Articles — Recent

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

Sidney Hann's Résumé
Sidney Hann's Résumé
Sidney Hann's résumé. Created using Ganesh Mohan's résumé template.
Sidney Hann
Abdallah Meddah's CV
Abdallah Meddah's CV
Abdallah Meddah's CV. Created with the AltaCV template.
Abdallah Meddah
Aadhithya Dinesh's Resume
Aadhithya Dinesh's Resume
Aadhithya Dinesh's Resume
Aadhithya Dinesh
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