Aljosa Osep

About Aljosa Osep

Aljosa Osep, With an exceptional h-index of 20 and a recent h-index of 19 (since 2020), a distinguished researcher at Technische Universität München, specializes in the field of Robot vision, open-world perception, multi-object tracking.

His recent articles reflect a diverse array of research interests and contributions to the field:

Better Call SAL: Towards Learning to Segment Anything in Lidar

SeMoLi: What Moves Together Belongs Together

Pix2map: Cross-modal retrieval for inferring street maps from images

Lidar Panoptic Segmentation and Tracking without Bells and Whistles

Walking your lidog: A journey through multiple domains for lidar semantic segmentation

Learning to discover and detect objects

Quo vadis: Is trajectory forecasting the key towards long-term multi-object tracking?

Directtracker: 3d multi-object tracking using direct image alignment and photometric bundle adjustment

Aljosa Osep Information

University

Position

Postdoc

Citations(all)

2660

Citations(since 2020)

2551

Cited By

563

hIndex(all)

20

hIndex(since 2020)

19

i10Index(all)

25

i10Index(since 2020)

24

Email

University Profile Page

Google Scholar

Aljosa Osep Skills & Research Interests

Robot vision

open-world perception

multi-object tracking

Top articles of Aljosa Osep

Better Call SAL: Towards Learning to Segment Anything in Lidar

arXiv preprint arXiv:2403.13129

2024/3/19

SeMoLi: What Moves Together Belongs Together

arXiv preprint arXiv:2402.19463

2024/2/29

Pix2map: Cross-modal retrieval for inferring street maps from images

2023

Lidar Panoptic Segmentation and Tracking without Bells and Whistles

2023/10/1

Walking your lidog: A journey through multiple domains for lidar semantic segmentation

2023

Learning to discover and detect objects

2022/10/19

Quo vadis: Is trajectory forecasting the key towards long-term multi-object tracking?

2022/10/14

Directtracker: 3d multi-object tracking using direct image alignment and photometric bundle adjustment

2022/10/23

Polarmot: How far can geometric relations take us in 3d multi-object tracking?

2022/10/23

Is geometry enough for matching in visual localization?

2022/10/23

Unsupervised class-agnostic instance segmentation of 3d lidar data for autonomous vehicles

IEEE Robotics and Automation Letters

2022/7/1

Text2pos: Text-to-point-cloud cross-modal localization

2022

Eagermot: 3d multi-object tracking via sensor fusion

2021/5/30

Motchallenge: A benchmark for single-camera multiple target tracking

International Journal of Computer Vision

2021/4

Step: Segmenting and tracking every pixel

NeurIPS Track on Datasets and Benchmarks, 2021

2021

Hota: A higher order metric for evaluating multi-object tracking

International journal of computer vision

2021/2

A single-stage, bottom-up approach for occluded vis using spatio-temporal embeddings

2021

Aljosa Osep
Aljosa Osep

H-Index: 11

Laura Leal-Taixé
Laura Leal-Taixé

H-Index: 24

See List of Professors in Aljosa Osep University(Technische Universität München)

Co-Authors

academic-engine