collaborators

7 papers

cs.CV2020

Learning to Scale Multilingual Representations for Vision-Language Tasks

Andrea Burns, Donghyun Kim, Derry Wijaya +2

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are a…

cs.CV2020

Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels

Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh +3

Existing unsupervised domain adaptation methods aim to transfer knowledge from a label-rich source domain to an unlabeled target domain. However, obtaining labels for some source d…

cs.CV2019

LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval

Reuben Tan, Huijuan Xu, Kate Saenko +1

The goal of weakly-supervised video moment retrieval is to localize the video segment most relevant to the given natural language query without access to temporal annotations durin…

cs.CV2019

MULE: Multimodal Universal Language Embedding

Donghyun Kim, Kuniaki Saito, Kate Saenko +2

Existing vision-language methods typically support two languages at a time at most. In this paper, we present a modular approach which can easily be incorporated into existing visi…

cs.CV2019

Learning Similarity Conditions Without Explicit Supervision

Reuben Tan, Mariya I. Vasileva, Kate Saenko +1

Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these…

cs.CV2019

Language Features Matter: Effective Language Representations for Vision-Language Tasks

Andrea Burns, Reuben Tan, Kate Saenko +2

Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language m…