Search Results for author: Jinsoo Choi

Found 14 papers, 5 papers with code

Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data

no code implementations26 Jan 2023 Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi, In So Kweon

We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models.

Relational Captioning Sentence

Self-Supervised Real-time Video Stabilization

no code implementations10 Nov 2021 Jinsoo Choi, Jaesik Park, In So Kweon

Videos are a popular media form, where online video streaming has recently gathered much popularity.

Video Stabilization

ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection

1 code implementation9 Sep 2021 Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, In So Kweon

A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution.

Human-Object Interaction Detection

Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation

no code implementations13 Apr 2021 Jae Won Cho, Dong-Jin Kim, Jinsoo Choi, Yunjae Jung, In So Kweon

In this work, we address the issues of missing modalities that have arisen from the Visual Question Answer-Difference prediction task and find a novel method to solve the task at hand.

Knowledge Distillation Visual Question Answering (VQA)

Dense Relational Image Captioning via Multi-task Triple-Stream Networks

1 code implementation8 Oct 2020 Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi, In So Kweon

To this end, we propose the multi-task triple-stream network (MTTSNet) which consists of three recurrent units responsible for each POS which is trained by jointly predicting the correct captions and POS for each word.

Graph Generation Object +4

Detecting Human-Object Interactions with Action Co-occurrence Priors

1 code implementation17 Jul 2020 Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, In So Kweon

A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution.

Human-Object Interaction Detection

Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach

no code implementations IJCNLP 2019 Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon

To this end, our proposed semi-supervised learning method assigns pseudo-labels to unpaired samples via Generative Adversarial Networks to learn the joint distribution of image and caption.

Image Captioning

Deep Iterative Frame Interpolation for Full-frame Video Stabilization

2 code implementations5 Sep 2019 Jinsoo Choi, In So Kweon

We present a novel deep approach to video stabilization which can generate video frames without cropping and low distortion.

Video Stabilization

Contextually Customized Video Summaries via Natural Language

no code implementations6 Feb 2017 Jinsoo Choi, Tae-Hyun Oh, In So Kweon

Despite the challenging baselines, our method still manages to show comparable or even exceeding performance.

Video-Story Composition via Plot Analysis

no code implementations CVPR 2016 Jinsoo Choi, Tae-Hyun Oh, In So Kweon

Inspired by plot analysis of written stories, our method generates a sequence of video clips ordered in such a way that it reflects plot dynamics and content coherency.

Optical Flow Estimation Patch Matching

Human Attention Estimation for Natural Images: An Automatic Gaze Refinement Approach

no code implementations12 Jan 2016 Jinsoo Choi, Tae-Hyun Oh, In So Kweon

Photo collections and its applications today attempt to reflect user interactions in various forms.

Gaze Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.