Papers › SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding

SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding

6 Jul 2024arXiv:2407.05118archive 2025-07-28

Zixu Cheng, Yujiang Pu, Shaogang Gong, Parisa Kordjamshidi, Yu Kong

Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enables the localization beyond predefined events, posing a certain challenge to the compositional generalizability of existing methods. Recent studies establish the correspondence between videos and queries through a decompose-reconstruct manner to achieve compositional generalization. However, they only consider dominant primitives and build negative queries through random sampling and recombination, resulting in semantically implausible negatives that hinder the models from learning rational compositions. In addition, recent DETR-based methods still underperform in compositional temporal grounding, showing irrational saliency responses when given negative queries that have subtle differences from positive queries. To address these limitations, we first propose a large language model-driven method for negative query construction, utilizing GPT-3.5-Turbo to generate semantically plausible hard negative queries. Subsequently, we introduce a coarse-to-fine saliency ranking strategy, which encourages the model to learn the multi-granularity semantic relationships between videos and hierarchical negative queries to boost compositional generalization. Extensive experiments on two challenging benchmarks validate the effectiveness and generalizability of our proposed method. Our code is available at https://github.com/zxccade/SHINE.

PaperPDFCodeCode Syntology ran

In Syntology 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="2407.05118")

Code

Syntology Ran 9 of 13 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zxccade/shine officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
6ran
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 zxccade/SHINE. “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.

build_position_encoding zxccade/SHINE/shine/position_encoding.py official repository ran licence not identified · pointer only · d6ca656c20df137a · report
coarse_ranking zxccade/SHINE/shine/ctf_ranking.py official repository ran licence not identified · pointer only · e62dd692b8390088 · report
div_loss zxccade/SHINE/shine/ctf_ranking.py official repository ran licence not identified · pointer only · 2fb84c87e0a7ca0e · report
inverse_sigmoid zxccade/SHINE/shine/model.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 6897880b6ce14c94 · report
kl_loss zxccade/SHINE/shine/ctf_ranking.py official repository ran licence not identified · pointer only · db2249562e0e9af0 · report
mask_logits zxccade/SHINE/shine/text_encoder.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 1c17153fb5488283 · report
prepare_batch_inputs zxccade/SHINE/shine/start_end_dataset.py official repository ran licence not identified · pointer only · a959a00d132fc4ac · report
prepare_batch_inputs_train zxccade/SHINE/shine/start_end_dataset.py official repository ran licence not identified · pointer only · 690e7cb41525c697 · report
span_cxw_to_xx zxccade/SHINE/shine/span_utils.py official repository ran · violated contract fingerprinted no licence file found · pointer only · b7639c2e8b83837b · report
accuracy zxccade/SHINE/shine/misc.py official repository unverified no licence file found · pointer only · 081c8abd57d082fd · report
multi_head_attention_forward zxccade/SHINE/shine/attention.py official repository unverified no licence file found · pointer only · a82091666b9db8cf · report
span_xx_to_cxw zxccade/SHINE/shine/span_utils.py official repository unverified no licence file found · pointer only · 7114f025044af9b4 · report
temporal_iou zxccade/SHINE/shine/span_utils.py official repository unverified no licence file found · pointer only · e4ae5582a2533cdb · report

Tasks

Language ModelingLanguage ModellingLarge Language ModelMoment RetrievalSaliency RankingSentence

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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