Papers › VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

29 May 2023NeurIPS 2023 11arXiv:2305.18500archive 2025-07-28

Sihan Chen, Handong Li, Qunbo Wang, Zijia Zhao, Mingzhen Sun, Xinxin Zhu, Jing Liu

Vision and text have been fully explored in contemporary video-text foundational models, while other modalities such as audio and subtitles in videos have not received sufficient attention. In this paper, we resort to establish connections between multi-modality video tracks, including Vision, Audio, and Subtitle, and Text by exploring an automatically generated large-scale omni-modality video caption dataset called VAST-27M. Specifically, we first collect 27 million open-domain video clips and separately train a vision and an audio captioner to generate vision and audio captions. Then, we employ an off-the-shelf Large Language Model (LLM) to integrate the generated captions, together with subtitles and instructional prompts into omni-modality captions. Based on the proposed VAST-27M dataset, we train an omni-modality video-text foundational model named VAST, which can perceive and process vision, audio, and subtitle modalities from video, and better support various tasks including vision-text, audio-text, and multi-modal video-text tasks (retrieval, captioning and QA). Extensive experiments have been conducted to demonstrate the effectiveness of our proposed VAST-27M corpus and VAST foundation model. VAST achieves 22 new state-of-the-art results on various cross-modality benchmarks. Code, model and dataset will be released at https://github.com/TXH-mercury/VAST.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 42 code samples harvested from 2 repositories linked to this paper: 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. Where Syntology's instrument failed: 9 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 12 ran (9 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 23 samples from 1 repository, 23 ran (16 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 35 samples that ran have no recorded date.

txh-mercury/vast officialmentioned in paperpytorchMITSyntology: 19 samples, 12 ran (3 instrument-failed) · 7 unverified report
TXH-mercury/VALOR mentioned on GitHubpytorchMITSyntology: 23 samples, 23 ran (7 instrument-failed) · 0 unverified 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

42 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
1ran · violated contract
9ran · our draft was wrong
1ran; the contract check could not run
20ran
7unverified

Licence: 8 of the 42 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

txh-mercury/vast official repository 19 samples, 12 ran (3 instrument-failed) · 7 unverified
Contra_head model/vast.py ran · metamorphic tier: deterministic MIT (permissive) · d0dc6ea5061f7dc5 · report fixture: returned Contra_head · level recorded 2026-09-22
GELU in 21 papers model/vast.py ran fingerprinted MIT (permissive) · 48d525c2e5cbc84a · report fixture: signature input_:Tensor/2/float · returned Tensor · level recorded 2026-09-24
GatherLayer in 12 papers model/vast.py ran MIT (permissive) · a839c0c942f1b694 · report fixture: returned GatherLayer · level recorded 2026-09-22
Match_head model/vast.py ran · metamorphic tier: deterministic MIT (permissive) · 2e0587cc12b477e2 · report fixture: returned Match_head · level recorded 2026-09-22
TokenMasker model/vast.py ran · metamorphic tier: deterministic MIT (permissive) · 3e58c21b8cf01cc4 · report fixture: returned TokenMasker · level recorded 2026-09-22
compute_max_audio_sample_num_for_position_embeddings utils/args.py ran · honoured contract MIT (permissive) · 0122d74913461cf9 · report fixture: signature data_cfg:DataConfig/0/? · returned int · level recorded 2026-09-25
compute_max_vision_sample_num_for_position_embeddings utils/args.py ran · honoured contract MIT (permissive) · 30fd4a1a3eedb19c · report fixture: signature data_cfg:DataConfig/0/? · returned int · level recorded 2026-09-25
disabled_train in 172 papers model/general_module.py ran · violated contract MIT (permissive) · 4cb732f513d69dfd · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded, date not recorded
execCmd utils/offline_process_data.py ran · our draft was wrong fingerprinted MIT (permissive) · 77a45c1e515dbe2e · report fixture: signature cmd:str/0/str · returned str · level recorded 2026-09-25
get_best_name utils/pipeline.py ran MIT (permissive) · 36075dd106d2bbbe · report fixture: signature eval_name:str/0/str, metric:dict/0/? · returned str · level recorded 2026-09-26
load_from_pretrained_dir utils/build_model.py ran · our draft was wrong MIT (permissive) · 7d297bdebd282cba · report fixture: signature args:Args/0/? · returned dict · level recorded 2026-09-25
parse_with_config in 12 papers utils/args.py ran · our draft was wrong MIT (permissive) · 15b65a6a6e8fd954 · report fixture: signature parser:ArgumentParser/0/? · returned EasyDict · level recorded 2026-09-25
MMGeneralModule model/vast.py unverified MIT (permissive) · b6fa06654838e4da · report
VAST model/vast.py unverified MIT (permissive) · c22a88dfed0bd02e · report
all_gather_list in 9 papers utils/distributed.py unverified MIT (permissive) · eee800bfe0a47a9f · report
all_gather_with_grad in 93 papers model/vast.py unverified MIT (permissive) · 0ec9fc2025c16f65 · report
build_optimizer in 83 papers utils/build_optimizer.py unverified MIT (permissive) · cc4ffe92873b4ee6 · report
load_from_resume utils/build_model.py unverified MIT (permissive) · 647f671c01bde501 · report
TXH-mercury/VALOR community (archive-listed) 23 samples, 23 ran (7 instrument-failed) · 0 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
model/bert.py ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
basic_clean in 217 papers model/clip_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
cached_path in 47 papers model/file_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 349d780dd4a89a37 · report fixture: signature url_or_filename:str/0/str, cache_dir:str/0/str · returned str · level recorded 2026-09-26
clean in 39 papers inference.py ran MIT (permissive) · 67dae5beb14eebd7 · report fixture: signature self:TextCleaner/0/?, text:str/0/str · returned str · level recorded 2026-09-26
clones in 92 papers model/transformer.py ran MIT (permissive) · 98110ed59394ae02 · report fixture: signature x:callable/0/?, times:int/0/int · returned ModuleList · level recorded 2026-09-26
cook_refs in 36 papers scorer/bleu_scorer.py ran MIT (permissive) · 6c465efd98518ed2 · report fixture: signature refs:list/1/list, eff:str/0/str, n:int/0/int · returned tuple · level recorded 2026-09-26
cook_test in 35 papers scorer/bleu_scorer.py ran MIT (permissive) · fb961e80ca3db085 · report fixture: signature test:list/1/str, xxx_todo_changeme:tuple/1/list, eff:NoneType/0/?, n:int/0/int · returned dict · level recorded 2026-09-26
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
model/videoswin.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 55120f2026b56aa2 · report fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded, date not recorded
filename_to_url in 54 papers model/file_utils.py ran MIT (permissive) here; the stored copy is pointer only · db0ac56aaf6e35e6 · report fixture: signature filename:str/0/str, cache_dir:str/0/str · returned tuple · level recorded 2026-09-26
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
model/transformer.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · fdc64f4c72036ae4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
model/bert.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 40e9fee2e0b7e278 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_padded_tokens inference.py ran MIT (permissive) · b65e5286fa81fca8 · report fixture: signature self:MockTokenizer/0/?, txt_tokens:list/1/int, type:str/0/str, max_len:int/0/int · returned Tensor · level recorded 2026-09-26
get_pairs in 260 papers model/clip_tokenizer.py ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
load_vocab in 107 papers model/bert_tokenizer.py ran MIT (permissive) · fb95c4b13cdf89a2 · report fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded 2026-09-26
precook in 38 papers scorer/bleu_scorer.py ran MIT (permissive) · aad08f61905b40a5 · report fixture: signature words:list/1/str, n:int/0/int, out:bool/0/bool · returned tuple · level recorded 2026-09-26
split in 67 papers inference.py ran fingerprinted MIT (permissive) · d92ebd9f3d882489 · report fixture: signature frame_name_lists:list/1/str, sample_num:int/0/int · returned list · level recorded 2026-09-26
trans in 9 papers model/modeling.py ran MIT (permissive) · 8b5247b663a8f1b5 · report fixture: signature x:ndarray/2/float · returned Tensor · level recorded 2026-09-26
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input
model/videoswin.py ran MIT (permissive) · 7810fed39bf5c241 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-24
url_to_filename in 73 papers model/file_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · af64ec220e8bcdbc · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-22
valid in 24 papers model/modeling.py ran MIT (permissive) · 3df7530a6ef7c69d · report fixture: signature x:Tensor/1/float · returned bool · level recorded 2026-09-26
whitespace_clean in 230 papers model/clip_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
whitespace_tokenize in 49 papers model/bert_tokenizer.py ran fingerprinted MIT (permissive) · da7295883cd7da14 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-26
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
model/videoswin.py ran MIT (permissive) · ed4b0e420c5e9bde · report fixture: signature x:Tensor/5/float, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-26

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for VAST (graph method: VAST). 11 bricks; individually on a fixture: 7 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. VAST entry · level 0 · unverified · c22a88dfed0bd02e
  2. Contra_head helper · level 1 · ran · d0dc6ea5061f7dc5
  3. MMGeneralModule helper · level 0 · unverified · b6fa06654838e4da
  4. Match_head helper · level 1 · ran · 2e0587cc12b477e2
  5. TokenMasker helper · level 1 · ran · 3e58c21b8cf01cc4
  6. all_gather_with_grad helper · level 0 · unverified · 0ec9fc2025c16f65
  7. concat_all_gather helper · level 0 · unverified · 73cecca9f3575f09
  8. disabled_train helper · level 1 · ran · violated contract · 4cb732f513d69dfd
  9. GELU helper · level 1 · ran · 48d525c2e5cbc84a
  10. GatherLayer helper · level 1 · ran · a839c0c942f1b694
  11. gelu helper · level 1 · ran · honoured contract · c2f0705ed8e6f7e6

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2305.18500") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Audio captioningAudio-visual Question AnsweringCross-Modal RetrievalImage CaptioningLanguage ModellingLarge Language ModelTGIF-FrameText to Audio RetrievalVideo CaptioningVideo Question AnsweringVideo RetrievalVisual Question Answering (VQA)Zero-Shot Cross-Modal RetrievalZero-Shot Video Retrieval

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio captioning AudioCaps VAST BLEU-4 0.295 #17 of 18 Archive leaderboard report
Audio captioning AudioCaps VAST CIDEr 0.781 #17 of 18 Archive leaderboard report
Audio captioning AudioCaps VAST METEOR 0.247 #17 of 18 Archive leaderboard report
Audio captioning AudioCaps VAST ROUGE-L 0.509 #17 of 18 Archive leaderboard report
Audio captioning Clotho VAST BLEU-4 19 #9 of 11 Archive leaderboard report
Audio captioning Clotho VAST CIDEr 0.519 #9 of 11 Archive leaderboard report
Audio captioning Clotho VAST METEOR 19.3 #9 of 11 Archive leaderboard report
Audio captioning Clotho VAST ROUGE-L 40.8 #9 of 11 Archive leaderboard report
Audio-visual Question Answering MUSIC-AVQA VAST Acc 80.7 #1 of 6 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 VAST Text-to-image R@1 68.0 #1 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 VAST Text-to-image R@10 92.8 #1 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 VAST Text-to-image R@5 87.7 #1 of 36 Archive leaderboard report
Cross-Modal Retrieval Flickr30k VAST Text-to-image R@1 91.0 #27 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k VAST Text-to-image R@10 99.5 #27 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k VAST Text-to-image R@5 98.5 #27 of 27 Archive leaderboard report
Image Captioning COCO Captions VAST CIDER 149.0 #37 of 41 Archive leaderboard report
Image Captioning COCO Captions VAST SPICE 27.0 #37 of 41 Archive leaderboard report
Text to Audio Retrieval AudioCaps VAST R@1 52.0 #2 of 11 Archive leaderboard report
Text to Audio Retrieval AudioCaps VAST R@10 82.9 #2 of 11 Archive leaderboard report
Text to Audio Retrieval AudioCaps VAST R@5 76.8 #2 of 11 Archive leaderboard report
Text to Audio Retrieval Clotho VAST R@1 26.9 #3 of 12 Archive leaderboard report
Text to Audio Retrieval Clotho VAST R@10 66.1 #3 of 12 Archive leaderboard report
Text to Audio Retrieval Clotho VAST R@5 53.2 #3 of 12 Archive leaderboard report
Video Captioning MSR-VTT VAST BLEU-4 56.7 #2 of 24 Archive leaderboard report
Video Captioning MSR-VTT VAST CIDEr 78.0 #2 of 24 Archive leaderboard report
Video Captioning TVC VAST BLEU-4 19.9 #1 of 2 Archive leaderboard report
Video Captioning TVC VAST CIDEr 74.1 #1 of 2 Archive leaderboard report
Video Captioning VATEX VAST BLEU-4 45.0 #2 of 10 Archive leaderboard report
Video Captioning VATEX VAST CIDEr 99.5 #2 of 10 Archive leaderboard report
Video Captioning YouCook2 VAST BLEU-4 18.2 #1 of 14 Archive leaderboard report
Video Captioning YouCook2 VAST CIDEr 1.99 #1 of 14 Archive leaderboard report
Video Question Answering ActivityNet-QA VAST Accuracy 50.4 #5 of 36 Archive leaderboard report
Video Question Answering MSRVTT-QA VAST Accuracy 50.1 #2 of 14 Archive leaderboard report
Video Retrieval ActivityNet VAST text-to-video R@1 70.5 #2 of 31 Archive leaderboard report
Video Retrieval ActivityNet VAST text-to-video R@10 95.5 #2 of 31 Archive leaderboard report
Video Retrieval ActivityNet VAST text-to-video R@5 90.9 #2 of 31 Archive leaderboard report
Video Retrieval DiDeMo VAST text-to-video R@1 72.0 #3 of 40 Archive leaderboard report
Video Retrieval DiDeMo VAST text-to-video R@10 91.4 #3 of 40 Archive leaderboard report
Video Retrieval DiDeMo VAST text-to-video R@5 89.0 #3 of 40 Archive leaderboard report
Video Retrieval MSR-VTT VAST text-to-video R@1 63.9 #2 of 40 Archive leaderboard report
Video Retrieval MSR-VTT VAST text-to-video R@10 89.6 #2 of 40 Archive leaderboard report
Video Retrieval MSR-VTT VAST text-to-video R@5 84.3 #2 of 40 Archive leaderboard report
Video Retrieval VATEX VAST text-to-video R@1 83.0 #2 of 13 Archive leaderboard report
Video Retrieval VATEX VAST text-to-video R@10 99.2 #2 of 13 Archive leaderboard report
Video Retrieval VATEX VAST text-to-video R@5 98.2 #2 of 13 Archive leaderboard report
Video Retrieval YouCook2 VAST text-to-video R@1 50.4 #1 of 16 Archive leaderboard report
Video Retrieval YouCook2 VAST text-to-video R@10 80.8 #1 of 16 Archive leaderboard report
Video Retrieval YouCook2 VAST text-to-video R@5 74.3 #1 of 16 Archive leaderboard report
Visual Question Answering (VQA) MSVD-QA VAST Accuracy 0.60 #5 of 36 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k VAST Text-to-image R@1 90.4 #22 of 22 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo VAST text-to-video R@1 55.5 #3 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo VAST text-to-video R@10 79.6 #3 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo VAST text-to-video R@5 74.3 #3 of 26 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT VAST text-to-video R@1 49.3 #6 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT VAST text-to-video R@10 73.9 #6 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT VAST text-to-video R@5 68.3 #6 of 41 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