AI Paper Atlas

Research map / Detection and segmentation / Tracking

Deep Affinity Network for Multiple Object Tracking

Shijie Sun, Naveed Akhtar, Huansheng Song, Ajmal Saeed Mian, Mubarak A. Shah

TPAMI 2019 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 358 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
use DAN online tracker versus best prior online trackerDAN · MOT17MOTA: 48.0439 -> 52.4224Improved
use DAN versus best prior online trackerDAN · MOT17MOTAL: 48.7518 -> 53.916Improved
DAN has more identity switches than prior trackersDAN · MOT17ID switches: 3998 -> 8431Hurt
apply MOT17-trained DAN directly to MOT15 without fine-tuning versus CDA-DDALDAN · MOT15MOTA: 32.80 -> 38.30Improved
use CompACT instead of EB detectorDAN · UA-DETRACPR-MOTA: 18.6Mixed
use RCNN instead of EB detectorDAN · UA-DETRACPR-MOTAP: 15.1 and 37.1Mixed

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