AI Paper Atlas

Research map / Detection and segmentation / Tracking

End-to-End Active Object Tracking and Its Real-World Deployment via Reinforcement Learning

Wenhan Luo, Peng Sun, Fangwei Zhong, Wei Liu, Tong Zhang, Yizhou Wang

TPAMI 2019 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 206 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 environment augmentation (randomized initial positions and flips) to training (ablation)Active tracker · ViZDoom StandardAR: 840 -> 2547Improved
add environment augmentation (invisible background objects, varied start points) (ablation)Active tracker · UE S2MP2AR: -453.4 -> 1203.6Improved
add the LSTM sequence encoder (ablation)Active tracker · ViZDoom StandardAR: 1522 -> 2547Improved
replace LSTM with GRU (ablation)Active tracker · ViZDoom StandardAR: 2547 -> 2022No clear effect
add three more convolutional layers (deeper network) (ablation)Active tracker · ViZDoom StandardAR: 2547 -> 2535No clear effect
use end-to-end active tracker instead of passive tracker plus PID-like camera control (MIL)Active tracker · ViZDoom StandardEL: 743.1 -> 2959Improved
use end-to-end active tracker instead of Meanshift with camera controlActive tracker · UE S2MP2EL: 3000.0 -> 2565.3Mixed
use discrete 9-action space instead of continuous actions in real robot (ablation)Active tracker on TurtleBot · Real robot indoorSuccess rate: 0.7 -> 1.0Improved
use discrete 9-action space instead of continuous actions in real robot (ablation)Active tracker on TurtleBot · Real robot outdoorSuccess rate: 0.7 -> 0.9Improved
change target appearance, background or distractor at test timeActive tracker · ViZDoom FloorCeilingAR: 2547 -> 1504Hurt

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