Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks168 from public data
- DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection1,297
The proposed DRÆM method enables direct anomaly localization without the need for additional complicated post-processing of the network output and can be trained using simple and general anomaly simulations.
- 1,124
- The Visual Object Tracking VOT2015 Challenge Results902
The Visual Object Tracking challenge 2015, VOT2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and presents a new VOT 2015 dataset twice as large as in VOT2014 with full annotation of targets by rotated bounding boxes and per-frame attribute.
- The Sixth Visual Object Tracking VOT2018 Challenge Results804
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative; results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years.
- The Visual Object Tracking VOT2016 Challenge Results776
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
- Reconstruction by inpainting for visual anomaly detection769
The RIAD approach (RIAD) randomly removes partial image regions and reconstructs the image from partial inpaintings, thus addressing the drawbacks of auto-enocoding methods.
- A Novel Performance Evaluation Methodology for Single-Target Trackers667
The requirements are the basis of a new evaluation methodology that aims at a simple and easily interpretable tracker comparison and a fully-annotated dataset with per-frame annotations with several visual attributes, which is the largest benchmark to date.
- The Visual Object Tracking VOT2014 Challenge Results588
The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and introduces a new dataset with full annotation of targets by rotated bounding boxes and per-frame attribute.
- 496
- 434
- The Eighth Visual Object Tracking VOT2020 Challenge Results350
A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.
- 308
- D3S – A Discriminative Single Shot Segmentation Tracker299
Without per-dataset finetuning and trained only for segmentation as the primary output, D3S outperforms all trackers on VOT2016, VOT2018 and GOT-10k benchmarks and performs close to the state-of-the-artTrackers on the TrackingNet.
- Multivariate online kernel density estimation with Gaussian kernels211
This document includes some detailed supplemental derivations used in the bandwidth estimation for the online Kernel Density Estimator which was proposed in the paper \Multivariate Online Kernel D density Estimation with Gaussian Kernels.
- 203
- Fast Image-Based Obstacle Detection From Unmanned Surface Vehicles187
A new graphical model is proposed that affords a fast and continuous obstacle image-map estimation from a single video stream captured on board a USV, and outperforms the related approaches, while requiring a fraction of computational effort.
- Stereo obstacle detection for unmanned surface vehicles by IMU-assisted semantic segmentation166
A new obstacle detection algorithm for unmanned surface vehicles (USVs) is presented, which significantly outperforms the state of the art, with nearly 30% improvement in water-edge detection accuracy, an over 21% reduction of false positive rate, and an over 65% increase of true positive rate while its Matlab implementation runs in real-time.
- 162
- A trajectory-based analysis of coordinated team activity in a basketball game160
A probabilistic play model is applied to the player-trajectory data in order to segment the play into game phases (offense, defense, time out) and the activity is recognized by comparing its semantic description with the descriptions of manually defined templates, stored in a database.
- 145
- 139
- 130
- The Ninth Visual Object Tracking VOT2021 Challenge Results127
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative; results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years.
- A Bayes-spectral-entropy-based measure of camera focus using a discrete cosine transform117
A novel measure of camera focus based on the Bayes spectral entropy of an image spectrum, which outperformed the reference measures by exhibiting a wider working range and a smaller failure rate.
- Deformable Parts Correlation Filters for Robust Visual Tracking113
A new formulation of the constellation model with correlation filters that treats the geometric and visual constraints within a single convex cost function and derive a highly efficient optimization for maximum a posteriori inference of a fully connected constellation is presented.
- A Low-Shot Object Counting Network With Iterative Prototype Adaptation112
A Low-shot Object Counting network with iterative prototype Adaptation (LOCA) is proposed, which outperforms all recent state-of-the-art methods on FSC147 benchmark by 20-30% in RMSE on one-shot and few-shot and achieves state-of-the-art on zero-shot scenarios, while demonstrating better generalization capabilities.
- 107
- 105
- A Distractor-Aware Memory for Visual Object Tracking with SAM2102
It is argued that a more sophisticated memory model is required, and a new distractor-aware memory model for SAM2 and an introspection-based update strategy that jointly addresses the segmentation accuracy as well as tracking robustness are proposed.
- Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters98
The proposed long-term RGB-D tracker called OTR – Object Tracking by Reconstruction performs online 3D target reconstruction to facilitate robust learning of a set of view-specific discriminative correlation filters (DCFs).
- 92
- 91
- Histograms of optical flow for efficient representation of body motion88
A novel method for efficient encoding of human body motion, extracted from image sequences is presented, which could be applied both to verification of person identities due to minuscule differences in their motion, and to detection of unusual behavior, such as tailgating.
- CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark83
The CDTB dataset is the largest and most diverse dataset in RGB-D tracking, with an order of magnitude larger number of frames than related datasets, indicating a large gap between the two fields, which has not been previously detected by the prior benchmarks.
- Closed-world tracking of multiple interacting targets for indoor-sports applications81
The proposed tracker is based on multiple, single-player trackers, which are combined using a closed-world assumption about the interactions among players, which renders the tracking more robust and reduces the computational complexity of the tracker.
- FuCoLoT – A Fully-Correlational Long-Term Tracker77
The proposed FuCoLoT exploits the novel DCF constrained filter learning method to design a detector that is able to re-detect the target in the whole image efficiently and has an order of magnitude smaller memory footprint than its best-performing competitors and runs at 15 fps in a single CPU thread.
- The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results66
A significant general improvement of results has been observed, which partly compensate for the more difficult sequences introduced into the dataset in VOT-TIR2016.
- LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark63
The first maritime panoptic obstacle detection benchmark LaRS is presented, featuring scenes from Lakes, Rivers and Seas, and the new dataset boasts the largest diversity in recording locations, scene types, obstacle classes, and acquisition conditions among the related datasets.
- Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation60
A novel Depth-Aware Discrete Autoencoder (DADA) architecture is proposed, that enables learning a general discrete latent space that jointly models RGB and 3D data for 3D surface anomaly detection and proposes a new surface anomaly detection method 3DSR, which outperforms all existing state-of-theart on the challenging MVTec3D anomaly detection benchmark.
- 59
- 57
- 1 st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results48
A new benchmark is introduced, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage and is summarized in the report.
- Online kernel density estimation for interactive learning48
A Gaussian-kernel-based online kernel density estimation which can be used for applications of online probability density estimation and online learning and allows online adaptation from positive examples as well as from the negative examples.
- 46
- Self-Understanding and Self-Extension: A Systems and Representational Approach46
An architecture and a set of representations used in two robot systems that exhibit a limited degree of autonomous mental development are presented, which are term self-extension and include representations of gaps and uncertainty for specific kinds of knowledge.
- A local-motion-based probabilistic model for visual tracking42
The experiments show that the proposed local-motion model largely resolves situations when the target is occluded by, or moves in front of, a visually similar object.
- Wide-angle camera distortions and non-uniform illumination in mobile robot tracking41
The lens correction method successfully corrects the distortion caused by the camera lens, thus achieving a more accurate and precise estimation of object position, and the illumination compensation improves robustness to irregular and non-uniform illumination that is nearly always present in real conditions.
- 38
- A water-obstacle separation and refinement network for unmanned surface vehicles38
A new deep encoder-decoder architecture, a water-obstacle separation and refinement network (WaSR), is proposed, which outperforms the current state-of-the-art by a large margin, yielding a 14% increase in F-measure over the second-best method.
- 36
- 35
- 33
- 32
- 31
- 29
- 29
- 28
- 28
- 25
- 23
- Beyond Standard Benchmarks: Parameterizing Performance Evaluation in Visual Object Tracking23
This paper presents an approach that utilizes omnidirectional videos to generate realistic, consistently annotated, short-term tracking scenarios with exactly parameterized motion patterns, and provides an in-depth analysis of major tracking paradigms which is complementary to the standard benchmarks.
- 23
- 23
- 22
- 21
- 21
- 21
- 21
- The VOT2013 challenge: overview and additional results21
An overview of the VOT2013 challenge is provided, its main results are pointed out, and the additional previously unpublished experiments and results are documented.
- 20
- 20
- 19
- 19
- 19
- Towards deep compositional networks18
This work proposes a novel analytic model of a basic unit in a layered hierarchical model with both explicit compositional structure and a well-defined discriminative cost function, affording a straight-forward visualization of parts and faster inference due to separability of the units.
- 18
- 18
- 17
- 17
- 16
- 16
- CONTINUOUS LEARNING OF SIMPLE VISUAL CONCEPTS USING INCREMENTAL KERNEL DENSITY ESTIMATION16
This paper proposes a method for continuous learning of simple visual concepts that continuously associates words describing observed scenes with automatically extracted visual features with kernel density probability distribution estimates.
- 16
- 15
- 15
- 13
- 12
- 12
- Spatially-Adaptive Filter Units for Deep Neural Networks12
This paper proposes a novel displaced aggregation unit (DAU) that does not require hand-crafting, and extensively demonstrate the strength of DAUs on a classification and semantic segmentation tasks.
- 12
- 11
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 8
- Room Categorization Based on a Hierarchical Representation of Space8
This paper proposes a new compositional hierarchical representation of space that is based on learning statistically significant observations, in terms of the frequency of occurrence of various shapes in the environment, on a two-dimensional space.
- 7
- 6
- 6
- 6
- Adding discriminative power to a generative hierarchical compositional model using histograms of compositions6
The generative model of hierarchical compositions is combined with the discriminative descriptor by performing hypothesis verification of detections produced by the hierarchical compositional model and is compared against a state-of-the-art convolutional neural network and shown to outperform it under significant occlusions.
- 5
- 5
- 4
- 4
- Adding Discriminative Power to Hierarchical Compositional Models for Object Class Detection3
This paper proposes a novel approach that preserves the appealing properties of the generative hierarchical models, while at the same time improves their discrimination properties by introducing a network of discriminative nodes on top of the existing generative hierarchy.
- 2
- 2
- 2
- 2
- Learning part-based spatial models for laser-vision-based room categorization2
A new approach for room categorization that is based on two-dimensional laser range data and a new discriminative dictionary learning technique that is applied for part-dictionary selection in both laser-based and vision-based modalities are presented.
- A Web-Service for Object Detection Using Hierarchical Models2
This paper proposes an architecture for an object detection system suitable for a web-service running distributed on a cluster of machines and provides implementation details for running hierarchical models on top of a distributed platform and proposes an additional hypothesis verification step to reduce many false-positives that are common in hierarchical models.
- A basic cognitive system for interactive learning of simple visual concepts2
In this work, a system and underlying representations and mechanisms for continuous learning of visual concepts in dialogue with a human tutor are presented.
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.