Papers › Adaptive Focus for Efficient Video Recognition

Adaptive Focus for Efficient Video Recognition

7 May 2021ICCV 2021 10arXiv:2105.03245archive 2025-07-28

Yulin Wang, Zhaoxi Chen, Haojun Jiang, Shiji Song, Yizeng Han, Gao Huang

In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which shifts smoothly across frames. Therefore, we model the patch localization problem as a sequential decision task, and propose a reinforcement learning based approach for efficient spatially adaptive video recognition (AdaFocus). In specific, a light-weighted ConvNet is first adopted to quickly process the full video sequence, whose features are used by a recurrent policy network to localize the most task-relevant regions. Then the selected patches are inferred by a high-capacity network for the final prediction. During offline inference, once the informative patch sequence has been generated, the bulk of computation can be done in parallel, and is efficient on modern GPU devices. In addition, we demonstrate that the proposed method can be easily extended by further considering the temporal redundancy, e.g., dynamically skipping less valuable frames. Extensive experiments on five benchmark datasets, i.e., ActivityNet, FCVID, Mini-Kinetics, Something-Something V1&V2, demonstrate that our method is significantly more efficient than the competitive baselines. Code is available at https://github.com/blackfeather-wang/AdaFocus.

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 23 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 13 ran (7 with no instrument failure; 6 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

blackfeather-wang/AdaFocus officialmentioned in papermentioned on GitHubpytorchSyntology: 23 samples, 13 ran (6 instrument-failed) · 10 unverified report
leaplabthu/uni-adafocus mentioned on GitHubpytorchMITSyntology: 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.

Code Syntology ran Syntology

23 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 10 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 · our draft was wrong
2ran; the contract check could not run
7ran
10unverified

Licence: 23 of the 23 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 blackfeather-wang/AdaFocus. “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.

blackfeather-wang/AdaFocus official repository 23 samples, 13 ran (6 instrument-failed) · 10 unverified
Bottleneck in 98 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran no licence file found · pointer only · dba4e40d3ec4e1a6 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ConvBNReLU in 16 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 694778287c1e57cb · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
InvertedResidual in 9 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · b0b0395a2d15fd11 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LinearCLassifier Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0d27f8bcdbc1a81a · report fixture: signature feature:Tensor/3/float · returned tuple · level recorded 2026-09-22
Memory in 19 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran no licence file found · pointer only · 6dab8592a6da4561 · report fixture: returned NoneType · level recorded 2026-09-24
MobileNetV2 in 6 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran fingerprinted no licence file found · pointer only · a0a4faf6f3826228 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
RecurrentClassifier Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran no licence file found · pointer only · 49b0ecfe3309749c · report fixture: signature feature:Tensor/3/float · returned tuple · level recorded 2026-09-24
conv1x1 in 691 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran · our draft was wrong no licence file found · pointer only · 8b4abacfcdbd5f34 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran · our draft was wrong no licence file found · pointer only · 29b46555d311b33f · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-22
get_patch in 8 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran · our draft was wrong no licence file found · pointer only · e8eed825e5369a09 · report fixture: signature images:Tensor/4/float, action_sequence:Tensor/2/float, patch_size:int/0/int · returned Tensor · level recorded 2026-09-24
mobilenet_v2 in 23 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran · our draft was wrong no licence file found · pointer only · 2f3f5423309d07f4 · report fixture: signature num_classes:int/0/int, width_mult:float/0/float, inverted_residual_setting:NoneType/0/?, round_nearest:int/0/int · returned MobileNetV2 · level recorded 2026-09-22
random_crop in 59 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 1270d498daf32c06 · report fixture: signature im:ndarray/3/float, size:int/0/int, pad_size:int/0/int · returned ndarray · level recorded 2026-09-22
zero_pad in 9 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 8e712c383c677282 · report fixture: signature im:ndarray/3/float, pad_size:int/0/int · returned ndarray · level recorded 2026-09-22
ActorCritic in 10 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · aaf4fc54301dc25b · report
Focuser Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · ecfff27ee4d3b4ea · report
GFV Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · f2ede844bb4fec8b · report
Glancer Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · 778bd73246149e78 · report
PPO Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · d95a709e40c1819c · report
PatchSampler Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · 8306c10e2d90a490 · report
ResNet in 139 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · 076a8d0ad95b226b · report
_resnet in 27 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · 5e103ea4fee0452b · report
resnet50 in 121 papers Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py unverified no licence file found · pointer only · d4b9ffcd5506ea85 · report

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 AdaFocus (graph method: AdaFocus). 24 bricks; individually on a fixture: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. GFV entry · level 0 · unverified · f2ede844bb4fec8b
  2. Focuser model · level 0 · unverified · ecfff27ee4d3b4ea
  3. Glancer model · level 0 · unverified · 778bd73246149e78
  4. LinearCLassifier model · level 1 · ran · 0d27f8bcdbc1a81a
  5. RecurrentClassifier model · level 1 · ran · 49b0ecfe3309749c
  6. Memory helper · level 1 · ran · 6dab8592a6da4561
  7. PPO helper · level 0 · unverified · d95a709e40c1819c
  8. PatchSampler sampler · level 0 · unverified · 8306c10e2d90a490
  9. resnet50 helper · level 0 · unverified · d4b9ffcd5506ea85
  10. mobilenet_v2 helper · level 1 · ran · our draft was wrong · 2f3f5423309d07f4
  11. ActorCritic helper · level 0 · unverified · aaf4fc54301dc25b
  12. get_patch helper · level 1 · ran · our draft was wrong · e8eed825e5369a09
  13. random_crop helper · level 1 · ran; the contract check could not run (RAISES) · 1270d498daf32c06
  14. Bottleneck helper · level 1 · ran · dba4e40d3ec4e1a6
  15. _resnet helper · level 0 · unverified · 5e103ea4fee0452b
  16. MobileNetV2 helper · level 1 · ran · a0a4faf6f3826228
  17. zero_pad helper · level 1 · ran; the contract check could not run (RAISES) · 8e712c383c677282
  18. conv1x1 helper · level 1 · ran · our draft was wrong · 8b4abacfcdbd5f34
  19. conv3x3 helper · level 1 · ran · our draft was wrong · 29b46555d311b33f
  20. ResNet helper · level 0 · unverified · 076a8d0ad95b226b
  21. ConvBNReLU helper · level 1 · ran · 694778287c1e57cb
  22. InvertedResidual helper · level 1 · ran · b0b0395a2d15fd11
  23. _make_divisible helper · level 1 · ran · honoured contract · 13f1c8e878ee2013
  24. BasicBlock helper · level 0 · unverified · 3e72f5c3aa3cfb73

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="2105.03245") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Computational EfficiencyVideo Recognition

1 archive task tag without a task page not shown.

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