AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Social-Implicit: Rethinking Trajectory Prediction Evaluation and the Effectiveness of Implicit Maximum Likelihood Estimation

Abduallah Mohamed, Deyao Zhu, Warren Vu, Mohamed Elhoseiny, Christian Claudel

ECCV 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Probabilistic calibration · 108 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 Social-Zones (ablation)Social-Implicit · ETH/UCYAMD/AMV: 1.16 -> 0.90Improved
add triplet, geometric distance and angle losses on top of zones (ablation)Social-Implicit · ETH/UCYAMD/AMV: 1.07 -> 0.90Improved
add geometric distance loss to triplet loss with zones (ablation)Social-Implicit · ETH/UCYAMD/AMV: 1.03 -> 1.11Hurt
add geometric angle loss to triplet loss with zones (ablation)Social-Implicit · ETH/UCYAMD/AMV: 1.03 -> 0.97Improved
add triplet loss to Zones (ablation)Social-Implicit · ETH/UCYAMD/AMV: 1.07 -> 1.03Improved
increase number of zones from 1 to 4 (1.2 m/s top zone) (ablation)Social-Implicit · ETH/UCYAMD/AMV: 1.16 -> 0.90Improved
set last zone speed at 0.6 m/s instead of 1.2 m/s (ablation)Social-Implicit · ETH/UCYAMD/AMV: 0.90 -> 1.19Hurt
use 2 zones instead of 1 (ablation)Social-Implicit · ETH/UCYAMD/AMV: 1.16 -> 1.20No clear effect
shift predicted samples by 10 cmSocial-Implicit and baselines · ETH/UCYBoN ADE/FDENo clear effect
evaluate with AMD/AMV instead of ADE/FDETrajectron++ vs ExpertTraj · ETH/UCYAMD: 1.84 -> 38.4Mixed
train with IMLE (Social-Implicit) vs larger baselinesSocial-Implicit · ETH/UCYparameters: 323.3k -> 5.8KImproved
Social-Implicit vs DAG-NetSocial-Implicit · SDDKDE: 1.76 -> 3.89Hurt

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