Aljosa Osep
20 papers · 2013–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (5) π Academic Marathon (12) π Conference Polyglot (5) πΊοΈ Taxonomy Completionist (33)
π
Conference Polyglot
(5)
π
Academic Marathon
(12)
π
Interdisciplinary Bridge
π€
Dynamic Duo
(17)
π₯
Unstoppable
(7)
π
Century Club
(20)
π
Conference Pioneer
ποΈ
Keyword Collector
(84)
β‘
Prolific Year
(7)
β
The Questioner
(4)
Conferences
CVPR (9)
ECCV (4)
ICCV (4)
NIPS (2)
ICML (1)
Top co-authors
Keywords
multi-object tracking
(5)
object detection
(4)
instance segmentation
(2)
point cloud
(2)
semantic segmentation
(2)
autonomous driving
(2)
3d vision
(2)
visual localization
(2)
iterative optimization
(1)
point cloud registration
(1)
semi-supervised learning
(1)
3d reconstruction
(1)
motion estimation
(1)
cross-domain learning
(1)
visual similarity
(1)
motion forecasting
(1)
video segmentation
(1)
trajectory prediction
(1)
cross-modal learning
(1)
scene understanding
(1)
Papers
Towards Learning to Complete Anything in Lidar
ICML 2025
Zero-Shot 4D Lidar Panoptic Segmentation
CVPR 2025
SeMoLi: What Moves Together Belongs Together
CVPR 2024
Better Call SAL: Towards Learning to Segment Anything in Lidar
ECCV 2024
Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation
ICCV 2023
Pix2map: Cross-Modal Retrieval for Inferring Street Maps From Images
CVPR 2023
Opening Up Open World Tracking
CVPR 2022
Forecasting From LiDAR via Future Object Detection
CVPR 2022
Is Geometry Enough for Matching in Visual Localization?
ECCV 2022
PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
ECCV 2022
Text2Pos: Text-to-Point-Cloud Cross-Modal Localization
CVPR 2022
Learning to Discover and Detect Objects
NIPS 2022
Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?
NIPS 2022
(Just) A Spoonful of Refinements Helps the Registration Error Go Down
ICCV 2021
4D Panoptic LiDAR Segmentation
CVPR 2021
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
ICCV 2021
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
ECCV 2020
How to Train Your Deep Multi-Object Tracker
CVPR 2020
MOTS: Multi-Object Tracking and Segmentation
CVPR 2019
Multi-view Normal Field Integration for 3D Reconstruction of Mirroring Objects
ICCV 2013