Papers › Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos
Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos
Rui Qian, Shuangrui Ding, Xian Liu, Dahua Lin
Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further and explore the possibility of integrating these two features to enhance object-centric representations. Our preliminary experiments indicate that query slot attention can extract different semantic components from the RGB feature map, while random sampling based slot attention can exploit temporal correspondence cues between frames to assist instance identification. Motivated by this, we propose a novel semantic-aware masked slot attention on top of the fused semantic features and correspondence maps. It comprises two slot attention stages with a set of shared learnable Gaussian distributions. In the first stage, we use the mean vectors as slot initialization to decompose potential semantics and generate semantic segmentation masks through iterative attention. In the second stage, for each semantics, we randomly sample slots from the corresponding Gaussian distribution and perform masked feature aggregation within the semantic area to exploit temporal correspondence patterns for instance identification. We adopt semantic- and instance-level temporal consistency as self-supervision to encourage temporally coherent object-centric representations. Our model effectively identifies multiple object instances with semantic structure, reaching promising results on unsupervised video object discovery. Furthermore, we achieve state-of-the-art performance on dense label propagation tasks, demonstrating the potential for object-centric analysis. The code is released at https://github.com/shvdiwnkozbw/SMTC.
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):
get_harvested_code_for_paper(arxiv_id="2308.09951")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2308.09951", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2308.09951")
Code
Syntology 32 code samples harvested from 1 repository linked to this paper: 24 ran (of which 5 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 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: 32 samples from 1 repository, 24 ran (21 with no instrument failure; 3 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.
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
32 samples harvested: 24 ran (of which 5 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 8 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.
Licence: 32 of the 32 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 shvdiwnkozbw/smtc. “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 3 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.
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket src/model/model_action.py ran no licence file found · pointer only ·
59f6323575d06123 · report
fixture: returned Attention · level recorded 2026-09-22 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket src/model/model_action.py ran no licence file found · pointer only ·
fdfb57b897e2108a · report
fixture: returned Block · level recorded 2026-09-22 8d3958a6f3d74f48 · report
fixture: returned LinearPositionEmbedding · level recorded 2026-09-22 78d5aec68b3b3810 · report
fixture: returned Mlp · level recorded 2026-09-22 census: 9 implementations from 9 papers, 6 distinct outputs on one shared input src/model/model_action.py ran no licence file found · pointer only ·
57d7cfb61454da15 · report
fixture: returned PatchEmbed · level recorded 2026-09-22 961e24591b43a876 · report
fixture: signature inputs:Tensor/3/float, bs:int/0/int, weight:Tensor/2/float, init_slots:NoneType/0/?, num_slots:NoneType/0/? · returned tuple · level recorded 2026-09-24 census: 16 implementations from 16 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 src/model/model_action.py ran; the contract check could not run (RAISES) no licence file found · pointer only ·
cffc671a6c09decc · 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 2026-09-22 1ad1217597a9ce9a · report
fixture: signature tensor:Tensor/2/float, expand_dim:int/0/int, num_replicas:int/0/int · returned Tensor · level recorded 2026-09-24 da6467b584338d1e · report
fixture: signature data:Tensor/4/float · returned Tensor · level recorded 2026-09-24 fb2519bb639a667c · report
fixture: signature frame_aug:str/0/str, patch_size:tuple/1/int · returned function · level recorded 2026-09-24 aec20ef76445c38c · report
fixture: signature filename:str/0/str, extensions:tuple/1/str · returned bool · level recorded 2026-09-24 401846920f5d643b · report
fixture: signature img:Tensor/3/float · returned ndarray · level recorded 2026-09-24 d2f9a9f21c7deaef · report
fixture: signature directory:str/0/str, class_to_idx:dict/0/?, videos:dict/0/?, extensions:tuple/1/str, is_valid_file:NoneType/0/? · returned list · level recorded 2026-09-24 05f4448b41123ba7 · report
fixture: signature B:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22 14b1cc74dcb694bf · report
fixture: signature x:ndarray/3/int, n:int/0/int, transform:callable/0/?, shape:tuple/1/int, scale:list/1/float · returned Tensor · level recorded 2026-09-24 80fbe78b6d72ce6b · report
fixture: signature v_grid:Tensor/4/float · returned Tensor · level recorded 2026-09-22 f69760b372f30f51 · report
fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-24 600497c0fb4eb8c7 · report
fixture: signature transform:callable/0/?, shape:tuple/1/int, stride:list/1/float · returned function · level recorded 2026-09-24 ff6fed6f7dbd0b2d · report
fixture: signature sample_dir:str/0/str, resolution:tuple/1/int · returned ndarray · level recorded 2026-09-24 a3d6633188714161 · report
fixture: signature sample_dir:str/0/str, resolution:tuple/1/int · returned ndarray · level recorded 2026-09-24 3bc5479a4c355475 · report
fixture: signature args:Namespace/0/? · returned list · level recorded 2026-09-24 census: 24 implementations from 29 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 src/vos.py ran · honoured contract no licence file found · pointer only ·
b476623700945834 · report
fixture: signature tensor:Tensor/2/float · returned ndarray · level recorded 2026-09-22 census: 5 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float64 src/vos.py ran · honoured contract no licence file found · pointer only ·
7aac4c51e0ceee97 · report
fixture: signature ndarray:ndarray/2/float · returned Tensor · level recorded 2026-09-22 census: 37 implementations from 54 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 src/model/model_action.py ran; the contract check could not run (RAISES) no licence file found · pointer only ·
d8578a1e5c318cf9 · 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 2026-09-22 112bc720ea2ac6a4 · report
552cf891cb0247d4 · report
6af62a7f5b6eeae7 · report
a66bde73ff0d98ea · report
80b696d316a10cca · report
932f488e9f83940b · report
af24f61606320660 · report
f7c7ef0730305776 · 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 semantic-aware masked slot attention (graph method: semantic-aware masked slot attention). 15 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
- SlotAttentionAutoEncoder entry · level 0 · unverified ·
a66bde73ff0d98ea - Attention helper · level 1 · ran ·
59f6323575d06123 - Block helper · level 1 · ran ·
fdfb57b897e2108a - LinearPositionEmbedding helper · level 1 · ran ·
8d3958a6f3d74f48 - ObjectStateChange model · level 0 · unverified ·
6af62a7f5b6eeae7 - SlotAttention model · level 1 · ran ·
961e24591b43a876 - vit_small helper · level 0 · unverified ·
f7c7ef0730305776 - Mlp helper · level 1 · ran ·
78d5aec68b3b3810 - SlotBlock helper · level 0 · unverified ·
80b696d316a10cca - VisionTransformer helper · level 0 · unverified ·
932f488e9f83940b - DropPath helper · level 1 · ran ·
ad5f80b54573c0e0 - PatchEmbed helper · level 1 · ran ·
57d7cfb61454da15 - trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) ·
d8578a1e5c318cf9 - drop_path helper · level 1 · ran; the contract check could not run ·
55120f2026b56aa2 - _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) ·
cffc671a6c09decc
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="2308.09951") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
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