Papers › Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

27 Sep 2022arXiv:2209.13306archive 2025-07-28

Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

Spatio-Temporal video grounding (STVG) focuses on retrieving the spatio-temporal tube of a specific object depicted by a free-form textual expression. Existing approaches mainly treat this complicated task as a parallel frame-grounding problem and thus suffer from two types of inconsistency drawbacks: feature alignment inconsistency and prediction inconsistency. In this paper, we present an end-to-end one-stage framework, termed Spatio-Temporal Consistency-Aware Transformer (STCAT), to alleviate these issues. Specially, we introduce a novel multi-modal template as the global objective to address this task, which explicitly constricts the grounding region and associates the predictions among all video frames. Moreover, to generate the above template under sufficient video-textual perception, an encoder-decoder architecture is proposed for effective global context modeling. Thanks to these critical designs, STCAT enjoys more consistent cross-modal feature alignment and tube prediction without reliance on any pre-trained object detectors. Extensive experiments show that our method outperforms previous state-of-the-arts with clear margins on two challenging video benchmarks (VidSTG and HC-STVG), illustrating the superiority of the proposed framework to better understanding the association between vision and natural language. Code is publicly available at https://github.com/jy0205/STCAT.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2209.13306")

Code

Syntology Ran 11 of 18 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 10 ran with no contract checked.

By repository: official repository: 18 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jy0205/stcat officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

18 samples harvested; 11 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
10ran
7unverified

Licence: 0 of the 18 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 jy0205/stcat. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

BackboneBase jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · 61a5ef5ec49e4ea8 · report
FeatureResizer jy0205/stcat/models/pipeline.py official repository ran fingerprinted Apache-2.0 (permissive) · 2c8652f8cdc39a8a · report
GroupNorm32 jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · 6a44d56c318a9f2b · report
Joiner jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · d79f14a1bc1a6186 · report
MLP jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · c7728510fb5fa2dd · report
NestedTensor jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · 60a2fb58c9949c1d · report
PositionEmbeddingLearned jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · fa04a0c6d2415dac · report
PositionEmbeddingSine jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · f52bb0cf00c7d60c · report
PositionEmbeddingSineHW jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · 7b9116f0334dab6b · report
Roberta jy0205/stcat/models/pipeline.py official repository ran Apache-2.0 (permissive) · 0edb5fe68c13683e · report
build_position_encoding jy0205/stcat/models/pipeline.py official repository ran · our draft was wrong Apache-2.0 (permissive) · ebf7ea1f0aba8315 · report
Backbone jy0205/stcat/models/pipeline.py official repository unverified Apache-2.0 (permissive) · 8687762072eb9277 · report
GroupNormBackbone jy0205/stcat/models/pipeline.py official repository unverified Apache-2.0 (permissive) · ad5c02224767d3c7 · report
STCATNet jy0205/stcat/models/pipeline.py official repository unverified Apache-2.0 (permissive) · ffc2b8b986f923af · report
build_decoder jy0205/stcat/models/pipeline.py official repository unverified Apache-2.0 (permissive) · 554210938d06c170 · report
build_encoder jy0205/stcat/models/pipeline.py official repository unverified Apache-2.0 (permissive) · 0a690726c1cb50e7 · report
build_text_encoder jy0205/stcat/models/pipeline.py official repository unverified Apache-2.0 (permissive) · 10aac717b87ceafd · report
build_vis_encoder jy0205/stcat/models/pipeline.py official repository unverified Apache-2.0 (permissive) · f85b47f8c900ff25 · report

Tasks

DecoderSpatio-Temporal Video GroundingVideo Grounding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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