AI Paper Atlas

Research map / Detection and segmentation / Tracking

Type-to-Track: Retrieve Any Object via Prompt-based Tracking

Pha Nguyen, Kha Gia Quach, Kris M. Kitani, Khoa Luu

NeurIPS 2023 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 9 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 two-stage MDETR+TrackFormer with single-stage MENDERMENDER · GroOT TAO, retr promptsCA-MOTA: 25.70 -> 32.90Improved
replace two-stage MDETR+TrackFormer with MENDERMENDER · GroOT MOT17, cap promptsCA-MOTA: 44.80 -> 59.50Improved
replace two-stage baseline with MENDERMENDER · GroOT MOT17, def promptsFPS: 2.2 -> 10.3Improved
replace two-stage baseline with MENDERMENDER · GroOT TAO, def promptsCA-MOTA: 14.60 -> 16.80Improved
use simplified correlation instead of full third-order tensor (ablation)MENDER · GroOT MOT17, cap promptsFPS: 3.4 -> 7.8Improved
use simplified correlation instead of full third-order tensor (ablation)MENDER · GroOT TAO, retr promptsFPS: 7.6 -> 11.5Improved
use simplified correlation instead of full tensor (ablation)MENDER · GroOT MOT17, cap promptsCA-MOTA: 58.20 -> 59.50Improved
use simplified correlation instead of full tensor (ablation)MENDER · GroOT TAO, retr promptsCA-MOTA: 32.40 -> 32.90Improved
use simplified correlation instead of full tensor (ablation)MENDER · GroOT MOT20, def promptsCA-MOTA: 72.90 -> 72.10Hurt
use simplified correlation instead of full tensor (ablation)MENDER · GroOT MOT17, cap promptsMT: 289 -> 201Hurt
use detailed captions (cap) instead of category definitions (def) as promptMENDER · GroOT MOT17CA-MOTA: 67.30 -> 59.50Hurt
use detailed captions (cap) instead of category definitions (def) as promptMENDER · GroOT TAOCA-MOTA: 16.80 -> 20.70Improved

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