activity
20162020
most citedPoster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset

1 citations · 1 across the 1 of their papers we have counts for

collaborators

5 papers

cs.CV2020

Learning Architectures for Binary Networks

Dahyun Kim, Kunal Pratap Singh, Jonghyun Choi

Backbone architectures of most binary networks are well-known floating point architectures such as the ResNet family. Questioning that the architectures designed for floating point…

cs.CV2019

Learning to Super Resolve Intensity Images from Events

S. Mohammad Mostafavi I., Jonghyun Choi, Kuk-Jin Yoon

An event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic range, and low power consumption. As a trade-off, the e…

cs.CR20191 cited

Poster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset

Sanghyun Hong, Tae-hoon Kim, Tudor Dumitraş +1

As there are increasing needs of sharing data for machine learning, there is growing attention for the owners of the data to claim the ownership. Visible watermarking has been an e…

cs.CV2016

Mining Discriminative Triplets of Patches for Fine-Grained Classification

Yaming Wang, Jonghyun Choi, Vlad I. Morariu +1

Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions; therefore, accurate localization of disc…

cs.CV2016

Learning Temporal Regularity in Video Sequences

Mahmudul Hasan, Jonghyun Choi, Jan Neumann +2

Perceiving meaningful activities in a long video sequence is a challenging problem due to ambiguous definition of 'meaningfulness' as well as clutters in the scene. We approach thi…