Articles — Recent

Papers, presentations, reports and more, written in LaTeX and published by our community. Search or browse below.

Ali Özen's Resume
Ali Özen's Resume
Ali Özen's Resume. Created using the Deedy CV template.
Ali Özen
Conservative Wasserstein Training for Pose Estimation
Conservative Wasserstein Training for Pose Estimation
Paper presented at ICCV 2019. This paper targets the task with discrete and periodic class labels (e.g., pose/orientation estimation) in the context of deep learning. The commonly used cross-entropy or regression loss is not well matched to this problem as they ignore the periodic nature of the labels and the class similarity, or assume labels are continuous value. We propose to incorporate inter-class correlations in a Wasserstein training framework by pre-defining (i.e., using arc length of a circle) or adaptively learning the ground metric. We extend the ground metric as a linear, convex or concave increasing function w.r.t. arc length from an optimization perspective. We also propose to construct the conservative target labels which model the inlier and outlier noises using a wrapped unimodal-uniform mixture distribution. Unlike the one-hot setting, the conservative label makes the computation of Wasserstein distance more challenging. We systematically conclude the practical closed-form solution of Wasserstein distance for pose data with either one-hot or conservative target label. We evaluate our method on head, body, vehicle and 3D object pose benchmarks with exhaustive ablation studies. The Wasserstein loss obtaining superior performance over the current methods, especially using convex mapping function for ground metric, conservative label, and closed-form solution.
Xiaofeng Liu, Yang Zou, Tong Che, Peng Ding, Ping Jia, Jane You, B.V.K. Vijaya Kumar
Group Isomorphism
Group Isomorphism
Group Isomorphisms
Srishti Patel
The Logarithmic Method of Ranking Stocks
The Logarithmic Method of Ranking Stocks
A ranking system for tech stocks and bank stocks of S&P 500 companies
Albert Liang
Shaila Ang's CV
Shaila Ang's CV
Shaila Ang's CV Created with the CV for Freshers template.
Shaila
Survey on Bi-LSTM CNNs CRF for Italian Sequence Labeling and Multi-Task Learning
Survey on Bi-LSTM CNNs CRF for Italian Sequence Labeling and Multi-Task Learning
In the last few years the resolution of NLP tasks with architectures composed of neural models has taken vogue. There are many advantages to using these approaches especially because there is no need to do features engineering. In this paper, we make a survey of a Deep Learning architecture that propose a resolutive approach to some classical tasks of the NLP. The Deep Learning architecture is based on a cutting-edge model that exploits both word-level and character-level representations through the combination of bidirectional LSTM, CNN and CRF. This architecture has provided cutting-edge performance in several sequential labeling activities for the English language. The architecture that will be treated uses the same approach for the Italian language. The same guideline is extended to perform a multi-task learning involving PoS labeling and sentiment analysis. The results show that the system performs well and achieves good results in all activities. In some cases it exceeds the best systems previously developed for Italian.
leo.ranaldi
A Letter Template for the Institute for Biostatistics and Analyses at the Masaryk University in Brno
A Letter Template for the Institute for Biostatistics and Analyses at the Masaryk University in Brno
A template for muletter, a document class for the typesetting of letters at the Masaryk Univer­sity (Brno, Czech Repub­lic).
Vít Novotný
Techniques Of Electromagnetic Cloaking
Techniques Of Electromagnetic Cloaking
How to conceal objects from electromagnetic radiation has been a hot research topic. Radar is an object detection system that uses Radio waves to determine the range, angle, or velocity. A radar transmit radio waves or microwaves that reflect from any object in their path. A receive radar is typically the same system as transmit radar, receives and processes these reflected wave to determine properties of object. Different organizations are working onto hide object from the radar in outer space. Any confidential object can be taken through space without being detected by the enemies. This calls for necessity of devising new method to conceal an object electromagnetically.
Ankit Kumar
Edge-Disjoint Tree Realization of Tree Degree Matrices that avoid routine induction
Edge-Disjoint Tree Realization of Tree Degree Matrices that avoid routine induction
Identifying whether a degree matrix has an edge-disjoint realization is an NP-hard problem. In comparison, identifying whether a tree degree matrix has an edge-disjoint realization is easier, but the task is still challenging. In 1975, a sufficient condition for the tree degree matrices with three rows has been found, but the condition has not been improved since. This paper contains an essential part of the proof which improves the sufficient condition.
Ian Seong