3つの要点 ✔️ End-to-Endのテキスト制御物体検出モデルの提案 ✔️ マルチモーダルタスクにおいてEnd-to-Endでの検出達成 ✔️ ダウンストリームタスクでも性能発揮 MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding written by Aishwarya Kamath, Mannat Singh, Yann LeCun, Ishan Misra, Gabriel Synnaeve, Nicolas Carion (Submitted on 26 Apr 2021) Comments: Accepted by ICCV2021 oral Subjects: Computer Vision and Pattern Recognition (cs.CV); Computation and