Inception v3 model classifies face shapes with high accuracy.
problem Face shape classification using deep learning.
method Retraining Inception v3 model on face shape dataset.
result Inception v3 outperforms other classifiers.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “celebrity faces”
GANs can bias synthetic data, affecting minority and female faces.
problem GANs can amplify biases in synthetic data augmentation.
method Examine GANs on face-shots with gender and skin tone biases.
result GANs generate biased synthetic data, skewing minority modes and features.
Facial analysis models are increasingly used in applications that have serious impacts on people's lives, ranging from authentication to surveillance tracking. It is therefore critical to develop techniques that can reveal unintended biases in facial classifiers to help guide the ethical use of facial analysis technolo…
Researchers describe isometric deformations of T-hedra and T-surfaces.
problem Understanding the isometric deformations of discrete and smooth T-surfaces.
method Synthetic and analytic descriptions of T-hedra and T-surfaces, providing parametrizations of isometric deformations.
result Explicit parametrization of isometric deformations of T-hedra and T-surfaces.
Paper presents a new algorithm to approximate Wasserstein-2 barycenters without bias.
problem Approximating Wasserstein-2 barycenters of continuous measures.
method Generative model approach using arbitrary neural networks.
result The method does not introduce bias and is applicable to large-scale tasks.
RAD detects anomalies in unreliable data streams with up to 98% accuracy.
problem Anomaly detection in unreliable data sources.
method Two-layer on-line learning framework with data cleansing and oracle learning.
result RAD improves anomaly detection accuracy by up to 28%.
In recent times, many of the breakthroughs in various vision-related tasks have revolved around improving learning of deep models; these methods have ranged from network architectural improvements such as Residual Networks, to various forms of regularisation such as Batch Normalisation. In essence, many of these techni…
Elliptically-Contoured Tensor-variate Distributions with Application to Improved Image Learningstat.ME
Improved image learning using elliptically contoured tensor-variate distributions.
problem Inadequate statistical analysis for tensor-valued data, especially with heavier or lighter tails.
method Developed a family of elliptically contoured tensor-variate distributions and derived their properties and procedures for estimation.
result Tensor-variate classification rules and tensor-on-tensor regression better predict and characterize data than TVN-based methods.
Consider a simplicial complex that allows for an embedding into . How many faces of dimension or higher can it have? How dense can they be? This basic question goes back to Descartes' "Lost Theorem" and Euler's work on polyhedra. Using it and other fundamental combinatorial problems, we intr…
The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form …
Generalized Fáry's theorem to higher dimensions.
problem No specific problem stated; generalization of Fáry's theorem.
method Proof of a higher-dimensional version of Fáry's theorem.
result Proved a generalization of Fáry's theorem in higher dimensions.
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
problem Impersonation attacks using master faces for face-based identity authentication.
method Evolutionary algorithm in latent space of StyleGAN, neural network to direct search, 2D and 3D face reconstruction.
result Obtains high impersonation rates with fewer master faces for 2D and 3D face verification.
We characterize the existence of a locally conformally Kähler metric on a compact complex manifold in terms of currents, adapting the celebrated result of Harvey and Lawson for Kähler metrics.
New algorithm reduces regret and constraint violation in adversarial CMDP learning.
problem Online learning for episodic stochastically constrained Markov decision processes (CMDPs) with adversarial loss.
method Upper Confidence Primal-Dual Reinforcement Learning (UC-PDL) algorithm.
result Achieves upper bounds of both regret and constraint violation.
Face recognition systems are vulnerable to composite face reconstruction attacks.
problem Vulnerability of face recognition systems to composite face reconstruction attacks.
method Assumed attacker uses composite face parts to reconstruct faces faster and more efficiently.
result Current face recognition systems are extremely vulnerable to random search attacks.
Generalizes embeddedness result for extreme curves.
problem Embeddedness of solutions to the Plateau problem for extreme curves.
method Generalization of Meeks-Yau's result.
result Generalization of embeddedness result.
In this paper we prove a relative index theorem for pairs of generalized Dirac operators on orbifolds which are the same at infinity. This generalizes to orbifolds a celebrated theorem of Gromov and Lawson.
For any positive natural number we construct new explicit proper -harmonic functions on the celebrated -dimensional Thurston geometries $\Sol$, $\Nil$, $\SL2$, $\H^2\times\rn$ and $\s^2\times\rn$.
Universal adversarial patches prevent face detection in various frameworks.
problem Preventing face detection in state-of-the-art face detection systems.
method Investigated the phenomenon of patches that suppress face detection and proposed optimization-based approaches for automatic design.
result Universal adversarial patches can prevent face detection without introducing false positives.
We consider an infinite dimensional optimization problem motivated by mathematical economics. Within the celebrated "Arbitrage Pricing Model", we use probabilistic and functional analytic techniques to show the existence of optimal strategies for investors who maximize their expected utility.
Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop a method that can convert speech into a voice that matches an input face image and generate a face image that matches the voice of the inpu…
We summarize the main ideas of General Relativity and Lorentzian geometry, leading to a proof of the simplest of the celebrated Hawking-Penrose singularity theorems. The reader is assumed to be familiar with Riemannian geometry and point set topology.
Partial differential equations (PDEs) are indispensable for modeling many physical phenomena and also commonly used for solving image processing tasks. In the latter area, PDE-based approaches interpret image data as discretizations of multivariate functions and the output of image processing algorithms as solutions to…
Despite the remarkable progress in face recognition related technologies, reliably recognizing faces across ages still remains a big challenge. The appearance of a human face changes substantially over time, resulting in significant intra-class variations. As opposed to current techniques for age-invariant face recogni…
Perelman's Stability Theoremmath.DG
We give a proof of the celebrated stability theorem of Perelman stating that for a noncollapsing sequence of Alexandrov spaces with curvature bounded below Gromov-Hausdorff converging to a compact Alexandrov space , is homeomorphic to for all large .
Following the lines of the celebrated Riemannian result of Gromoll and Meyer, we use infinite dimensional equivariant Morse theory to establish the existence of infinitely many geometrically distinct closed geodesics in a class of globally hyperbolic stationary Lorentzian manifolds.
Faces of quasi-arithmetic Coxeter polytopes are also quasi-arithmetic.
problem Characterizing faces of quasi-arithmetic Coxeter polytopes.
method Proof of quasi-arithmetic property of faces and sufficient condition for arithmetic faces.
result Lower-dimensional faces of quasi-arithmetic Coxeter polytopes are quasi-arithmetic.
In this paper, we study face vectors of simplicial posets that are the face posets of cell decompositions of topological manifolds without boundary. We characterize all possible face vectors of simplicial posets whose geometric realizations are homeomorphic to the product of spheres. As a corollary, we obtain the chara…
We are interested in attribute-guided face generation: given a low-res face input image, an attribute vector that can be extracted from a high-res image (attribute image), our new method generates a high-res face image for the low-res input that satisfies the given attributes. To address this problem, we condition the …
Study on critical faces convergence in a Poisson point process.
problem Convergence of point processes associated with critical faces in a Čech filtration.
method Established convergence in -topology for critical faces above vanishing threshold.
result Obtained limit theorems for positive and negative critical faces.
Bayesian optimization generates personalized face stimuli for cognitive neuroscience.
problem Lack of personalized face stimuli in cognitive neuroscience studies.
method Combines GANs with Bayesian optimization to identify individual response patterns to faces.
result Algorithm efficiently generates optimal faces maximizing individual subject's response.
Motivated principally by the low-rank matrix completion problem, we present an extension of the Frank-Wolfe method that is designed to induce near-optimal solutions on low-dimensional faces of the feasible region. This is accomplished by a new approach to generating ``in-face" directions at each iteration, as well as t…
Generates realistic faces from detailed textual descriptions.
problem Face generation from fine-grained textual descriptions.
method Conditional GAN model with DC-GAN and GAN-CLS loss, using CelebA dataset with generated captions.
result Promising results in generating diverse face images from fine-grained textual descriptions.
The paper is motivated by the study of graded representations of Takiff algebras, cominuscule parabolics, and their generalizations. We study certain special subsets of the set of weights (and of their convex hull) of the generalized Verma modules (or GVM's) of a semisimple Lie algebra $\lie g$. In particular, we exten…
Extends Milnor's criterion to biharmonic functions.
problem Deciding surface type for biharmonic functions.
method Generalizes Milnor's criterion to biharmonic functions.
result Characterizes whether a surface is hyperbolic or parabolic for biharmonic functions.
We prove that under some assumptions on the mean curvature the set of umbilical points of an immersed surface in a -dimensional space form has positive measure. In case of an immersed sphere our result can be seen as a generalization of the celebrated Hopf theorem.
In his celebrated paper "Generic projections", John Mather has given a striking transversality theorem and its applications on generic projections. On the other hand, in this paper, two transversality theorems on generic linearly perturbed mappings are shown . Moreover, some applications of the two the…
Formula for manifold Euler characteristic using even faces.
problem Calculating Euler characteristic of triangulated manifolds.
method Formula based on even-dimensional faces.
result Universal coefficients for Euler characteristic.
We develop a parabolic pluripotential theory on compact K{ä}hler manifolds, defining and studying weak solutions to degenerate parabolic complex Monge-Amp{è}re equations. We provide a parabolic analogue of the celebrated Bedford-Taylor theory and apply it to the study of the K{ä}hler-Ricci flow on varieties with log te…
Face recall is a basic human cognitive process performed routinely, e.g., when meeting someone and determining if we have met that person before. Assisting a subject during face recall by suggesting candidate faces can be challenging. One of the reasons is that the search space - the face space - is quite large and lac…
Mutations and faces of the Thurston norm ball dynamically represented by multiple distinct flowsmath.GT
New flows represent Thurston norm ball faces, differing by veering mutations.
problem Dynamic representation of Thurston norm ball faces by distinct flows.
method Combining veering triangulations and mutations to represent faces by multiple flows.
result Non-fibered faces can be represented by two distinct flows differing by veering mutations.
We show that the Kauffman bracket of a checkerboard colorable virtual link is an evaluation of the Bollobás-Riordan polynomial of a ribbon graph associated with . This result generalizes Thistlethwaite's celebrated theorem relating the Kauffman bracket with the Tutte polynomial of planar graphs.
In this paper we address the following question, given a face representation, how many identities can it resolve? In other words, what is the capacity of the face representation? A scientific basis for estimating the capacity of a given face representation will not only benefit the evaluation and comparison of differen…
A celebrated theorem of Marshall Hall Jr. implies that finitely generated free groups are subgroup separable and that all of their finitely generated subgroups are retracts of finite-index subgroups. We use topological techniques inspired by the work of Stallings to prove that all limit groups share these two propertie…
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.
Paper proposes a method to encrypt faces while maintaining visual similarity.
problem Protecting personal data from unauthorized face recognition.
method Targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
result TIP-IM provides 95%+ protection success rate against face recognition models.
Study evaluates the impact of academic support center's face-to-face assistance on student performance.
problem Underestimation of Academic Support Center's true impact due to group bias.
method Applied causal inference theory and T-learner to evaluate conditional average treatment effect (CATE) of F2F personal assistance.
result Developed a new CATE function that depends on the number of F2F sessions, predicting improved CATE performance.
The face pairing graph of a 3-manifold triangulation is a 4-valent graph denoting which tetrahedron faces are identified with which others. We present a series of properties that must be satisfied by the face pairing graph of a closed minimal P^2-irreducible triangulation. In addition we present constraints upon the co…