Papers › KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception

KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception

13 Mar 2025CVPR 2025 1arXiv:2503.10259archive 2025-07-28

Yunpeng Qu, Kun Yuan, Qizhi Xie, Ming Sun, Chao Zhou, Jian Wang

Video Quality Assessment (VQA), which intends to predict the perceptual quality of videos, has attracted increasing attention. Due to factors like motion blur or specific distortions, the quality of different regions in a video varies. Recognizing the region-wise local quality within a video is beneficial for assessing global quality and can guide us in adopting fine-grained enhancement or transcoding strategies. Due to the heavy cost of annotating region-wise quality, the lack of ground truth constraints from relevant datasets further complicates the utilization of local perception. Inspired by the Human Visual System (HVS) that links global quality to the local texture of different regions and their visual saliency, we propose a Kaleidoscope Video Quality Assessment (KVQ) framework, which aims to effectively assess both saliency and local texture, thereby facilitating the assessment of global quality. Our framework extracts visual saliency and allocates attention using Fusion-Window Attention (FWA) while incorporating a Local Perception Constraint (LPC) to mitigate the reliance of regional texture perception on neighboring areas. KVQ obtains significant improvements across multiple scenarios on five VQA benchmarks compared to SOTA methods. Furthermore, to assess local perception, we establish a new Local Perception Visual Quality (LPVQ) dataset with region-wise annotations. Experimental results demonstrate the capability of KVQ in perceiving local distortions. KVQ models and the LPVQ dataset will be available at https://github.com/qyp2000/KVQ.

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 13 code samples harvested from 1 repository linked to this paper: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 9 ran (5 with no instrument failure; 4 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qyp2000/kvq officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 9 ran (4 instrument-failed) · 4 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

13 samples harvested: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 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 · our draft was wrong
3ran; the contract check could not run
5ran
4unverified

Licence: 13 of the 13 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 qyp2000/kvq. “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 1 sample 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.

qyp2000/kvq official repository 13 samples, 9 ran (4 instrument-failed) · 4 unverified
CrossWindowAttention3D vqa/models/kvq.py ran no licence file found · pointer only · 9d98150dc26639b2 · report fixture: returned CrossWindowAttention3D · level recorded 2026-09-22
SalientHead vqa/models/kvq.py ran no licence file found · pointer only · 41c2a23916f4de8e · report fixture: returned SalientHead · level recorded 2026-09-22
TopkRouting vqa/models/kvq.py ran fingerprinted no licence file found · pointer only · ef39b517351848d6 · report fixture: returned TopkRouting · level recorded 2026-09-22
VQAHead vqa/models/kvq.py ran no licence file found · pointer only · 19f608c8a84eaa3b · report fixture: returned VQAHead · level recorded 2026-09-22
WindowAttention3D in 10 papers vqa/models/kvq.py ran no licence file found · pointer only · 9fe56e5dd36cd5d8 · report fixture: returned WindowAttention3D · level recorded 2026-09-22
compute_mask in 19 papers vqa/models/kvq.py ran · our draft was wrong no licence file found · pointer only · 6af013ed0732fd80 · report fixture: signature D:int/0/int, H:int/0/int, W:int/0/int, window_size:tuple/1/int, shift_size:tuple/1/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
get_adaptive_window_size vqa/models/kvq.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 0f0460042f50af71 · report fixture: signature base_window_size:tuple/1/int, input_x_size:tuple/1/int, base_x_size:tuple/1/int · returned tuple · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
vqa/models/kvq.py ran; the contract check could not run (RAISES) no licence file found · pointer only · a168a4b2deed08db · report fixture: signature x:Tensor/5/float, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
window_process vqa/models/kvq.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 5728ba1a61bc8ba3 · report fixture: signature x:Tensor/5/float, pad_shape:tuple/1/int, window_size:tuple/1/int, shift_size:tuple/1/int, shift:bool/0/bool, resized_window_size:NoneType/0/? · returned Tensor · level recorded 2026-09-22
BasicLayer in 56 papers vqa/models/kvq.py unverified no licence file found · pointer only · 5d131053b59593c9 · report
KVQ vqa/models/kvq.py unverified no licence file found · pointer only · 948f64fb15da495e · report
SwinTransformer3D vqa/models/kvq.py unverified no licence file found · pointer only · 330b001a1802dab9 · report
SwinTransformerBlock3D in 9 papers vqa/models/kvq.py unverified no licence file found · pointer only · d72969cac508cd41 · 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 KVQ (graph method: KVQ). 18 bricks; individually on a fixture: 14 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. KVQ entry · level 0 · unverified · 948f64fb15da495e
  2. SalientHead model · level 1 · ran · 41c2a23916f4de8e
  3. SwinTransformer3D model · level 0 · unverified · 330b001a1802dab9
  4. VQAHead model · level 1 · ran · 19f608c8a84eaa3b
  5. BasicLayer model · level 0 · unverified · 5d131053b59593c9
  6. PatchEmbed3D model · level 1 · ran · f9e0db5dae9068ca
  7. PatchMerging model · level 1 · ran · 092afab2341fa8d8
  8. get_adaptive_window_size helper · level 1 · ran; the contract check could not run (RAISES) · 0f0460042f50af71
  9. SwinTransformerBlock3D model · level 0 · unverified · d72969cac508cd41
  10. get_window_size helper · level 1 · ran; the contract check could not run · aad0ea11cb13d353
  11. Mlp helper · level 1 · ran · b684a3f5d798d30a
  12. WindowAttention3D helper · level 1 · ran · 9fe56e5dd36cd5d8
  13. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · a168a4b2deed08db
  14. window_process helper · level 1 · ran; the contract check could not run (RAISES) · 5728ba1a61bc8ba3
  15. window_reverse helper · level 1 · ran · our draft was wrong · 75fd6fbfca7a246c
  16. CrossWindowAttention3D helper · level 1 · ran · 9d98150dc26639b2
  17. compute_mask helper · level 1 · ran · our draft was wrong · 6af013ed0732fd80
  18. TopkRouting helper · level 1 · ran · ef39b517351848d6

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="2503.10259") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Video Quality AssessmentVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionSoftmax

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