AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

ROAD: The Road Event Awareness Dataset for Autonomous Driving

Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Valentina Fontana, Reza Javanmard Alitappeh, Salman Khan, Suman Saha, Kossar Jeddisaravi, Farzad Yousefi, Jacob Culley, Tom Nicholson, Jordan Omokeowa and 4 more

TPAMI 2022 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 114 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
replace 2D ResNet50 backbone with I3D (ablation)3D-RetinaNet · ROAD test, frame-level eventsframe-mAP (%): 12.8 -> 16.5Improved
replace I3D backbone with Slowfast (ablation)3D-RetinaNet · ROAD test, frame-level eventsframe-mAP (%): 16.5 -> 23.7Improved
replace I3D backbone with Slowfast (ablation)3D-RetinaNet · ROAD test, frame-level actionsframe-mAP (%): 25.4 -> 31.1Improved
replace 2D backbone with I3D (ablation)3D-RetinaNet · ROAD test, frame-level locationsframe-mAP (%): 30.8 -> 34.9Improved
increase test-time clip length from 8 to 32 frames (ablation)3D-RetinaNet 2D · ROAD test, frame-level agentsframe-mAP (%): 39.5 -> 39.8No clear effect
increase test-time clip length from 8 to 32 frames (ablation)3D-RetinaNet I3D · ROAD test, frame-level agentsframe-mAP (%): 39.5 -> 39.2No clear effect
increase test-time clip length from 8 to 32 frames (ablation)3D-RetinaNet Slowfast · ROAD test, frame-level agentsframe-mAP (%): 47.5 -> 43.7Hurt
use I3D backbone instead of 2D on UCF-101-24 (ablation)3D-RetinaNet · UCF-101-24 video-mAP@0.5video-mAP (%): 48.6 -> 58.2Improved
use I3D backbone instead of 2D on UCF-101-24 (ablation)3D-RetinaNet · UCF-101-24 f-mAPframe-mAP (%): 65.2 -> 75.2Improved
apply YOLOv5 instead of 3D-RetinaNet for agent detectionYOLOv5 · ROAD test, video-level delta=0.2 agentsvideo-mAP (%): 29.0 -> 43.3Improved
apply YOLOv5 instead of 3D-RetinaNet for agent detectionYOLOv5 · ROAD test, frame-level agentsframe-mAP (%): 47.5 -> 56.9Improved
move from UCF-101-24 to ROAD with the same I3D baseline3D-RetinaNet I3D · video-mAP at delta 0.5video-mAP (%): 58.2 -> 4.7Hurt

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