AI Paper Atlas

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

Detecting Invisible People

Tarasha Khurana, Achal Dave, Deva Ramanan

ICCV 2021 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 46 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 reporting of internal linear forecasts (ablation)DeepSORT · MOT-17 train (FRCNN)Occluded Top-5 F1: 28.4 -> 29.8Improved
add camera motion (egomotion) compensation (ablation)DeepSORT + Forecast · MOT-17 train (FRCNN)Occluded Top-5 F1: 29.8 -> 32.2Improved
add depth-based freespace filtering (ablation)DeepSORT + Forecast + Egomotion · MOT-17 train (FRCNN)Occluded Top-5 F1: 32.2 -> 35.7Improved
add depth-aware process noise (ablation)DeepSORT + Forecast + Egomotion + Freespace · MOT-17 train (FRCNN)Occluded Top-5 F1: 35.7 -> 39.8Improved
replace linear forecaster with SGAN or STGAT (ablation)Full pipeline · MOT-17 train (FRCNN)Occluded Top-5 F1: 39.8 -> 36.0 (SGAN); 39.8 -> 36.4 (STGAT)Hurt
replace MegaDepth with Mannequin Challenge depth (ablation)Pipeline without depth noise · MOT-17 train (FRCNN)Occluded Top-5 F1: 35.4 -> 34.2Hurt
replace MegaDepth with MIDAS depth at default resolution (ablation)Pipeline without depth noise · MOT-17 train (FRCNN)Occluded Top-5 F1: 35.4 -> 34.4Hurt
increase MIDAS input resolution from 1x to 3x (ablation)Pipeline with MIDAS depth · MOT-17 train (FRCNN)Occluded Top-5 F1: 34.4 -> 37.5Improved
use Mask R-CNN masks instead of boxes for average depth (ablation)Full pipeline · MOT-17 train (FRCNN)Occluded Top-5 F1: 39.8 -> 40.6Improved
apply method on top of existing trackersSix trackers on MOT-17 train · MOT-17 trainAll Top-5 F1: -0.3 (MIFT), -0.4 (CenterTrack), +0.3 (SDP)No clear effect
apply method on top of MIFTMIFT · MOT-17 testOccluded Top-5 F1: 38.4 -> 43.4Improved
apply method on top of Tracktor++Tracktor++ · MOT-20 testOccluded Top-5 F1: 44.2 -> 46.9Improved

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