AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning To Track Objects From Unlabeled Videos

Jilai Zheng, Chao Ma, Houwen Peng, Xiaokang Yang

ICCV 2021 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 65 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
generate pseudo boxes from optical flow and dynamic programming instead of random boxes (ablation)USOT* · VOT2017/18EAO: 0.195 -> 0.263Improved
add naive Siamese tracker initialization before cycle memory training (ablation)USOT* · VOT2017/18EAO: 0.306 -> 0.344Improved
add naive Siamese tracker initialization before cycle memory training (ablation)USOT* · VOT2017/18accuracy (A): 0.575 -> 0.578No clear effect
add GOT-10k to VID as training data (ablation)USOT* · VOT2017/18EAO: 0.315 -> 0.320Improved
add LaSOT to VID and GOT-10k training data (ablation)USOT* · VOT2017/18EAO: 0.320 -> 0.337Improved
add YouTube-VOS to training data (ablation)USOT* · VOT2017/18EAO: 0.337 -> 0.344Improved
set online weight w to 0.7 instead of 0.3 at queue length 7 (ablation)USOT* · VOT2017/18EAO: 0.310 -> 0.344Improved
set memory queue length to 7 instead of 5 at w=0.7 (ablation)USOT* · VOT2017/18EAO: 0.313 -> 0.344Improved
set memory queue length to 8 instead of 7 at w=0.7 (ablation)USOT* · VOT2017/18EAO: 0.344 -> 0.341No clear effect
use supervised ImageNet backbone pretraining (USOT* vs USOT)USOT · VOT2017/18EAO: 0.290 -> 0.344Improved
use supervised ImageNet backbone pretraining (USOT* vs USOT)USOT · OTB2015AUC success: 58.9 -> 57.4Hurt
use supervised ImageNet backbone pretraining (USOT* vs USOT)USOT · VOT2020EAO: 0.222 -> 0.219No clear effect

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