Aljosa Osep

79 papers A* 23A 6Journal 41Unranked 8
YearRankTypeTitle / Venue / Authors
2026 J jnl
VGG-T
CoRR
Sven Elflein, Ruilong Li, Sérgio Agostinho, Zan Gojcic, Laura Leal-Taixé, Qunjie Zhou, Aljosa Osep
2025 J jnl
Lidar Panoptic Segmentation in an Open World.
Int. J. Comput. Vis.
Anirudh Srinivasan Chakravarthy, Meghana Reddy Ganesina, Peiyun Hu, Laura Leal-Taixé, Shu Kong, Deva Ramanan, Aljosa Osep
2025 J jnl
Native Segmentation Vision Transformers.
CoRR
Guillem Brasó, Aljosa Osep, Laura Leal-Taixé
2025 J jnl
SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding.
CoRR
Tanveer Hannan, Shuaicong Wu, Mark Weber, Suprosanna Shit, Jindong Gu, Rajat Koner, Aljosa Osep, Laura Leal-Taixé, Thomas Seidl
2025 A* conf
Towards Learning to Complete Anything in Lidar.
ICML
Ayça Takmaz, Cristiano Saltori, Neehar Peri, Tim Meinhardt, Riccardo de Lutio, Laura Leal-Taixé, Aljosa Osep
2025 J jnl
Towards Learning to Complete Anything in Lidar.
CoRR
Ayça Takmaz, Cristiano Saltori, Neehar Peri, Tim Meinhardt, Riccardo de Lutio, Laura Leal-Taixé, Aljosa Osep
2025 A* conf
Zero-Shot 4D Lidar Panoptic Segmentation.
CVPR
Yushan Zhang, Aljosa Osep, Laura Leal-Taixé, Tim Meinhardt
2025 J jnl
Zero-Shot 4D Lidar Panoptic Segmentation.
CoRR
Yushan Zhang, Aljosa Osep, Laura Leal-Taixé, Tim Meinhardt
2024 — conf
Better Call SAL: Towards Learning to Segment Anything in Lidar.
ECCV (39)
Aljosa Osep, Tim Meinhardt, Francesco Ferroni, Neehar Peri, Deva Ramanan, Laura Leal-Taixé
2024 J jnl
Better Call SAL: Towards Learning to Segment Anything in Lidar.
CoRR
Aljosa Osep, Tim Meinhardt, Francesco Ferroni, Neehar Peri, Deva Ramanan, Laura Leal-Taixé
2024 J jnl
Lidar Panoptic Segmentation in an Open World.
CoRR
Anirudh Srinivasan Chakravarthy, Meghana Reddy Ganesina, Peiyun Hu, Laura Leal-Taixé, Shu Kong, Deva Ramanan, Aljosa Osep
2024 A* conf
SeMoLi: What Moves Together Belongs Together.
CVPR
Jenny Seidenschwarz, Aljosa Osep, Francesco Ferroni, Simon Lucey, Laura Leal-Taixé
2024 J jnl
SeMoLi: What Moves Together Belongs Together.
CoRR
Jenny Seidenschwarz, Aljosa Osep, Francesco Ferroni, Simon Lucey, Laura Leal-Taixé
2023 A conf
Lidar Panoptic Segmentation and Tracking without Bells and Whistles.
IROS
Abhinav Agarwalla, Xuhua Huang, Jason Ziglar, Francesco Ferroni, Laura Leal-Taixé, James Hays, Aljosa Osep, Deva Ramanan
2023 J jnl
Lidar Panoptic Segmentation and Tracking without Bells and Whistles.
CoRR
Abhinav Agarwalla, Xuhua Huang, Jason Ziglar, Francesco Ferroni, Laura Leal-Taixé, James Hays, Aljosa Osep, Deva Ramanan
2023 A* conf
Pix2Map: Cross-Modal Retrieval for Inferring Street Maps from Images.
CVPR
Xindi Wu, KwunFung Lau, Francesco Ferroni, Aljosa Osep, Deva Ramanan
2023 J jnl
Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images.
CoRR
Xindi Wu, KwunFung Lau, Francesco Ferroni, Aljosa Osep, Deva Ramanan
2023 A* conf
Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation.
ICCV
Cristiano Saltori, Aljosa Osep, Elisa Ricci, Laura Leal-Taixé
2023 J jnl
Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation.
CoRR
Cristiano Saltori, Aljosa Osep, Elisa Ricci, Laura Leal-Taixé
2022 A conf
DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment.
IROS
Mariia Gladkova, Nikita Korobov, Nikolaus Demmel, Aljosa Osep, Laura Leal-Taixé, Daniel Cremers
2022 J jnl
DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment.
CoRR
Mariia Gladkova, Nikita Korobov, Nikolaus Demmel, Aljosa Osep, Laura Leal-Taixé, Daniel Cremers
2022 A* conf
Forecasting from LiDAR via Future Object Detection.
CVPR
Neehar Peri, Jonathon Luiten, Mengtian Li, Aljosa Osep, Laura Leal-Taixé, Deva Ramanan
2022 J jnl
Forecasting from LiDAR via Future Object Detection.
CoRR
Neehar Peri, Jonathon Luiten, Mengtian Li, Aljosa Osep, Laura Leal-Taixé, Deva Ramanan
2022 — conf
Is Geometry Enough for Matching in Visual Localization?
ECCV (10)
Qunjie Zhou, Sérgio Agostinho, Aljosa Osep, Laura Leal-Taixé
2022 J jnl
Is Geometry Enough for Matching in Visual Localization?
CoRR
Qunjie Zhou, Sérgio Agostinho, Aljosa Osep, Laura Leal-Taixé
2022 A* conf
Learning to Discover and Detect Objects.
NeurIPS
Vladimir Fomenko, Ismail Elezi, Deva Ramanan, Laura Leal-Taixé, Aljosa Osep
2022 J jnl
Learning to Discover and Detect Objects.
CoRR
Vladimir Fomenko, Ismail Elezi, Deva Ramanan, Laura Leal-Taixé, Aljosa Osep
2022 A* conf
Opening up Open World Tracking.
CVPR
Yang Liu, Idil Esen Zulfikar, Jonathon Luiten, Achal Dave, Deva Ramanan, Bastian Leibe, Aljosa Osep, Laura Leal-Taixé
2022 J jnl
PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
CoRR
Aleksandr Kim, Guillem Brasó, Aljosa Osep, Laura Leal-Taixé
2022 — conf
PolarMOT: How Far Can Geometric Relations Take us in 3D Multi-object Tracking?
ECCV (22)
Aleksandr Kim, Guillem Brasó, Aljosa Osep, Laura Leal-Taixé
2022 A* conf
Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?
NeurIPS
Patrick Dendorfer, Vladimir Yugay, Aljosa Osep, Laura Leal-Taixé
2022 J jnl
Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?
CoRR
Patrick Dendorfer, Vladimir Yugay, Aljosa Osep, Laura Leal-Taixé
2022 A* conf
Text2Pos: Text-to-Point-Cloud Cross-Modal Localization.
CVPR
Manuel Kolmet, Qunjie Zhou, Aljosa Osep, Laura Leal-Taixé
2022 J jnl
Text2Pos: Text-to-Point-Cloud Cross-Modal Localization.
CoRR
Manuel Kolmet, Qunjie Zhou, Aljosa Osep, Laura Leal-Taixé
2022 J jnl
Unsupervised Class-Agnostic Instance Segmentation of 3D LiDAR Data for Autonomous Vehicles.
IEEE Robotics Autom. Lett.
Lucas Nunes, Xieyuanli Chen, Rodrigo Marcuzzi, Aljosa Osep, Laura Leal-Taixé, Cyrill Stachniss, Jens Behley
2021 A* conf
(Just) A Spoonful of Refinements Helps the Registration Error Go Down.
ICCV
Sérgio Agostinho, Aljosa Osep, Alessio Del Bue, Laura Leal-Taixé
2021 J jnl
(Just) A Spoonful of Refinements Helps the Registration Error Go Down.
CoRR
Sérgio Agostinho, Aljosa Osep, Alessio Del Bue, Laura Leal-Taixé
2021 A* conf
4D Panoptic LiDAR Segmentation.
CVPR
Mehmet Aygun, Aljosa Osep, Mark Weber, Maxim Maximov, Cyrill Stachniss, Jens Behley, Laura Leal-Taixé
2021 J jnl
4D Panoptic LiDAR Segmentation.
CoRR
Mehmet Aygün, Aljosa Osep, Mark Weber, Maxim Maximov, Cyrill Stachniss, Jens Behley, Laura Leal-Taixé
2021 — conf
A Single-Stage, Bottom-up Approach for Occluded VIS using Spatio-temporal Embeddings.
ICCVW
Ali Athar, Sabarinath Mahadevan, Aljosa Osep, Laura Leal-Taixé, Bastian Leibe
2021 A* conf
EagerMOT: 3D Multi-Object Tracking via Sensor Fusion.
ICRA
Aleksandr Kim, Aljosa Osep, Laura Leal-Taixé
2021 J jnl
EagerMOT: 3D Multi-Object Tracking via Sensor Fusion.
CoRR
Aleksandr Kim, Aljosa Osep, Laura Leal-Taixé
2021 J jnl
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking.
Int. J. Comput. Vis.
Jonathon Luiten, Aljosa Osep, Patrick Dendorfer, Philip H. S. Torr, Andreas Geiger, Laura Leal-Taixé, Bastian Leibe
2021 J jnl
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking.
Int. J. Comput. Vis.
Patrick Dendorfer, Aljosa Osep, Anton Milan, Konrad Schindler, Daniel Cremers, Ian Reid, Stefan Roth, Laura Leal-Taixé
2021 A* conf
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
ICCV
Matteo Fabbri, Guillem Brasó, Gianluca Maugeri, Orcun Cetintas, Riccardo Gasparini, Aljosa Osep, Simone Calderara, Laura Leal-Taixé, Rita Cucchiara
2021 J jnl
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
CoRR
Matteo Fabbri, Guillem Brasó, Gianluca Maugeri, Orcun Cetintas, Riccardo Gasparini, Aljosa Osep, Simone Calderara, Laura Leal-Taixé, Rita Cucchiara
2021 J jnl
Opening up Open-World Tracking.
CoRR
Yang Liu, Idil Esen Zulfikar, Jonathon Luiten, Achal Dave, Aljosa Osep, Deva Ramanan, Bastian Leibe, Laura Leal-Taixé
2021 — conf
STEP: Segmenting and Tracking Every Pixel.
NeurIPS Datasets and Benchmarks
Mark Weber, Jun Xie, Maxwell D. Collins, Yukun Zhu, Paul Voigtlaender, Hartwig Adam, Bradley Green, Andreas Geiger, Bastian Leibe, Daniel Cremers, Aljosa Osep, Laura Leal-Taixé, Liang-Chieh Chen
2021 J jnl
STEP: Segmenting and Tracking Every Pixel.
CoRR
Mark Weber, Jun Xie, Maxwell D. Collins, Yukun Zhu, Paul Voigtlaender, Hartwig Adam, Bradley Green, Andreas Geiger, Bastian Leibe, Daniel Cremers, Aljosa Osep, Laura Leal-Taixé, Liang-Chieh Chen
2020 A* conf
4D Generic Video Object Proposals.
ICRA
Aljosa Osep, Paul Voigtlaender, Mark Weber, Jonathon Luiten, Bastian Leibe
2020 — conf
Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation.
ACCV (2)
Patrick Dendorfer, Aljosa Osep, Laura Leal-Taixé
2020 J jnl
Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation.
CoRR
Patrick Dendorfer, Aljosa Osep, Laura Leal-Taixé
2020 J jnl
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking.
CoRR
Jonathon Luiten, Aljosa Osep, Patrick Dendorfer, Philip H. S. Torr, Andreas Geiger, Laura Leal-Taixé, Bastian Leibe
2020 A* conf
How to Train Your Deep Multi-Object Tracker.
CVPR
Yihong Xu, Aljosa Osep, Yutong Ban, Radu Horaud, Laura Leal-Taixé, Xavier Alameda-Pineda
2020 J jnl
MOTChallenge: A Benchmark for Single-camera Multiple Target Tracking.
CoRR
Patrick Dendorfer, Aljosa Osep, Anton Milan, Konrad Schindler, Daniel Cremers, Ian D. Reid, Stefan Roth, Laura Leal-Taixé
2020 A conf
Making a Case for 3D Convolutions for Object Segmentation in Videos.
BMVC
Sabarinath Mahadevan, Ali Athar, Aljosa Osep, Laura Leal-Taixé, Bastian Leibe, Sebastian Hennen
2020 J jnl
Making a Case for 3D Convolutions for Object Segmentation in Videos.
CoRR
Sabarinath Mahadevan, Ali Athar, Aljosa Osep, Sebastian Hennen, Laura Leal-Taixé, Bastian Leibe
2020 — conf
STEm-Seg: Spatio-Temporal Embeddings for Instance Segmentation in Videos.
ECCV (11)
Ali Athar, Sabarinath Mahadevan, Aljosa Osep, Laura Leal-Taixé, Bastian Leibe
2020 J jnl
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos.
CoRR
Ali Athar, Sabarinath Mahadevan, Aljosa Osep, Laura Leal-Taixé, Bastian Leibe
2019 J jnl
4D Generic Video Object Proposals.
CoRR
Aljosa Osep, Paul Voigtlaender, Mark Weber, Jonathon Luiten, Bastian Leibe
2019 — conf
AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects.
3DV
Johannes Groß, Aljosa Osep, Bastian Leibe
2019 J jnl
AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects.
CoRR
Johannes Groß, Aljosa Osep, Bastian Leibe
2019 A* conf
Large-Scale Object Mining for Object Discovery from Unlabeled Video.
ICRA
Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe
2019 J jnl
Large-Scale Object Mining for Object Discovery from Unlabeled Video.
CoRR
Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe
2019 A* conf
MOTS: Multi-Object Tracking and Segmentation.
CVPR
Paul Voigtlaender, Michael Krause, Aljosa Osep, Jonathon Luiten, Berin Balachandar Gnana Sekar, Andreas Geiger, Bastian Leibe
2019 J jnl
MOTS: Multi-Object Tracking and Segmentation.
CoRR
Paul Voigtlaender, Michael Krause, Aljosa Osep, Jonathon Luiten, Berin Balachandar Gnana Sekar, Andreas Geiger, Bastian Leibe
2019 — —
Vision-based category agnostic object tracking for mobile robots and intelligent vehicles / Aljose Osep ; Bastian Leibe, David Held.
Aljosa Osep
2018 J jnl
Combined Image- and World-Space Tracking in Traffic Scenes.
CoRR
Aljosa Osep, Wolfgang Mehner, Markus Mathias, Bastian Leibe
2018 J jnl
Towards Large-Scale Video Video Object Mining.
CoRR
Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe
2018 A* conf
Track, Then Decide: Category-Agnostic Vision-Based Multi-Object Tracking.
ICRA
Aljosa Osep, Wolfgang Mehner, Paul Voigtlaender, Bastian Leibe
2017 A* conf
Combined image- and world-space tracking in traffic scenes.
ICRA
Aljosa Osep, Wolfgang Mehner, Markus Mathias, Bastian Leibe
2017 J jnl
Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video.
CoRR
Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe
2017 J jnl
Track, then Decide: Category-Agnostic Vision-based Multi-Object Tracking.
CoRR
Aljosa Osep, Wolfgang Mehner, Paul Voigtlaender, Bastian Leibe
2016 A* conf
Multi-scale object candidates for generic object tracking in street scenes.
ICRA
Aljosa Osep, Alexander Hermans, Francis Engelmann, Dirk Klostermann, Markus Mathias, Bastian Leibe
2016 A conf
Scene flow propagation for semantic mapping and object discovery in dynamic street scenes.
IROS
Deyvid Kochanov, Aljosa Osep, Jörg Stückler, Bastian Leibe
2016 A conf
Unsupervised Learning of Shape-Motion Patterns for Objects in Urban Street Scenes.
BMVC
Dirk Klostermann, Aljosa Osep, Jörg Stückler, Bastian Leibe
2015 A* conf
A fixed-dimensional 3D shape representation for matching partially observed objects in street scenes.
ICRA
Dennis Mitzel, Jasper Diesel, Aljosa Osep, Umer Rafi, Bastian Leibe
2013 A* conf
Multi-view Normal Field Integration for 3D Reconstruction of Mirroring Objects.
ICCV
Michael Weinmann, Aljosa Osep, Roland Ruiters, Reinhard Klein
2012 A conf
Fusing Structured Light Consistency and Helmholtz Normals for 3D Reconstruction.
BMVC
Michael Weinmann, Roland Ruiters, Aljosa Osep, Christopher Schwartz, Reinhard Klein