Search Results for author:
Found 40 papers, 25 papers with code
Human-in-the-Loop Segmentation of Multi-species Coral Imagery
For extremely sparsely labeled images, we propose a labeling regime based on human-in-the-loop principles, resulting in significant improvement in annotation efficiency: If only 5 point labels per image are available, our proposed human-in-the-loop approach improves on the state-of-the-art by 17. 3% for pixel accuracy and 22. 6% for mIoU; and by 10. 6% and 19. 1% when 10 point labels per image are available.
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning
We propose KYN, a novel method for single-view scene reconstruction that reasons about semantic and spatial context to predict each point's density.
Enhancing Visual Place Recognition via Fast and Slow Adaptive Biasing in Event Cameras
Event cameras are increasingly popular in robotics due to their beneficial features, such as low latency, energy efficiency, and high dynamic range.
CR3DT: Camera-RADAR Fusion for 3D Detection and Tracking
Accurate detection and tracking of surrounding objects is essential to enable self-driving vehicles.
Racing With ROS 2 A Navigation System for an Autonomous Formula Student Race Car
The advent of autonomous vehicle technologies has significantly impacted various sectors, including motorsport, where Formula Student and Formula: Society of Automotive Engineers introduced autonomous racing classes.
Applications of Spiking Neural Networks in Visual Place Recognition
Lastly, we investigate the role of sequence matching in SNN-based VPR, a technique where consecutive images are used to refine place recognition.
FocusTune: Tuning Visual Localization through Focus-Guided Sampling
We propose FocusTune, a focus-guided sampling technique to improve the performance of visual localization algorithms.
R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras
We propose R3D3, a multi-camera system for dense 3D reconstruction and ego-motion estimation.
OVTrack: Open-Vocabulary Multiple Object Tracking
This leaves contemporary MOT methods limited to a small set of pre-defined object categories.
NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems
The NeuroBench framework introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent (algorithm track) and hardware-dependent (system track) settings.
Visual Place Recognition: A Tutorial
It unifies the terminology of VPR and complements prior research in two important directions: 1) It provides a systematic introduction for newcomers to the field, covering topics such as the formulation of the VPR problem, a general-purpose algorithmic pipeline, an evaluation methodology for VPR approaches, and the major challenges for VPR and how they may be addressed.
Image Labels Are All You Need for Coarse Seagrass Segmentation
Our method outperforms previous approaches that require patch-level labels on the multi-species 'DeepSeagrass' dataset by 6. 8% (absolute) for the class-weighted F1 score, and by 12. 1% (absolute) for the seagrass presence/absence F1 score on the 'Global Wetlands' dataset.
CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion
To track the 3D locations and trajectories of the other traffic participants at any given time, modern autonomous vehicles are equipped with multiple cameras that cover the vehicle's full surroundings.
Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique
One recent promising approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques using methods such as SRAL and multi-process fusion.
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking
In this paper, we present Quasi-Dense Similarity Learning, which densely samples hundreds of object regions on a pair of images for contrastive learning.
Ranked #4 on
Multiple Object Tracking
on BDD100K test
Ensembles of Compact, Region-specific & Regularized Spiking Neural Networks for Scalable Place Recognition
We evaluate this new scalable modular system on benchmark localization datasets Nordland and Oxford RobotCar, with comparisons to standard techniques NetVLAD, DenseVLAD, and SAD, and a previous spiking neural network system.
SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection
We address the problem of out-of-distribution (OOD) detection for the task of object detection.
How Many Events do You Need? Event-based Visual Place Recognition Using Sparse But Varying Pixels
Event cameras continue to attract interest due to desirable characteristics such as high dynamic range, low latency, virtually no motion blur, and high energy efficiency.
Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery
We propose a point label aware method for propagating labels within superpixel regions to obtain augmented ground truth for training a semantic segmentation model.
Hyperdimensional Feature Fusion for Out-Of-Distribution Detection
We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Unsupervised Complementary-aware Multi-process Fusion for Visual Place Recognition
A recent approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques simultaneously.
Ambiguities in Direction-of-Arrival Estimation with Linear Arrays
Our approach uses Young tableaux for which a submatrix of the steering matrix has a vanishing determinant, which can be expressed through vanishing sums of unit roots.
Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments
Spiking neural networks (SNNs) offer both compelling potential advantages, including energy efficiency and low latencies and challenges including the non-differentiable nature of event spikes.
Bio-inspired robot perception coupled with robot-modeled human perception
My overarching research goal is to provide robots with perceptional abilities that allow interactions with humans in a human-like manner.
Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness
Probabilistic state-estimation approaches offer a principled foundation for designing localization systems, because they naturally integrate sequences of imperfect motion and exteroceptive sensor data.
Monocular Quasi-Dense 3D Object Tracking
Experiments on our proposed simulation data and real-world benchmarks, including KITTI, nuScenes, and Waymo datasets, show that our tracking framework offers robust object association and tracking on urban-driving scenarios.
Ranked #7 on
Multiple Object Tracking
on KITTI Tracking test
Where is your place, Visual Place Recognition?
Visual Place Recognition (VPR) is often characterized as being able to recognize the same place despite significant changes in appearance and viewpoint.
Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
Visual Place Recognition is a challenging task for robotics and autonomous systems, which must deal with the twin problems of appearance and viewpoint change in an always changing world.
Ranked #1 on
Visual Localization
on RobotCar Seasons v2
Intelligent Reference Curation for Visual Place Recognition via Bayesian Selective Fusion
A key challenge in visual place recognition (VPR) is recognizing places despite drastic visual appearance changes due to factors such as time of day, season, weather or lighting conditions.
Constraining the onset density of the hadron-quark phase transition with gravitational-wave observations
The softening of the EoS by the PT at higher densities, i. e. after merging, leads to a characteristic increase of the dominant postmerger GW frequency f_peak relative to the tidal deformability Lambda inferred during the premerger inspiral phase.
High Energy Astrophysical Phenomena High Energy Physics - Phenomenology Nuclear Theory
Event-based visual place recognition with ensembles of temporal windows
Event cameras are bio-inspired sensors capable of providing a continuous stream of events with low latency and high dynamic range.
RT-BENE: A Dataset and Baselines for Real-Time Blink Estimation in Natural Environments
We further incorporate our proposed RT-BENE baselines in the recently presented RT-GENE gaze estimation framework where it provides a real-time inference of the openness of the eyes.
Ranked #1 on
Blink estimation
on RT-BENE
Track to Reconstruct and Reconstruct to Track
Object tracking and 3D reconstruction are often performed together, with tracking used as input for reconstruction.
Improved axion emissivity from a supernova via nucleon-nucleon bremsstrahlung
We find that the axion emissivity is reduced by over an order of magnitude with respect to the basic OPE calculation, after all these effects are accounted for.
High Energy Physics - Phenomenology Solar and Stellar Astrophysics
RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments
We first record a novel dataset of varied gaze and head pose images in a natural environment, addressing the issue of ground truth annotation by measuring head pose using a motion capture system and eye gaze using mobile eyetracking glasses.
Ranked #1 on
Gaze Estimation
on RT-GENE
Context-aware Deep Feature Compression for High-speed Visual Tracking
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers.
Ranked #15 on
Visual Object Tracking
on VOT2017/18
Attentional Correlation Filter Network for Adaptive Visual Tracking
We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency.
DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self
This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot.
Kinematic Structure Correspondences via Hypergraph Matching
In this paper, we present a novel framework for finding the kinematic structure correspondence between two objects in videos via hypergraph matching.
Revisiting the SN1987A gamma-ray limit on ultralight axion-like particles
We revise the bound from the supernova SN1987A on the coupling of ultralight axion-like particles (ALPs) to photons.
High Energy Astrophysical Phenomena High Energy Physics - Phenomenology
