Papers › SnAG: Scalable and Accurate Video Grounding

SnAG: Scalable and Accurate Video Grounding

2 Apr 2024CVPR 2024 1arXiv:2404.02257archive 2025-07-28

Fangzhou Mu, Sicheng Mo, Yin Li

Temporal grounding of text descriptions in videos is a central problem in vision-language learning and video understanding. Existing methods often prioritize accuracy over scalability -- they have been optimized for grounding only a few text queries within short videos, and fail to scale up to long videos with hundreds of queries. In this paper, we study the effect of cross-modal fusion on the scalability of video grounding models. Our analysis establishes late fusion as a more cost-effective fusion scheme for long-form videos with many text queries. Moreover, it leads us to a novel, video-centric sampling scheme for efficient training. Based on these findings, we present SnAG, a simple baseline for scalable and accurate video grounding. Without bells and whistles, SnAG is 43% more accurate and 1.5x faster than CONE, a state of the art for long-form video grounding on the challenging MAD dataset, while achieving highly competitive results on short videos.

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 20 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 1 repository, 13 ran (4 with no instrument failure; 9 where Syntology's instrument failed); found in paper text by Syntology: 5 samples from 1 repository, 0 ran (0 with no instrument failure; 0 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

happyharrycn/actionformer_release mentioned on GitHubpytorchMITSyntology: 15 samples, 13 ran (9 instrument-failed) · 2 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

20 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 7 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.

1ran · honoured contract
5ran · our draft was wrong
4ran; the contract check could not run
3ran
7unverified

Licence: 16 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 11 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 2 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. “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.

happyharrycn/actionformer_release community (archive-listed) 15 samples, 13 ran (9 instrument-failed) · 2 unverified
ctr_diou_loss_1d in 11 papers libs/modeling/losses.py ran MIT (permissive) here; the stored copy is pointer only · 12d8ba65aabcb2b4 · report fixture: returned Tensor · level recorded 2026-09-25
ctr_giou_loss_1d in 6 papers libs/modeling/losses.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 66693d03280664b1 · report fixture: returned Tensor · level recorded 2026-09-25
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
libs/modeling/blocks.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · a34c005ba2203f35 · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
get_sinusoid_encoding in 24 papers libs/modeling/blocks.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 3531df7b0c9b0791 · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-22
load_config in 389 papers libs/core/config.py ran · our draft was wrong MIT (permissive) · a957fa06c95c422f · report fixture: signature config_file:str/0/str · returned dict · level recorded 2026-09-24
register_backbone in 6 papers libs/modeling/models.py ran MIT (permissive) here; the stored copy is pointer only · cee845f405ecf37e · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-25
register_dataset in 26 papers libs/datasets/datasets.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 2ee0df0825339a6e · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-25
register_generator in 10 papers libs/modeling/models.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 3db1c5ab5f3f0198 · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-25
register_neck in 6 papers libs/modeling/models.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e5ef13b176081594 · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-25
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
libs/modeling/losses.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 0d06c0983d985a4a · report fixture: returned Tensor · level recorded 2026-09-25
trivial_batch_collator in 10 papers libs/datasets/data_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 0c250bf03b8c9311 · report fixture: signature batch:list/1/dict · returned list · level recorded 2026-09-25
trunc_normal_ in 154 papers
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
libs/modeling/weight_init.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 02566da69866c48c · 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
truncate_feats in 6 papers libs/datasets/data_utils.py ran MIT (permissive) · 073b23d898943c73 · report fixture: signature data_dict:dict/0/?, max_seq_len:int/0/int, trunc_thresh:float/0/float, offset:int/0/int, crop_ratio:NoneType/0/?, max_num_trials:int/0/int, has_action:bool/0/bool, no_trunc:bool/0/bool · returned dict · level recorded 2026-09-24
make_data_loader in 13 papers libs/datasets/datasets.py unverified MIT (permissive) · 635369f63ec96b89 · report
make_dataset in 144 papers libs/datasets/datasets.py unverified MIT (permissive) here; the stored copy is pointer only · ffebfbb8094c0dcc · report
fmu2/snag_release found in paper text by Syntology 5 samples, 0 ran · 5 unverified
PtTransformer libs/modeling/model.py unverified no licence file found · pointer only · 61e4463bc2eaf08c · report
make_fusion libs/modeling/model.py unverified no licence file found · pointer only · c4eba9d35a22d565 · report
make_head in 8 papers libs/modeling/model.py unverified no licence file found · pointer only · 10c20d3c7447a10c · report
make_text_net libs/modeling/model.py unverified no licence file found · pointer only · 45cd753de473cb89 · report
make_video_net libs/modeling/model.py unverified no licence file found · pointer only · e0b4f1cbb0de076d · 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 SnAG (graph method: SnAG). 5 bricks; individually on a fixture: 0 ran · 5 unverified. The assembly has not been run end-to-end.

  1. PtTransformer entry · level 0 · unverified · 61e4463bc2eaf08c
  2. make_fusion helper · level 0 · unverified · c4eba9d35a22d565
  3. make_head helper · level 0 · unverified · 10c20d3c7447a10c
  4. make_text_net helper · level 0 · unverified · 45cd753de473cb89
  5. make_video_net helper · level 0 · unverified · e0b4f1cbb0de076d

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="2404.02257") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Video GroundingVideo Understanding

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