Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks31 from public data
- 1,085
- 638
- 597
- 287
- 137
- 92
- Bilateral Functions for Global Motion Modeling87
This paper uses the bilateral domain to reformulate a piecewise smooth constraint as continuous global modeling constraint and demonstrates how the model can reliably obtain large numbers of good quality correspondences over wide baselines, while keeping outliers to a minimum.
- 78
- ImageSpirit72
This article proposes treating nouns as object labels and adjectives as visual attribute labels to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images, and proposes an efficient (interactive time) solution.
- 41
- Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems28
Relation Preserving Triplet Mining (RPTM) is introduced, a feature matching guided triplet mining scheme that ensures that triplets will respect the natural subgroupings within an object ID.
- Dual-SLAM: A framework for robust single camera navigation18
A Dual-SLAM framework is created that maintains real-time performance while being robust to local pose estimation failures, and can reduce failures by a dramatic 88%.
- 17
- 14
- Simultaneous Camera Pose and Correspondence Estimation with Motion Coherence14
An algorithm which jointly estimates camera pose and correspondence within a point set registration framework based on motion coherence, with the camera pose helping to localize the edge registration, while the “ambiguous” edge information helps to guide camera pose computation.
- Light Structure from Pin Motion: Geometric Point Light Source Calibration13
It is shown that shadow observations from a moving calibration target under a fixed light follow the principles of pinhole camera geometry and epipolar geometry, allowing joint recovery of the light position and3D shadow caster positions, equivalent to how conventional structure from motion jointly recovers camera parameters and 3D feature positions from observed 2D features.
- Dimensionality's Blessing: Clustering Images by Underlying Distribution13
Distribution-clustering, an elegant algorithm for grouping of data points by their (unknown) underlying distribution, creates notably clean clusters from raw unlabeled data, estimates the number of clusters for itself and is inherently robust to "outliers" which form their own clusters.
- 8
- Efficient velocity estimation for MAVs by fusing motion from two frontally parallel cameras7
A bio-inspired method that applies quasi-parallax technique to estimate the velocity of an MAV equipped with a forward-looking stereo camera without GPS, which can realize efficient metric velocity estimation without applying any depth information from either additional distance sensors or from stereopsis.
- Locally Varying Distance Transform for Unsupervised Visual Anomaly Detection6
A new embedding is proposed using a set of locally varying data projections, with each projection responsible for persever-ing the variations that distinguish a local cluster of instances from all other instances, while simultaneously allowing the probability that an instance belongs to a cluster to be statistically inferred from the one-dimensional, local projection associated with the cluster.
- 6
- Distance Based Image Classification: A solution to generative classification’s conundrum?4
This work proposes a new generative model in which semantic factors are accommodated by shell theory’s Wen-Yan et al. hierarchical generative process and non-semantic factors by an instance specific noise term, and uses the model to develop a classification scheme which suppresses the impact of noise while preserving semantic cues.
- 4
- An Analysis of Sketched IRLS for Accelerated Sparse Residual Regression3
It is shown that one of the most popular solution methods, iteratively reweighted least squares (IRLS), can be significantly accelerated by the use of matrix sketching and its effectiveness on a range of computer vision applications is shown.
- When Discrete Meets Differential3
It is shown that in practical small motion problems involving optical flow, these discrete structure from motion algorithms also provide better estimates than their differential counterparts, even when the motion magnitudes reach sub-pixel level.
- 2
- 2
- 1
- 1
- Image Matching Benchmark1
This work presents the first application-oriented image matching benchmark to facilitate the analysis of matching algorithms in application level and demonstrates the effectiveness of a simple technique which is readily pluggable into any matching system to improve performance.
- –
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 2026-10-11. 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.