Gallery — Conference Paper

Manuscript Templates for Conference Proceedings

The official LaTeX template for submissions to the 58th annual meeting of the Association for Computational Linguistics (ACL 2020). Note from Overleaf: SyncTeX will not work correctly with this template (as well as other templates based on similar underlying code, eg CVPR, EMNLP, etc) when the line numbers are active. To make SyncTeX function while authoring your manuscript, either on Overleaf or in your own LaTeX installation, the line numbers have to be turned off by uncommenting \aclfinalcopy. This version of the template is configured to open in Overleaf with the TeX Live 2016 compiler image. You may get an error if you compile it with TeX Live 2018 or newer. See this discussion for details if you need to compile this on TL2018 or newer.

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.

This is a template to respond reviewers of a journal paper

LaTeX template for 2019 ACM/IEEE Symposium on Architectures for Networking and Communications Systems (ANCS).

Template for 2020 International Conference on Learning Representations

Template for Polish Astronomical Society (PTA) proceedings

Template for the Interactive Sonification (ISon) workshop proceedings.

This is a LaTeX template available for use in submitting manuscripts to the 12th ICCP hosted in 2020 in Minneapolis, Minnesota.