AI Paper Atlas

Research map / Detection and segmentation / Tracking

Multi-object Tracking with Neural Gating Using Bilinear LSTM

Chanho Kim, Fuxin Li, James M. Rehg

ECCV 2018 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 246 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 Bilinear LSTM instead of baseline architecture 1 (ablation)appearance gating network · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingIDF1: 51.28 -> 59.07Improved
use Bilinear LSTM instead of baseline architecture 2 (ablation)appearance gating network · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingIDF1: 51.49 -> 59.07Improved
use Bilinear LSTM instead of baseline 1, identity switches (ablation)appearance gating network · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingIDS: 412 -> 233Improved
use Bilinear LSTM instead of baseline 1, MOTA (ablation)appearance gating network · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingMOTA: 50.43 -> 52.33Improved
raise LSTM state dimension from 512 to 2048 (ablation)Bilinear LSTM · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingIDF1: 56.66 -> 59.07Improved
raise LSTM state dimension from 1024 to 2048 (ablation)Bilinear LSTM · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingIDF1: 55.85 -> 59.07Improved
raise LSTM state dimension from 512 to 2048 (ablation)Bilinear LSTM · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingMOTA: 52.14 -> 52.33No clear effect
increase max training sequence length from 10 to 40 (ablation)Bilinear LSTM · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingIDF1: 54.36 -> 59.07Improved
increase max training sequence length from 40 to 160 (ablation)Bilinear LSTM · MOT17 val (MOT17-09, -10), Faster R-CNN, appearance gatingIDF1: 59.07 -> 55.19Hurt
add re-ID pre-training to appearance gating (ablation)Bilinear LSTM (A) · MOT17 val (MOT17-09, -10), Faster R-CNN, Nmax=40IDF1: 57.46 -> 59.07Improved
add re-ID pre-training to motion+appearance gating (ablation)(M)+(A) LSTM · MOT17 val (MOT17-09, -10), Faster R-CNN, Nmax=40MOTA: 50.31 -> 52.63Improved
add missing detection augmentation to motion gating (ablation)Motion LSTM · MOT17 val (MOT17-09, -10), Faster R-CNN, Nmax=40IDF1: 47.71 -> 50.22Improved

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