AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Context-Aware Streaming Perception in Dynamic Environments

Gur-Eyal Sela, Ionel Gog, Justin Wong, Kumar Krishna Agrawal, Xiangxi Mo, Sukrit Kalra, Peter Schafhalter, Eric Leong, Xin Wang, Bharathan Balaji, Joseph Gonzalez, Ion Stoica

ECCV 2022 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 10 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 Octopus context-based dynamic policy instead of global best static policystreaming tracking pipeline · WaymoS-MOTA: 25.1 -> 27.0Improved
use Octopus context-based dynamic policy instead of global best static policystreaming tracking pipeline · ArgoverseS-MOTA: 49.4 -> 51.1Improved
use Octopus with ground truth features from current segment instead of prediction from previous segment (ablation)Octopus · WaymoS-MOTA: 27.0 -> 27.9Improved
use Octopus with ground truth features from current segment instead of prediction from previous segment (ablation)Octopus · ArgoverseS-MOTA: 51.1 -> 53.2Improved
dynamically change the detection model only (ablation)global best policy · WaymoS-MOTA: 25.1 -> 27.6Improved
dynamically change tracking max age only (ablation)global best policy · WaymoS-MOTA: 25.1 -> 25.6Improved
dynamically change both detection model and tracking max age (ablation)global best policy · WaymoS-MOTA: 25.1 -> 27.9Improved
allow tracking maximum age to change in addition to detection model (ablation)optimal dynamic policy · opportunity gapS-MOTA: 28.3 -> 30.1Improved
allow tracking re-init frequency, min IOU and confidence threshold to change as well (ablation)optimal dynamic policy · opportunity gapS-MOTA: 30.1 -> 31.3Improved
remove baseline subtraction from regression targets (ablation)Octopus regression · WaymoS-MOTA: 27.9 -> 27.6Hurt
use independent classification instead of regression to rank configurations (ablation)Octopus · WaymoS-MOTA: 27.9 -> 27.2Hurt
use CNN based policy instead of engineered features with random forest (ablation)policy model · WaymoS-MOTA: 27.9 -> 25.2Hurt

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