AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Graph Distillation for Action Detection with Privileged Modalities

Zelun Luo, Jun-Ting Hsieh, Lu Jiang, Juan Carlos Niebles, Li Fei-Fei

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Cross-domain translation and pose · 119 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 a learned distillation graph instead of an empty graph (ablation)graph distillation · mini-NTU RGB+DmAP: 0.464 -> 0.619Improved
use a learned graph instead of a uniform graph (ablation)graph distillation · mini-NTU RGB+DmAP: 0.537 -> 0.619Improved
use a learned graph instead of a prior graph (ablation)graph distillation · mini-NTU RGB+DmAP: 0.571 -> 0.619Improved
use a learned graph instead of a prior graph (ablation)graph distillation · mini-PKU-MMD (tIoU 0.5)mAP: 0.515 -> 0.559Improved
use graph distillation instead of knowledge distillationknowledge distillation · mini-NTU RGB+DmAP: 0.524 -> 0.619Improved
use multi-task privileged learning instead of independent trainingempty graph · mini-NTU RGB+DmAP: 0.464 -> 0.456Hurt
add privileged modalities in the source domain (ablation)src + trg · mini-PKU-MMD (tIoU 0.5)mAP: 0.501 -> 0.533Improved
add privileged modalities in the target domain on top of source PIs (ablation)src w/ PIs + trg · mini-PKU-MMD (tIoU 0.5)mAP: 0.533 -> 0.562Improved
add source-domain pre-training (transfer from NTU RGB+D) (ablation)trg only · mini-PKU-MMD (tIoU 0.5)mAP: 0.200 -> 0.501Improved
increase target privileged modalities from 1 to all (ablation)graph distillation · mini-PKU-MMD (tIoU 0.5)mAP: 0.549 -> 0.562Improved
add transfer pre-training from NTU RGB+D on full PKU-MMD (ablation)graph distillation · PKU-MMD, test RGB (tIoU 0.5)mAP: 0.743 -> 0.801Improved
distill optical flow into RGB on UCF-101 instead of training from scratchRGB stream · UCF-101mAP: 0.484 -> 0.757Improved

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