Leticia Pinto

I am a visiting student in the Vislang lab at the University of Virginia, where I work on computer vision, natural language processing, and machine learning.

At Vislang I've worked on ChairSeg, Machine Translation, Text2Scene demo.

Email  /  CV  /  Google Scholar  /  LinkedIn

profile photo
Chair Segments: A Compact Benchmark for the Study of Object Segmentation
Leticia Pinto-Alva, Ian K., Rosangel Garcia, Ziyan Yang, Vicente Ordonez
arXiv, 2020
project page / arXiv

ChairSegments, a novel and compact semi-synthetic dataset for object segmentation.

Using Visual Feature Space as a Pivot Across Languages
Ziyan Yang, Leticia Pinto-Alva, Franck Dernoncourt, Vicente Ordonez
Findings of EMNLP 2020,
project page / ACL

Our work aims to leverage visual feature space to pass information across languages.

An Iterated Semi-Greedy Algorithm for the 0-1 Quadratic Knapsack Problem
Leticia Pinto-Alva, Alexander J. Benavides,
CLAIO 2018 XIX Latin-Iberoamerican Conference on Operations Research,

This paper presents a new Iterated Semi-Greedy Algorithm (ISGA) for the 0-1 Quadratic Knapsack Problem.


I developed demos with Flask and Pytorch.

Text2Scene Demo
Leticia Pinto-Alva, Vicente Ordonez, Fuwen Tan

The Text2Scene model was proposed by our group in CVPR 2019 paper titled Text2Scene: Generating Compositional Scenes from Textual Descriptions. This model combines pieces of images from the COCO Dataset and creates new images with them by stitching them into a new image. This demo generates cartoon-like images using the vocabulary and graphics from the Abstract Scenes dataset proposed by Zitnick and Parikh.

Website template courtesy of Jon Barron.