AI Paper Atlas

Research map / Detection and segmentation / CNN features

Object Detection in Videos by High Quality Object Linking

Peng Tang, Chunyu Wang, Xinggang Wang, Wenyu Liu, Wenjun Zeng, Jingdong Wang

TPAMI 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 118 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 short tubelet linking to CPN + T-NMS (ablation)object linking detector · ImageNet VID valmAP (%): 70.5 -> 74.5Improved
add object linking over whole video (short tubelet linking)static detector · ImageNet VID val (fast objects)mAP (%): 47.2 -> 56.0Improved
add short tubelet linkingstatic detector · ImageNet VID val (occluded objects)mAP (%): 65.4 -> 70.4Improved
replace per-frame NMS with T-NMS in CPN (ablation)CPN · ImageNet VID valmAP (%): 69.3 -> 70.5Improved
use video segment length 2 instead of longer segments (ablation)T-NMS tubelet detection · ImageNet VID valmAP (%): +1.4% mAPImproved
link short tubelets in the same frame instead of Seq-NMS across neighboring frames (ablation)object linking · ImageNet VID val (fast objects)mAP (%): 49.4 -> 56.0Improved
replace Seq-NMS with CPN+Seq-NMS (ablation)Seq-NMS · ImageNet VID valmAP (%): 70.9 -> 72.1Improved
use CPN cuboid proposals instead of union proposals (ablation)short tubelet linking · ImageNet VID valmAP (%): 72.6 -> 74.5Improved
use CPN cuboid proposals instead of union proposals (ablation)proposal generation · Cuboid recall IoU 0.7recall (%): 84.9 -> 90.6Improved
use strict evaluation protocol with instance IDs (ablation)tubelet evaluation · ImageNet VID valmAP (%): 70.5 -> 69.8Hurt
train on VID+DET mixture with multi-scaleobject linking detector · ImageNet VID valmAP (%): 74.5 -> 80.6Improved

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