The clear benchmark: Continual learning on real-world imagery

Z Lin, J Shi, D Pathak, D Ramanan - Thirty-fifth conference on …, 2021 - openreview.net
Continual learning (CL) is widely regarded as crucial challenge for lifelong AI. However,
existing CL benchmarks, eg Permuted-MNIST and Split-CIFAR, make use of artificial …

Measuring similarity between brands using followers' post in social media

Y Zhang, X Wang, Y Sakai, T Yamasaki - Proceedings of the 1st ACM …, 2019 - dl.acm.org
In this paper, we propose a new measure to estimate the similarity between brands via posts
of brands' followers on social network services (SNS). Our method was developed with the …

Multi-label triplet embeddings for image annotation from user-generated tags

Z Seymour, Z Zhang - Proceedings of the 2018 ACM on International …, 2018 - dl.acm.org
This work studies the representational embedding of images and their corresponding
annotations--in the form of tag metadata--such that, given a piece of the raw data in one …

Measuring similarity between brands using social media content

Y Zhang, X Wang, Y Sakai… - ITE Transactions on Media …, 2021 - jstage.jst.go.jp
抄録 Exploring brands that customers are likely to purchase jointly has a profound effect on
marketing. This study proposes a new way to measure, or estimate the similarity between …

[图书][B] Combining Supervised Machine Learning and Structured Knowledge for Difficult Perceptual Tasks

M Klawonn - 2019 - search.proquest.com
Learning models of visual perception lies at the heart of a number of computer vision
problems, including object detection, image description, motion tracking, and more. There …

Leveraging Weakly-aligned User-generated Data for Deep Learning Features

Z Seymour - 2019 - search.proquest.com
The outputs of neural networks, either in the form of convolutional feature maps pre-trained
on ImageNet or distributed word representations fit to text from news articles, have proven to …