Papers › Recurrent Models of Visual Attention

Recurrent Models of Visual Attention

24 Jun 2014NeurIPS 2014 12arXiv:1406.6247archive 2025-07-28

Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image size. While the model is non-differentiable, it can be trained using reinforcement learning methods to learn task-specific policies. We evaluate our model on several image classification tasks, where it significantly outperforms a convolutional neural network baseline on cluttered images, and on a dynamic visual control problem, where it learns to track a simple object without an explicit training signal for doing so.

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

Syntology 24 code samples: 23 from 7 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 24: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 4 honoured, 2 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 23 samples from 7 repositories, 20 ran (19 with no instrument failure; 1 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 1 of its repositories that Syntology harvested for other papers:

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. 2 of the 21 samples that ran have no recorded date.

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

MiuGod0126/RAM-Paddle mentioned on GitHubpaddleMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
Sooram/cnn mentioned on GitHubtfSyntology: not harvested report
Sooram/stn mentioned on GitHubtfSyntology: not harvested report
abdosharaf98/active-sensing-paper mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
amobiny/Recurrent_Attention_Model mentioned on GitHubtfSyntology: not harvested report
baidu-research/DT-RAM mentioned on GitHubtorchSyntology: not harvested report
conan7882/recurrent-attention-model mentioned on GitHubtfMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
kevinzakka/recurrent-visual-attention mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
kiwi1944/CRISense mentioned on GitHubpytorchSyntology: not harvested report
luxxxlucy/recurrent-attention-model-revisited mentioned on GitHubpytorchSyntology: not harvested report
mengdi-li/robotic-occlusion-reasoning mentioned on GitHubpytorchMITSyntology: not harvested report
mimikaan/Attention-Model mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Spatial Transformer Networks (arXiv:1506.02025; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 4 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
qingzew/tensorflow-ram mentioned on GitHubtfGPL-3.0Syntology: not harvested report
stephanboner/gabor_data mentioned on GitHubSyntology: not harvested report
theowu23451/DRAM mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
tianyu-tristan/Visual-Attention-Model mentioned on GitHubtfSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
ulstu/ml mentioned on GitHubSyntology: not harvested report
ulstu/robotics_ml mentioned on GitHubSyntology: not harvested report
gitlab.com/exwzd-public/kiritani_ono_2020 mentioned on GitHubpytorchSyntology: not harvested report
johnrobinsn/catch pytorchSyntology: 1 sample, 1 ran (0 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.

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

24 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 4 honoured, 2 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 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.

4ran · honoured contract
2ran · violated contract
1ran · our draft was wrong
14ran
3unverified

Licence: 2 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 7 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.

MiuGod0126/RAM-Paddle community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
bounding_box utils.py ran MIT (permissive) · 51f550c140da0e1f · report fixture: signature x:float/0/float, y:float/0/float, size:int/0/int, color:str/0/str · returned Rectangle · level recorded 2026-09-26
denormalize in 64 papers
census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
utils.py ran fingerprinted MIT (permissive) · aba2291398c33f9e · report fixture: signature T:Tensor/0/float, coords:Tensor/2/float · returned Tensor · level recorded 2026-09-26
get_logger in 383 papers utils.py ran MIT (permissive) · 8f7357fe28cb2df6 · report fixture: signature loggername:str/0/str, save_path:str/0/str · returned Logger · level recorded 2026-09-26
str2bool in 533 papers config.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 248284f69adfeaad · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
abdosharaf98/active-sensing-paper community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
create_ff_network nets.py ran MIT (permissive) · 0a8922aeb5af661f · report fixture: signature layer_dims:list/1/int, h_activation:str/0/str, out_activation:str/0/str · returned Sequential · level recorded 2026-09-26
linear_cyclical_schedule annealing_schedules.py ran MIT (permissive) · 51c4801bd010779d · report fixture: signature n_epochs:int/0/int, start:float/0/float, stop:float/0/float, n_cycles:int/0/int, ratio:float/0/float · returned ndarray · level recorded 2026-09-26
ramp_schedule annealing_schedules.py ran MIT (permissive) · c55ed1649d97e51c · report fixture: signature n_epochs:int/0/int, epoch_thresh:int/0/int, start:float/0/float, stop:float/0/float · returned ndarray · level recorded 2026-09-26
step_schedule annealing_schedules.py ran MIT (permissive) · 29c539727d9bed6f · report fixture: signature n_epochs:int/0/int, epoch_thresh:int/0/int, step_from:float/0/float, step_to:float/0/float · returned ndarray · level recorded 2026-09-26
score_action BAS.py unverified MIT (permissive) · 13b8d8b5eb2eceb6 · report
conan7882/recurrent-attention-model community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
batch_flatten lib/model/layers.py ran MIT (permissive) · 7df4bf75e234defd · report fixture: signature x:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-26
get_rng lib/dataflow/mnist.py ran MIT (permissive) · d7f84a4593d266f3 · report fixture: signature obj:SimpleObject/0/? · returned RandomState · level recorded 2026-09-26
get_shape2D lib/utils/utils.py ran fingerprinted MIT (permissive) · 1d25c8422ef144ad · report fixture: signature in_val:int/0/int · returned list · level recorded 2026-09-26
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
lib/dataflow/mnist.py ran fingerprinted MIT (permissive) · 1b199adffea8aa84 · report fixture: signature im:Tensor/4/float · returned Tensor · level recorded 2026-09-26
Linear in 127 papers lib/model/layers.py unverified MIT (permissive) · 729767fbba984f0f · report
sample_normal_single lib/utils/tfutils.py unverified MIT (permissive) · 1f580339b4241ecb · report
kevinzakka/recurrent-visual-attention community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
add_argument_group in 31 papers config.py ran · our draft was wrong MIT (permissive) · b7dd47e91ac1448a · report fixture: signature name:str/0/str · returned _ArgumentGroup · level recorded 2026-09-22
theowu23451/DRAM community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
convert_to_dataset model/utils.py ran MIT (permissive) · 42875219a09169da · report fixture: signature data:ndarray/2/float, batch_size:int/0/int · returned _BatchDataset · level recorded 2026-09-26
create_bbox model/visualizer.py ran MIT (permissive) · 92d2f0beac737086 · report fixture: signature xy:tuple/1/int, width:int/0/int, height:int/0/int, color:str/0/str, linewidth:float/0/float, alpha:int/0/int · returned Rectangle · level recorded 2026-09-26
truncate in 26 papers model/utils.py ran fingerprinted MIT (permissive) · eae54352422ca8a7 · report fixture: signature n:float/0/float, decimals:int/0/int · returned float · level recorded 2026-09-26
tianyu-tristan/Visual-Attention-Model community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
mask_labels SVHN/dram/dram.py ran · honoured contract fingerprinted MIT (permissive) · dfdf1a70103e043b · report fixture: signature labels:ndarray/2/int · returned ndarray · level recorded 2026-09-22
repair_labels SVHN/dram/dram.py ran · honoured contract fingerprinted MIT (permissive) · ee60170e008f8124 · report fixture: signature labels:ndarray/2/int · returned ndarray · level recorded 2026-09-22
truncate_labels SVHN/dram/dram.py ran · honoured contract fingerprinted MIT (permissive) · 58d0f0ae48e3212e · report fixture: signature labels:ndarray/2/int · returned ndarray · level recorded 2026-09-22
johnrobinsn/catch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
adjust_learning_rate in 125 papers ram_catch.py ran · honoured contract MIT (permissive) · b9ae4f85e8921042 · report fixture: signature optimizer:SGD/0/?, epoch:int/0/int, lr:float/0/float · returned float · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (0 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.
str2bool in 533 papers repository not located ran · violated contract licence of this copy not recorded · 7c508037b40522af · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded

Tasks

Hard AttentionImage ClassificationReinforcement LearningTranslationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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