AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Cross-Category Video Highlight Detection via Set-Based Learning

Minghao Xu, Hang Wang, Bingbing Ni, Riheng Zhu, Zhenbang Sun, Changhu Wang

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 63 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 Transformer encoder T to set-based learning module (ablation)SL-module · YouTube Highlights (average)mAP: 0.651 -> 0.693Improved
add Transformer encoder T to set-based learning module (ablation)SL-module · TVSum (average)top-5 mAP: 0.712 -> 0.733Improved
add Transformer encoder T to set-based learning module (ablation)SL-module · ActivityNet (average)mAP: 0.759 -> 0.779Improved
add knowledge distillation between coarse and fine learners (ablation)DL-VHD · ActivityNet sport->householdmAP: 0.778 -> 0.793Improved
add knowledge distillation between coarse and fine learners (ablation)DL-VHD · YouTube Highlights surfing->skiingmAP: 0.658 -> 0.686Improved
add fine-grained learner to coarse learner with distillation (ablation)DL-VHD · YouTube Highlights surfing->skiingmAP: 0.631 -> 0.686Improved
add coarse-grained learner on top of source-only (fine learner) (ablation)DL-VHD · ActivityNet sport->householdmAP: 0.707 -> 0.742Improved
use full DL-VHD instead of target-oracle on gymnastics and skiingDL-VHD · YouTube Highlights surfing->skiingmAP: 0.661 -> 0.686Improved
use full DL-VHD instead of strongest UDA baselineDL-VHD · ActivityNet sport->householdmAP: 0.765 -> 0.793Improved
use set-based learning module instead of MINI-NetSL-module · TVSum (average)top-5 mAP: 0.698 -> 0.733Improved
use set size N of at least 16SL-module · YouTube HighlightsmAP: N >= 16Improved
set trade-off lambda around 1.0DL-VHD · cross-category tasksmAP: around 1.0Improved

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