AI Paper Atlas

Research map / Video / Video-language understanding

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

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

ECCV 2024 · Video › Video-language understanding · approach: Temporal video grounding · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SHINE (LLM hard negatives + coarse-to-fine saliency ranking) to QD-DETRQD-DETR · Charades-CG Novel-CompositionR1@0.5: 42.30 -> 50.23Improved
add SHINE to Moment-DETRMoment-DETR · Charades-CG Test-TrivialR1@0.5: 49.48 -> 57.14Improved
add SHINE to QD-DETR on ActivityNet-CGQD-DETR · ActivityNet-CG Novel-CompositionR1@0.5: 26.91 -> 29.56Improved
add SHINE to QD-DETR on Novel-Word split of ActivityNet-CGQD-DETR · ActivityNet-CG Novel-WordmIoU: 31.21 -> 30.98No clear effect
add L_inter (positive vs negative query saliency gap) to coarse-grained loss (ablation)QD-DETR · Charades-CG Novel-CompositionR1@0.5: 42.30 -> 46.69Improved
replace base saliency loss with L_intra (ablation)QD-DETR · Charades-CG Novel-CompositionR1@0.5: 42.30 -> 44.02Improved
add first fine-grained ranking constraint L_fr^1 (ablation)QD-DETR · Charades-CG Novel-CompositionR1@0.5: 42.30 -> 46.43Improved
add L_fr^3 without the complete hierarchy (ablation)QD-DETR · Charades-CG Novel-CompositionR1@0.5: 46.72 -> 46.40Hurt
complete all four fine-grained constraints together with L_cr (ablation)QD-DETR · Charades-CG Novel-CompositionR1@0.7: 24.52 -> 27.69Improved
use LLM (GPT-3.5 Turbo) hard negatives instead of random sampling (ablation)QD-DETR · Charades-CG Novel-CompositionR1@0.5: 47.41 -> 50.23Improved
use LLM hard negatives instead of random sampling on ActivityNet-CG (ablation)QD-DETR · ActivityNet-CG Novel-CompositionR1@0.5: 29.59 -> 29.56No clear effect
include prepositions and adverbs in hard negative construction (ablation)QD-DETR · Charades-CG Novel-CompositionR1@0.7: 25.28 -> 27.69Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy