AI Paper Atlas

Research map / Video / Video-language understanding

Selective Query-Guided Debiasing for Video Corpus Moment Retrieval

Sunjae Yoon, Ji Woo Hong, Eunseop Yoon, Dahyun Kim, Junyeong Kim, Hee Suk Yoon, Chang D. Yoo

ECCV 2022 · Video › Video-language understanding · approach: Video moment retrieval · 28 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 biased moment retrieval (BMR) with selective debiasing (ablation)SQuiDNet · VCMR TVR valR@1 (tIoU=0.7): 4.62 -> 8.52Improved
add conditional moment prediction (CMP) (ablation)SQuiDNet · VCMR TVR valR@1 (tIoU=0.7): 8.17 -> 8.52Improved
use selective decision rule instead of treating all BMR predictions as negative (ablation)SQuiDNet · VCMR TVR valR@1 (tIoU=0.7): 6.41 -> 8.52Improved
use selective decision rule instead of treating all BMR predictions as positive (ablation)SQuiDNet · VCMR TVR valR@1 (tIoU=0.7): 6.72 -> 8.52Improved
use co-occurrence table decision rule instead of all-negative (ablation)SQuiDNet · VCMR TVR valR@1 (tIoU=0.7): 6.41 -> 7.91Improved
use learnable confounder instead of co-occurrence table (ablation)SQuiDNet · VCMR TVR valR@1 (tIoU=0.7): 7.91 -> 8.52Improved
remove subtitles and use plain video features instead of subtitle-matched features (ablation)SQuiDNet · VCMR DiDeMoR@1/R@10/R@100 (tIoU=0.7): -0.36%/-0.74%/-1.82%Hurt
add BMR to a HERO baseline NMRHERO · VCMR TVR test-publicR@1 (tIoU=0.7): 6.21 -> 8.34Improved
add BMR to the naive model, with SQuiD debiasingSQuiDNet (N) · VCMR TVR test-publicR@1 (tIoU=0.7): 4.09 -> 10.09Improved
add BMR to the naive model, with SQuiD debiasingSQuiDNet (N) · VCMR ActivityNetR@1 (tIoU=0.7): 1.62 -> 4.43Improved
add BMR to the naive model, with SQuiD debiasingSQuiDNet (N) · VCMR DiDeMo +ASRR@1 (tIoU=0.7): 1.73 -> 3.52Improved

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