AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning

Zhengxuan Wei, Jiajin Tang, Sibei Yang

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 0 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
train on Splice augmented data in a single stage (ablation)baseline M-DETR variant · QVHighlights valmAP avg: 44.82 -> 42.56Hurt
add Boost to Splice in single-stage training (ablation)Splice only · QVHighlights valmAP avg: 42.56 -> 43.88Improved
two-stage training on real data only, no augmentation (ablation)baseline · QVHighlights valmAP avg: 44.82 -> 44.66No clear effect
add Splice augmentation to vanilla two-stage training (ablation)two-stage · QVHighlights valmAP avg: 44.66 -> 47.11Improved
add Boost on top of Splice with vanilla two-stage (ablation)two-stage · QVHighlights valmAP avg: 47.11 -> 48.07Improved
add dual-path distillation to Splice two-stage (ablation)Splice+two-stage · QVHighlights valmAP avg: 47.11 -> 49.11Improved
add discriminative contrastive loss to Splice two-stage (ablation)Splice+two-stage · QVHighlights valmAP avg: 47.11 -> 47.87Improved
add DCL to Splice+Dill (ablation)Splice+Dill · QVHighlights valmAP avg: 49.11 -> 50.64Improved
add Boost to Splice+Dill+DCL (full model) (ablation)AMR · QVHighlights valmAP avg: 50.64 -> 51.66Improved
add Boost to Splice+Dill (ablation)Splice+Dill · QVHighlights valmAP avg: 49.11 -> 50.03Improved
full AMR versus BAM-DETRAMR · QVHighlights valR1@0.5: 65.10 -> 70.13Improved
full AMR versus UVCOMAMR · TACoSR1@0.7: 23.32 -> 26.07Improved

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