arxiv.org/abs/2407.10092v5
Based on [1], we study the complexity of horizontality in each twistor space $\hat{E}_{\varepsilon}$ associated with an oriented vector bundle $E$ of rank $4$ with a positive-definite metric over the $2$-torus $T^2$, and obtain classification of the...
arxiv.org/abs/2511.04394v1
DORAEMON is an open-source PyTorch library that unifies visual object modeling and representation learning across diverse scales. A single YAML-driven workflow covers classification, retrieval and metric learning; more than 1000 pretrained backbones...
arxiv.org/abs/2211.07371v1
Over the past years, the main research innovations in face recognition focused on training deep neural networks on large-scale identity-labeled datasets using variations of multi-class classification losses. However, many of these datasets are retrea...
arxiv.org/abs/2411.01378v2
We report the results of a spectroscopic survey of candidate T subdwarfs identified by the Backyard Worlds: Planet 9 program. Near-infrared spectra of 31 sources with red $J-W2$ colors and large $J$-band reduced proper motions show varying signatures...
arxiv.org/abs/2401.15175v1
The escalating global concern over extensive food wastage necessitates innovative solutions to foster a net-zero lifestyle and reduce emissions. The LILA home composter presents a convenient means of recycling kitchen scraps and daily food waste into...
arxiv.org/abs/1608.00797v1
This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016. We follow the basic pipeline of temporal segment networks and further raise the performance via a number of other t...
arxiv.org/abs/2105.06253v2
In this work, we explore a Connectionist Temporal Classification (CTC) based end-to-end Automatic Speech Recognition (ASR) model for the Myanmar language. A series of experiments is presented on the topology of the model in which the convolutional la...
arxiv.org/abs/1308.1683v1
We determine conformal symmetry classes for the pp-wave spacetimes. This refines the isometry classification scheme given by Sippel and Goenner (1986 {\it Gen. Rel. Grav.} {\bf 18} 1229). It is shown that every conformal Killing vector for the null f...
arxiv.org/abs/0803.4055v1
Occasionally during the course of the human learning experience we are faced with an anomaly. An aberration of sorts, which try as we might, defies appropriate classification. The recent paper by Spiegelman et al.--Chemical and forensic analysis of...
arxiv.org/abs/dg-ga/9612013v1
P. Baird and the second author studied harmonic morphisms from a three-dimensional simply-connected space form to a surface and obtained a complete local and global classification of them. In this paper, we obtain a description of all harmonic morp...
arxiv.org/abs/2509.11615v1
With the ever-changing landscape of cyber threats, identifying their origin has become paramount, surpassing the simple task of attack classification. Cyber threat attribution gives security analysts the insights they need to device effective threat...
arxiv.org/abs/0705.2516v1
The work proposes the application of neural networks with particle swarm optimisation (PSO) and genetic algorithms (GA) to compensate for missing data in classifying high voltage bushings. The classification is done using DGA data from 60966 bushin...
arxiv.org/abs/2106.01364v1
Semi-iNat is a challenging dataset for semi-supervised classification with a long-tailed distribution of classes, fine-grained categories, and domain shifts between labeled and unlabeled data. This dataset is behind the second iteration of the semi-s...
arxiv.org/abs/2501.06031v2
Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the structure o...
arxiv.org/abs/1101.3480v3
The first part of this paper completes the classification of Whitney towers in the 4-ball that was started in three related papers. We provide an algebraic framework allowing the computations of the graded groups associated to geometric filtrations o...
arxiv.org/abs/2004.04232v3
In this paper we enumerate the skew braces of non-abelian type of size $p^2q$ for $p,q$ primes with $q>2$ by the classification of regular subgroups of the holomorph of the non-abelian groups of the same order. Since Crespo dealt with the case $q=2$,...
arxiv.org/abs/2004.04291v4
This is the first part of a series of two articles. In this paper we enumerate and classify the left braces of size $p^2q$ where $p$ and $q$ are distinct prime numbers by the classification of regular subgroups of the holomorph of the abelian groups...
arxiv.org/abs/2005.05809v3
Given a finite group $ G $, we study certain regular subgroups of the group of permutations of $ G $, which occur in the classification theories of two types of algebraic objects: skew left braces with multiplicative group isomorphic to $ G $ and Hop...
arxiv.org/abs/1912.11889v2
In this paper we enumerate the skew braces of size $p^2q$ for $p,q$ odd primes by the classification of regular subgroups of the holomorph of the groups of size $p^2q$. In particular, we provide explicit formulas for the skew braces of abelian type....
arxiv.org/abs/2407.18396v1
Merging and interactions can radically transform galaxies. However, identifying these events based solely on structure is challenging as the status of observed mergers is not easily accessible. Fortunately, cosmological simulations are now able to pr...