Search results
The following articles are merged in Scholar. Their combined citations are counted only for the first article.
Focus on object interactions and influences, without object information, e.g. appearance. Light graph neural network made of 3/4-layer MLPs with fully connected layers (only 71k parameters). It is capable of near-real-time inference: 33 FPS on NuScenes and 170 FPS on KITTI.
Aleksandr Kim. Affiliation. Technical University of Munich. Publication Topics 2D Information,2D Object,3D Bounding Box,3D Detection,3D Information,3D Multi-object ...
Tracking? Aleksandr Kim(B), Guillem Bras ́o, Aljoˇsa Oˇsep, and Laura Leal-Taix ́e. Technical University of Munich, Munich, Germany. {aleksandr.kim,guillem.braso,aljosa.osep,leal.taixe}@tum.de. Abstract. Most (3D) multi-object tracking methods rely on appear-ance-based cues for data association.
How far can geometric relations take us in 3D multi-object tracking? Aleksandr Kim, Guillem Braso, Aljosa Osep, Laura Leal-Taixe. August 2022. Cite.
EagerMOT Public. Official code for "EagerMOT: 3D Multi-Object Tracking via Sensor Fusion" [ICRA 2021] Python 379 79. aleksandr.kim@tum.de . aleksandrkim61 has 8 repositories available. Follow their code on GitHub.
Aleksandr Kim, Guillem Brasó, Aljoša Ošep, Laura Leal-Taixé. Technical University of Munich, Germany {aleksandr.kim, guillem.braso, aljosa.osep, leal.taixe}@tum.de. Abstract. Most (3D) multi-object tracking methods rely on object-level information, e.g. appearance, for data association.
