Automatic video modification to hide faces while maintaining pose, illumination, and expression.
problem Face de-identification in video to protect identities.
method A novel feed-forward encoder-decoder network architecture conditioned on facial image high-level representation.
result Fully automatic video modification at high frame rates with minimal distortion.
Optimizes UAV deployment for VLC-enabled UAVs considering illumination distribution.
problem Optimizing UAV deployment for VLC-enabled UAVs with illumination distribution consideration.
method Formulated as an optimization problem, solved using GRUs and Gaussian mixture model.
result Achieves up to 22.1% reduction in transmit power compared to conventional methods.
Bayesian quadrature improves numerical efficiency and uncertainty representation.
problem Computing integrals of multiple related functions efficiently and accurately.
method Extending Bayesian quadrature to handle multiple related functions, proving convergence rates.
result The method provides increased numerical efficiency and more faithful uncertainty representation.
New illumination bodies defined for ball-convex shapes, proving convexity and establishing surface area measures.
problem Characterizing properties of ball-convex shapes.
method Introducing illumination bodies and weighted illumination bodies, proving convexity, and establishing surface area measures.
result Illumination bodies are convex and provide surface area measures for ball-convex shapes.
Extends illumination bodies to non-Euclidean spaces and proves their volume derivative defines surface area.
problem Defining surface area in non-Euclidean geometries.
method Generalizes illumination bodies to Riemannian spaces of constant curvature and projective Finsler geometries, proving their volume derivative defines surface area.
result Derivative of volume of illumination bodies defines surface area in non-Euclidean geometries.
Prove a generalization of Werner's formula for the volume of illumination bodies on Riemannian manifolds.
problem Prove a generalization of Werner's formula for the volume of illumination bodies on Riemannian manifolds.
method Define the δ-illumination body and prove a generalization of Werner's formula. result Prove a generalization of Werner's formula for the volume of illumination bodies on Riemannian manifolds.
The paper derives inequalities on Finsler manifolds, influenced by their curvatures.
problem Deriving inequalities on Finsler manifolds.
method Local and global geometric inequalities on Riemannian and Finsler manifolds.
result Generalized Caffarelli-Kohn-Nirenberg and Hardy type inequalities on Finsler manifolds.
Automatically infers high dynamic range illumination from a single indoor photo.
problem Predicting accurate indoor illumination from a single image.
method End-to-end deep neural network trained in three steps: lighting classifier, scene light localization, and fine-tuning for intensity prediction.
result Significantly outperforms previous methods in recovering high-quality HDR illumination.
Study shows non-orientable manifolds restrict signature-changing metrics globally.
problem Global obstructions to signature-changing metrics on non-orientable manifolds.
method Explicit geometric constructions based on Möbius strip topology.
result Radical of signature-changing metrics cannot be everywhere transverse.
SAIL reduces design evaluations, producing diverse high-performing designs.
problem Design optimization requires many evaluations, limiting applicability.
method Surrogate-Assisted Illumination (SAIL) uses surrogate modeling.
result SAIL produces hundreds of diverse high-performing designs with fewer evaluations.
For a Veech surface (x,ω), we characterize subspaces of X^n, invariant under the diagonal action of the affine group of X. We prove that non-arithmetic Veech surfaces have only finitely many invariant subspaces of very particular shape (in any dimension). Among other consequences we find copies of (X,ω) embedded in the…
Efficient model for foggy scene understanding in vehicles.
problem Challenging scene understanding and segmentation under foggy conditions.
method Domain adaptation and illumination-invariant image transformation.
result Outperforms state-of-the-art models in foggy scene understanding.
Enhances 2D face recognition with 3D features using active illumination.
problem Improving robustness of 2D face recognition to spoofing attacks and low-light conditions.
method Projecting a high spatial frequency pattern onto the face to recover 3D information and a 2D image simultaneously.
result Significantly boosts face recognition performance and dramatically improves robustness to spoofing attacks.
Visual perception is a challenging problem in part due to illumination variations. A possible solution is to first estimate an illumination invariant representation before using it for recognition. The object albedo and surface normals are examples of such representations. In this paper, we introduce a multilayer gener…
GANPOP uses deep learning to estimate optical properties from single images, improving accuracy over existing methods.
problem Estimating optical properties from single wide-field images.
method Conditional generative adversarial networks trained on paired images and optical property maps.
result GANPOP estimates optical properties with 58% higher accuracy than single-snapshot optical property technique in human gastrointestinal specimens.
New DR algorithm preserves both local and global structure.
problem Trade-off between preserving local and global structure in DR methods.
method Analysis of existing DR methods and design principles for loss functions.
result Design of PaCMAP algorithm that preserves both local and global structure.
Person re-identification (re-id), an emerging problem in visual surveillance, deals with maintaining entities of individuals whilst they traverse various locations surveilled by a camera network. From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras wit…
SAIL improves design exploration by reducing evaluations.
problem Limited evaluations in design space exploration.
method Integrates approximative models and intelligent sampling.
result Efficiently produces accurate models and diverse high-performing solutions.
Proposes methods to recover labels from shuffled networks using graph averages.
problem Recovering labels from a shuffled network using graph averages.
method Cluster networks into classes, then match the new graph to cluster-averages, minimizing the graph matching objective function.
result Higher fidelity matching performance when clustering networks into different classes.
New approach for camera-specific color constancy using few-shot meta-learning.
problem Domain gaps and lack of generalization across different cameras.
method Formulates color constancy as few-shot meta-learning tasks, leveraging annotated samples across different cameras.
result Significant reduction in data collection time and improved generalization to new cameras.
This research classifies Teichmüller curves in genus 2, proving parity conjectures for specific cases.
problem Classifying imprimitive Teichmüller curves in $\M_2$ related to square-tiled surfaces and modular curves.
method Analyzing square-tiled surfaces and their modular curves, proving parity conjectures for specific cases.
result Established the parity conjecture for Wd2[n] in three cases, showing number of components does not depend on d. Develops causal explanations for black-box classifiers.
problem Creating understandable explanations for complex models.
method Generative model with information-theoretic measures of causal influence.
result Learned latent factors influence classifier outputs.
DeepBark improves tree bark re-identification accuracy.
problem Challenging illuminations make tree bark hard to re-identify.
method Used a large dataset of 2,400 bark images to train DeepBark and SqueezeBark.
result DeepBark achieves 87.2% mAP in retrieving relevant bark images.
Top 8 robotic vision systems tackled lifelong object recognition challenges.
problem Lifelong learning in robotic vision for varied, dynamic environments.
method Design of a dataset with diverse conditions and rules for evaluation.
result Robotic vision systems improved over time with dynamic object appearances.
In this paper we use 3-manifold techniques to illuminate the structure of the string link monoid. In particular, we give a prime decomposition theorem for string links on two components as well as give necessary conditions for string links to commute under the stacking operation.
Ancient solutions found on flag manifolds from invariant Einstein metrics.
problem Understanding the behavior of Ricci flow on flag manifolds.
method Global study of the dynamical system induced by the Ricci flow, using invariant Einstein metrics and Poincaré compactification.
result Non-collapsed ancient solutions emerge from invariant Einstein metrics, with a Type I singularity in finite time.
Mounting evidences are being gathered suggesting that income and wealth distribution in various countries or societies follow a robust pattern, close to the Gibbs distribution of energy in an ideal gas in equilibrium, but also deviating significantly for high income groups. Application of physics models seem to provide…
Paper shows idempotents in tangle categories split naturally.
problem Understanding structure of tangle categories.
method 3-manifold techniques to analyze tangle categories.
result Every idempotent morphism splits naturally.
System learns user preferences to synthesize materials quickly.
problem Slow material synthesis for novice and expert users.
method Gaussian Process Regression for user preferences, neural network for real-time image predictions.
result Real-time material synthesis enables novice users to generate hundreds of models.
The basic theorems of vector calculus are illuminated when we replace the original 3 stooges of vector calculus: Grad, Div, and Curl, with combinatorial substitutes. In addition to providing simple proofs of Green's theorem and the equivalence of the integral and derivative definitions of curl, we also provide a brief …
Let K be a knot in S^3. We study the iterated Bing doubles of K, giving a new proof for the following statement: If BD_n(K) is slice for some n, then K is algebraically slice. This result was first proved by Cha and Kim using covering link calculus. We also use this tool, but our proof is substantially simpler and illu…
Investigates model selection challenges in heterogeneous treatment effect estimation.
problem Lack of validation metrics for choosing the best model in treatment effect estimation.
method Empirical investigation of different model selection criteria.
result Complex interplay between selection strategies, estimators, and data.
Increasingly, a huge amount of statistics have been gathered which clearly indicates that income and wealth distributions in various countries or societies follow a robust pattern, close to the Gibbs distribution of energy in an ideal gas in equilibrium. However, it also deviates in the low income and more significantl…
Quality-Diversity algorithms explore multiple high-performing solutions in a search space.
problem Finding multiple high-performing solutions in complex optimization problems.
method Evolutionary computation approach focusing on behavioral space and holistic solution distribution.
result Quality-Diversity algorithms provide a comprehensive view of high-performing solutions in a search space.
Study connects curvature to graph theory and reveals differences.
problem Exploring differences between Quadratic Orthogonal Bisectional Curvature and Real Bisectional Curvature.
method Real (1,1)--forms and Weitzenböck curvature operator used to represent graph Dirichlet energy.
result Curvature differences illuminated between Quadratic Orthogonal Bisectional Curvature and Real Bisectional Curvature.
Robust visual tracking for long video sequences is a research area that has many important applications. The main challenges include how the target image can be modeled and how this model can be updated. In this paper, we model the target using a covariance descriptor, as this descriptor is robust to problems such as p…
In recent years, random matrices have come to play a major role in computational mathematics, but most of the classical areas of random matrix theory remain the province of experts. Over the last decade, with the advent of matrix concentration inequalities, research has advanced to the point where we can conquer many (…
Paper proposes a graph model for optimal AP deployment in indoor optical wireless networks.
problem Challenges in deploying optical wireless networks due to LoS requirement and limited range.
method Graph modeling approach to identify minimum number of APs and their optimal locations.
result Optimal deployment of APs ensures connectivity and minimizes interference in indoor environments.
Improves synthetic data for deep model training and adaptation.
problem Evaluating and improving synthetic data for deep learning models.
method Proposes a novel learned synthesis technique using generative models for shading and rendering, and uses an ensemble of models to generate datasets.
result Improves classifier performance on real data compared to state-of-the-art methods.
A stroke-based method reconstructs characters from noisy images.
problem Challenges in reconstructing characters from noisy images.
method Uses a weighted quadratic Bezier curve (WQBC) to represent strokes.
result Achieves excellent reconstruction in real scenes.
The abstract explores connections between reinforcement learning, scaling, and diffusion.
problem Aligning reinforcement learning with human feedback and scaling techniques.
method Clarifying connections between reinforcement learning, scaling, and diffusion.
result Introducing a resampling approach for alignment and reward-directed diffusion models.
We classify GL(2,R) invariant point markings over components of strata of Abelian differentials. Such point markings exist only when the component is hyperelliptic and arise from marking Weierstrass points or two points exchanged by the hyperelliptic involution. We show that these point markings can be used to determin…
Functional Magnetic Resonance Imaging (fMRI) provides dynamical access into the complex functioning of the human brain, detailing the hemodynamic activity of thousands of voxels during hundreds of sequential time points. One approach towards illuminating the connection between fMRI and cognitive function is through dec…
Data science enhances knot theory by analyzing invariant relations.
problem Understanding the complex relations between knot invariants.
method Topological data analysis applied to knot theory.
result New insights into long-standing conjectures about knots.
Study anisotropic capillary surfaces in a wedge using generalized Minkowski norms.
problem Understanding capillary surfaces with anisotropic forces.
method Generalized Minkowski norm on the unit sphere, new Minkowski formulae, Heintze-Karcher inequality.
result Proved an Alexandrov-type theorem in the anisotropic setting.
New tool helps analyze complex financial data.
problem Difficulty in comprehending high-dimensional financial data.
method Topological Data Analysis Ball Mapper algorithm.
result Shows new way to see detail in financial data.
In the present paper we discuss the cabling procedure for the colored HOMFLY polynomial. We describe how it can be used and how one can find all the quantities such as projectors and R-matrices, which are needed in this procedure. The constructed matrix forms of the projectors and the fundamental $\mathcal{…
Mechanisms of human color vision are characterized by two phenomenological aspects: the system is nonlinear and adaptive to changing environments. Conventional attempts to derive these features from statistics use separate arguments for each aspect. The few statistical approaches that do consider both phenomena simulta…