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.
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
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…
Face recognition systems are vulnerable to composite face reconstruction attacks.
This paper converts speech to match a face image and vice versa.
Face verification remains a challenging problem in very complex conditions with large variations such as pose, illumination, expression, and occlusions. This problem is exacerbated when we rely unrealistically on a single training data source, which is often insufficient to cover the intrinsically complex face variatio…
Inception v3 model classifies face shapes with high accuracy.
Pixel-wise relevance method shows how CNNs classify faces, varying across datasets and tasks.
Generates realistic faces from detailed textual descriptions.
FairCal improves face verification accuracy while making results fairer.
Bayesian optimization generates personalized face stimuli for cognitive neuroscience.
Study analyzes carbon footprint of 1,417 ML models on Hugging Face.
A recent Cell paper [Chang and Tsao, 2017] reports an interesting discovery. For the face stimuli generated by a pre-trained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition exhibit strong linear relationship with the shape variables and…
Improved autoencoder for realistic face manipulation.
OGAN attacks autoencoders to prevent deepfake creation.
The state-of-the-art performance of deep learning algorithms has led to a considerable increase in the utilization of machine learning in security-sensitive and critical applications. However, it has recently been shown that a small and carefully crafted perturbation in the input space can completely fool a deep model.…
Paper proposes a method to encrypt faces while maintaining visual similarity.
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…
Universal adversarial patches prevent face detection in various frameworks.
Deep convolutional neural networks (CNNs) based approaches are the state-of-the-art in various computer vision tasks, including face recognition. Considerable research effort is currently being directed towards further improving deep CNNs by focusing on more powerful model architectures and better learning techniques. …
Model manipulates facial expressions without affecting other attributes.
We call "flippable tilings" of a constant curvature surface a tiling by "black" and "white" faces, so that each edge is adjacent to two black and two white faces (one of each on each side), the black face is forward on the right side and backward on the left side, and it is possible to "flip" the tiling by pushing all …
Faces of quasi-arithmetic Coxeter polytopes are also 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…
Biometrics emerged as a robust solution for security systems. However, given the dissemination of biometric applications, criminals are developing techniques to circumvent them by simulating physical or behavioral traits of legal users (spoofing attacks). Despite face being a promising characteristic due to its univers…
In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related attributes. This is done by training an embedding network that maps discrete id…
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.
Energy-based models can generate complex images by combining simpler concepts.
Our focus is on realistically modeling and forecasting dynamic networks of face-to-face contacts among individuals. Important aspects of such data that lead to problems with current methods include the tendency of the contacts to move between periods of slow and rapid changes, and the dynamic heterogeneity in the actor…
We propose a model for the credit and liquidity risks faced by clearing members of Central Counterparty Clearing houses (CCPs). This model aims to capture the features of: gap risk; feedback between clearing member default, market volatility and margining requirements; the different risks faced by various types of mark…
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…
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…
A new method for higher-order co-occurrences in hypergraphs.
In this paper, we address the problem of conditional modality learning, whereby one is interested in generating one modality given the other. While it is straightforward to learn a joint distribution over multiple modalities using a deep multimodal architecture, we observe that such models aren't very effective at cond…
Reduces gender classification bias by learning race-invariant face representations.
Formula for manifold Euler characteristic using even faces.
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…
New flows represent Thurston norm ball faces, differing by veering mutations.
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manne…
This work generates synthetic 3D thermal facial data using 2D facial data and deep learning.
Enhances 2D face recognition with 3D features using active illumination.
Study evaluates the impact of academic support center's face-to-face assistance on student 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…
If a convex body C has modular and irreducible face lattice (and is not strictly convex), there is a face-preserving homeomorphism from C to a section of a cone of hermitian matrices or C has dimension 8, 14 or 26.
Deep learning detects face swapping with high accuracy and uncertainty.
HMN detects fake faces using memory networks and visual cues.
This paper reviews deep learning techniques for face recognition and sketch matching.
Simple method detects deepfakes with few labeled samples.