12 citations · 36 across the 26 of their papers we have counts for
30 papers
The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms
Lingdong Kong, Shaoyuan Xie, Zeying Gong +135
Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under…
STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
Christian Fruhwirth-Reisinger, Dušan Malić, Wei Lin +3
We introduce STSBench, a scenario-based framework to benchmark the holistic understanding of vision-language models (VLMs) for autonomous driving. The framework automatically mines…
Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation
Johannes Spoecklberger, Wei Lin, Pedro Hermosilla +3
Vision Foundation Models (VFMs) have become a de facto choice for many downstream vision tasks, like image classification, image segmentation, and object localization. However, the…
GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection
Dušan Malić, Christian Fruhwirth-Reisinger, Samuel Schulter +1
LiDAR-based 3D detectors need large datasets for training, yet they struggle to generalize to novel domains. Domain Generalization (DG) aims to mitigate this by training detectors…
LiSu: A Dataset and Method for LiDAR Surface Normal Estimation
Dušan Malić, Christian Fruhwirth-Reisinger, Samuel Schulter +1
While surface normals are widely used to analyse 3D scene geometry, surface normal estimation from LiDAR point clouds remains severely underexplored. This is caused by the lack of…
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
M. Jehanzeb Mirza, Mengjie Zhao, Zhuoyuan Mao +12
In this work, we propose GLOV, which enables Large Language Models (LLMs) to act as implicit optimizers for Vision-Language Models (VLMs) to enhance downstream vision tasks. GLOV p…
Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin +5
Prompt ensembling of Large Language Model (LLM) generated category-specific prompts has emerged as an effective method to enhance zero-shot recognition ability of Vision-Language M…
GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data
David Schinagl, Georg Krispel, Christian Fruhwirth-Reisinger +2
Widely-used LiDAR-based 3D object detectors often neglect fundamental geometric information readily available from the object proposals in their confidence estimation. This is most…
TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin +3
Vision and Language Models (VLMs), such as CLIP, have enabled visual recognition of a potentially unlimited set of categories described by text prompts. However, for the best visua…
Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
Stefan Leitner, M. Jehanzeb Mirza, Wei Lin +5
In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. However, their performance deteriorates significantly when te…
LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin +4
Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of…
TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering
Wei Lin, Anna Kukleva, Horst Possegger +2
Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming a…
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
Wei Lin, Leonid Karlinsky, Nina Shvetsova +6
Large scale Vision-Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. This enables remarkable progress in zero-shot…
Sparse Message Passing Network with Feature Integration for Online Multiple Object Tracking
Bisheng Wang, Horst Possegger, Horst Bischof +1
Existing Multiple Object Tracking (MOT) methods design complex architectures for better tracking performance. However, without a proper organization of input information, they stil…
MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds
Georg Krispel, David Schinagl, Christian Fruhwirth-Reisinger +2
The sensing process of large-scale LiDAR point clouds inevitably causes large blind spots, i.e. regions not visible to the sensor. We demonstrate how these inherent sampling proper…
Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses
Abhiram Kolli, Muhammad Jehanzeb Mirza, Horst Possegger +1
Keyless entry systems in cars are adopting neural networks for localizing its operators. Using test-time adversarial defences equip such systems with the ability to defend against…
Video Test-Time Adaptation for Action Recognition
Wei Lin, Muhammad Jehanzeb Mirza, Mateusz Kozinski +3
Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data…
ActMAD: Activation Matching to Align Distributions for Test-Time-Training
Muhammad Jehanzeb Mirza, Pol Jané Soneira, Wei Lin +3
Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. We propose to perform…
MATE: Masked Autoencoders are Online 3D Test-Time Learners
M. Jehanzeb Mirza, Inkyu Shin, Wei Lin +8
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring…
SAILOR: Scaling Anchors via Insights into Latent Object Representation
Dušan Malić, Christian Fruhwirth-Reisinger, Horst Possegger +1
LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towar…
An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
M. Jehanzeb Mirza, Marc Masana, Horst Possegger +1
Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When…
OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data
David Schinagl, Georg Krispel, Horst Possegger +2
While 3D object detection in LiDAR point clouds is well-established in academia and industry, the explainability of these models is a largely unexplored field. In this paper, we pr…
3D Human Pose Estimation Using Möbius Graph Convolutional Networks
Niloofar Azizi, Horst Possegger, Emanuele Rodolà +1
3D human pose estimation is fundamental to understanding human behavior. Recently, promising results have been achieved by graph convolutional networks (GCNs), which achieve state-…
CycDA: Unsupervised Cycle Domain Adaptation from Image to Video
Wei Lin, Anna Kukleva, Kunyang Sun +3
Although action recognition has achieved impressive results over recent years, both collection and annotation of video training data are still time-consuming and cost intensive. Th…