Papers › Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

25 Jul 2017CVPR 2018 6arXiv:1707.07998archive 2025-07-28

Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, Lei Zhang

Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.

PaperPDFConference PDFCodeCode Syntology ran

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

The archive's official repository (peteanderson80/bottom-up-attention) was not harvested; the 8 samples below come from 3 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 9 code samples: 8 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 9: 9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 3 repositories, 8 ran (1 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 7 of its repositories that Syntology harvested for other papers:

No date is recorded for any of the 9 samples that ran: their levels were written before Syntology's graph kept the date.

65 repositories listed; official and paper-mentioned ones first.

peteanderson80/bottom-up-attention officialmentioned on GitHubSyntology: not harvested report
BierOne/VQA-AttReg mentioned on GitHubpytorchSyntology: not harvested report
BigRedT/info-ground mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Cloud-CV/visual-chatbot mentioned on GitHubpytorchSyntology: not harvested report
Dlut-lab-zmn/Image-Captioning-Attack mentioned on GitHubpytorchSyntology: not harvested report
FJSam/SelfCritical_ImageCaptioning mentioned on GitHubpytorchSyntology: not harvested report
FengSuSky/CCB-VQA mentioned on GitHubpytorchSyntology: not harvested report
JHKim-snu/GVCCI mentioned on GitHubpytorchSyntology: not harvested report
JHKim-snu/PGA mentioned on GitHubpytorchSyntology: not harvested report
SJTU-VLG/ImageCaption-LBPF-qy mentioned on GitHubpytorchSyntology: not harvested report
SatyamGaba/visual_question_answering mentioned on GitHubpytorchSyntology: not harvested report
SatyamGaba/vqa mentioned on GitHubpytorchSyntology: not harvested report
SinghJasdeep/Attention-on-Attention-for-VQA mentioned on GitHubpytorchSyntology: not harvested report
SpencerWhitehead/vqap2 mentioned on GitHubpytorchSyntology: not harvested report
ThanThoai/Visual-Question-Answering_Vietnamese mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks (arXiv:2004.06165; that paper's own run record: 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); nothing checks that they implement this paper's method. report
VincentYing/Attention-on-Attention-for-VQA mentioned on GitHubpytorchSyntology: not harvested report
Wentong-DST/up-down-captioner mentioned on GitHubcaffe2Syntology: not harvested report
ZephyrZhuQi/ssbaseline mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Zhendong-Wang/arsm_image_captioning mentioned on GitHubpytorchSyntology: not harvested report
airsplay/lxmert mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AAAI id aaai_32468 (that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
alab-nii/eval_vl_glue mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models (arXiv:2104.08066; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
allenai/pythia mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
batra-mlp-lab/visdial-challenge-starter-pytorch mentioned on GitHubpytorchSyntology: not harvested report
brandontrabucco/up_down_cell mentioned on GitHubtfSyntology: not harvested report
brandontrabucco/up_down_rnn_cell mentioned on GitHubtfSyntology: not harvested report
chrisc36/bottom-up-attention-vqa mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
facebookresearch/mmf mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
feifengwhu/question_attention mentioned on GitHubpytorchSyntology: not harvested report
fuqianya/bottom-up-attention-paddle mentioned on GitHubpaddleSyntology: not harvested report
hengyuan-hu/bottom-up-attention-vqa mentioned on GitHubpytorchSyntology: not harvested report
hjjpku/dynamic_graph_caption mentioned on GitHubpytorchSyntology: not harvested report
jackroos/pythia mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
jiahuei/COMIC-Compact-Image-Captioning-with-Attention mentioned on GitHubtfSyntology: not harvested report
jiahuei/Self-Critical-SCST-TensorFlow mentioned on GitHubtfSyntology: not harvested report
kangkang59812/GraphCaption mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
king-zark/self_critical mentioned on GitHubpytorchSyntology: not harvested report
lauradhatt/Interesting-Reads mentioned on GitHubSyntology: not harvested report
leaplabthu/pseudo-q mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding (arXiv:2203.08481; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
longjj/Caffe-SGDR mentioned on GitHubSyntology: not harvested report
marioskatsak/mapert mentioned on GitHubpytorchSyntology: not harvested report
mazm13/Image-to-Tree.pytorch mentioned on GitHubpytorchSyntology: not harvested report
meiqiguo/iccv2021-atypicalitydetection mentioned on GitHubpytorchSyntology: not harvested report
mitjanikolaus/compositional-image-captioning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Compositional Generalization in Image Captioning (arXiv:1909.04402; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
mokhalid-dev/Attention-based-VQA-model mentioned on GitHubpytorchSyntology: not harvested report
nocaps-org/updown-baseline mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to nocaps: novel object captioning at scale (arXiv:1812.08658; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method. report
peteanderson80/Up-Down-Captioner mentioned on GitHubcaffe2Syntology: not harvested report
rishavbb/bottom_up_vqa mentioned on GitHubtfSyntology: not harvested report
ronghanghu/pythia mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ruotianluo/DiscCaptioning mentioned on GitHubpytorchSyntology: not harvested report
ruotianluo/GoogleConceptualCaptioning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-critical Sequence Training for Image Captioning (arXiv:1612.00563; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
ruotianluo/ImageCaptioning.pytorch mentioned on GitHubpytorchSyntology: not harvested report
ruotianluo/Transformer_Captioning mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
ruotianluo/neuraltalk2.pytorch mentioned on GitHubpytorchSyntology: not harvested report
ruotianluo/self-critical.pytorch mentioned on GitHubpytorchSyntology: not harvested report
sgondala/GoogleConceptualCaptioning mentioned on GitHubpytorchSyntology: not harvested report
thilinicooray/Bottom-up-vqa mentioned on GitHubpytorchSyntology: not harvested report
ukyh/switch_disc_caption mentioned on GitHubpytorchSyntology: not harvested report
windweller/PragmaticVQA mentioned on GitHubSyntology: not harvested report
xiaobai714/image_caption mentioned on GitHubpytorchSyntology: not harvested report
xuewyang/Fashion_Captioning mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
yangdsh/VQA-BUTD-demo mentioned on GitHubSyntology: not harvested report
yanxinyan1/yxy mentioned on GitHubpytorchSyntology: not harvested report
yifanh1/gqa_pytorch mentioned on GitHubpytorchSyntology: not harvested report
laihuihui/htc paddleSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

9 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
8ran · our draft was wrong

Licence: 6 of the 9 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 3 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. 1 sample is listed last, in a group without a repository. “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”. “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.

chrisc36/bottom-up-attention-vqa community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
elementwise_logsumexp in 5 papers vqa_debias_loss_functions.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 4bd23f3562cfbd1c · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded, date not recorded
convert_sigmoid_logits_to_binary_logprobs in 5 papers vqa_debias_loss_functions.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 0e2c50fe59debfb7 · report fixture: signature logits:Tensor/2/float · returned tuple · level recorded, date not recorded
renormalize_binary_logits vqa_debias_loss_functions.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 21690a7e909f0f41 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned tuple · level recorded, date not recorded
kangkang59812/GraphCaption community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
pack_wrapper in 13 papers models/AttModel.py ran · our draft was wrong MIT (permissive) · d2379d710eedc4ae · report fixture: signature module:callable/0/?, att_feats:Tensor/3/float, att_masks:Tensor/2/float · returned Tensor · level recorded, date not recorded
pad_unsort_packed_sequence in 13 papers models/AttModel.py ran · our draft was wrong MIT (permissive) · bfac58a04b6835f5 · report fixture: signature input:PackedSequence/1/Tensor, inv_ix:Tensor/1/int · returned Tensor · level recorded, date not recorded
sort_pack_padded_sequence in 13 papers models/AttModel.py ran · our draft was wrong fingerprinted MIT (permissive) · e56d2f9cbd9cb8b1 · report fixture: signature input:Tensor/3/float, lengths:Tensor/1/int · returned tuple · level recorded, date not recorded
ruotianluo/Transformer_Captioning community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
models/TransformerModel.py ran · our draft was wrong no licence file found · pointer only · 20bb0ff4a2d77a03 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/4/float, dropout:callable/0/? · returned tuple · level recorded, date not recorded
subsequent_mask in 38 papers models/TransformerModel.py ran · violated contract no licence file found · pointer only · dd03765c7da9ca51 · report fixture: signature size:int/0/int · returned Tensor · level recorded, date not recorded
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
clones in 92 papers repository not located ran · our draft was wrong licence of this copy not recorded · a3722169bbc81569 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded, date not recorded

Tasks

Image CaptioningVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) GQA Test2019 BottomUp Accuracy 49.74 #107 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 BottomUp Binary 66.64 #107 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 BottomUp Consistency 78.71 #107 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 BottomUp Distribution 5.98 #107 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 BottomUp Open 34.83 #107 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 BottomUp Plausibility 84.57 #107 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 BottomUp Validity 96.18 #107 of 127 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std Up-Down overall 70.34 #28 of 38 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