

COCO Captions Benchmark (Image Captioning)

41 rows 36 with code listed 9 metrics Dataset page

Syntology Since the archive (Syntology): none placed; no newer paper judged to report on this board so far.

Image Captioning is the task of describing the content of an image in words. This task lies at the intersection of computer vision and natural language processing. Most image captioning systems use an encoder-decoder framework, where an input image is encoded into an intermediate representation of the information in the image, and then decoded into a descriptive text sequence. The most popular benchmarks are nocaps and COCO, and models are typically evaluated according to a BLEU or CIDER metric.

The archive carries no text for this table; the description above is the archive's text for the task Image Captioning. archive 2025-07-28

Over time archive 2025-07-28

Direction inferred from the metric name, not from the archive: BLEU-4 (higher is better), ROUGE-L (higher is better), BLEU-1 (higher is better), BLEU-2 (higher is better), BLEU-3 (higher is better). Not inferred (points only, no best-so-far line): CIDER, METEOR, SPICE, CLIPScore. Points are placed at the row's paper date, not an evaluation date; 40 of 41 rows carry one.

The chart needs JavaScript; the table below carries every value.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 mPLUG 46.5155.132.026.0 – Paper Code 2022 linked, not harvested report
2 OFA 44.9154.932.526.6 – Paper Code 2022 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
3 GIT 44.1151.1 32.226.3 – Paper Code 2022 official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified report
4 BLIP-2 ViT-G OPT 2.7B (zero-shot) 43.7145.8 – Paper Code 2023 community repositories only · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result report
5 BLIP-2 ViT-G OPT 6.7B (zero-shot) 43.5145.2 – Paper Code 2023 community repositories only · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result report
6 ExpansionNet v2 (No VL pretraining) 42.7143.730.624.761.183.5 – Paper Code 2022 linked, not harvested report
7 LEMON 42.6145.531.425.5 – Paper – 2021 no code linked report
8 BLIP-2 ViT-G FlanT5 XL (zero-shot) 42.4144.5 – Paper Code 2023 community repositories only · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result report
9 GRIT (No VL pretraining - base) 42.4144.230.624.360.784.2 – Paper Code 2022 linked, not harvested report
10 Prompt Tuning 41.81141.431.5124.42 – Paper Code 2022 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
11 Oscar 41.714030.624.5 – Paper Code 2020 official (archive's flag): 1 ran · 13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified report
12 Xmodal-Ctx 41.4139.930.424.060.483.4 – Paper Code 2022 linked, not harvested report
13 Xmodal-Ctx + OSCAR 41.3142.224.9 – Paper Code 2022 linked, not harvested report
14 X-VLM (base) 41.3140.8 – Paper Code 2021 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 report
15 VinVL 41.0140.931.125.2 – Paper Code 2021 community repositories only · 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 report
16 CoCa 40.9143.633.924.7 – Paper Code 2022 10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified report
17 SimVLM 40.6143.333.425.4 – Paper Code 2021 22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 3 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified report
18 Prismer 40.4136.531.424.4 – Paper Code 2023 linked, not harvested report
19 PTP-BLIP (14M) 40.1135.030.423.7 – Paper Code 2022 official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 1 unverified report
20 L-Verse 39.931.423.360.4 – Paper Code 2021 linked, not harvested report
21 Xmodal-Ctx 39.7135.930.023.759.581.5 – Paper Code 2022 linked, not harvested report
22 X-Transformer 39.7132.829.523.459.180.965.851.5 – Paper Code 2020 linked, not harvested report
23 AoANet + VC 39.529.359.3 – Paper Code 2020 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified report
24 Transformer_NSC 39.4129.628.922.858.780.765.651.3 – Paper Code 2020 linked, not harvested report
25 Meshed-Memory Transformer 39.1131.229.222.658.680.8 – Paper Code 2019 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
26 CLIP Text Encoder (RL w/ CIDEr-reward) 38.2124.928.758.5 – Paper Code 2022 linked, not harvested report
27 RefineCap (w/ REINFORCE) 37.8127.228.322.558.080.264.549.9 – Paper – 2021 no code linked report
28 RDN 37.3125.228.157.480.2 – Paper – 2019 no code linked report
29 SmallCapd=16, Large 37.2121.828.321.5 – Paper Code 2022 linked, not harvested report
30 ClipCap (Transformer) 33.53113.0827.4521.05 – Paper Code 2021 official (archive's flag): 5 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
31 ClipCap (MLP + GPT2 tuning) 32.15108.3527.120.12 – Paper Code 2021 official (archive's flag): 5 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
32 CapDec 26.491.825.1 – Paper Code 2022 official (archive's flag): 2 ran · 4 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; 2 where Syntology's instrument failed) · 1 unverified report
33 From Captions to Visual Concepts and Back 25.723.6 – Paper Code 2014 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified report
34 VLKD (ViT-B/16) 16.758.319.713.4 – Paper – 2021 no code linked report
35 LaDiC (ours, 30 steps) 0.382126.229.5 – Paper Code 2024 linked, not harvested report
36 VALOR 152.525.7 ✓ Paper Code 2023 linked, not harvested report
37 VAST 149.027.0 ✓ Paper Code 2023 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 report
38 Virtex (ResNet-101) 9418.5 – Paper Code 2020 community repositories only · 1 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; 0 where Syntology's instrument failed) · 0 unverified report
39 KOSMOS-1 (1.6B) (zero-shot) 84.716.8 – – – not matched report
40 LaDiC 22.458.7 – Paper Code 2024 linked, not harvested report
41 BLIP-FuseCap 78.5 – Paper Code 2023 linked, not harvested report

All 41 rows shown. 40 link to a paper page on this site; 2 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran 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”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 20 rows have a graph line, from 17 distinct papers. Rows whose paper has a sample that ran: 20 (19 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument). Papers: 17 with a sample that ran: 16 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 20 rows with a graph line, 18 have an archive-official repository: on 13 a sample from it ran (12 with a run with no instrument failure), on 5 the samples that ran came from community repositories only, and on 0 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 188 samples: 131 ran (of which 27 constructed an object rather than computing a result; 99 with no instrument failure: 12 honoured, 5 violated, 82 with no contract checked; 32 where Syntology's instrument failed) · 57 unverified. Separately, 53 of those 188 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), none had this board among the leaderboards the extractor considered for their tables yet (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,596 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), so none await a verdict here. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

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