Visually Grounded Paraphrase Identification via Gating and Phrase Localization
コメディドラマにおける字幕と表情を用いた笑い予測
Adaptive Gating Mechanism for Identifying Visually Grounded Paraphrases
広告バナー画像への自動テキスト配置
画像の圧縮トレードオフ推定
Rethinking the Evaluation of Video Summaries
Collecting Relation-Aware Video Captions
Learning to Identify Visually Grounded Paraphrase
Serif or Sans: Visual Font Analytics on Book Covers and Online Advertisements
An Empirical Study of Language Representations for Video Question Answering
Regularizing Adversarial Training for Single-shot Object Placement
CycleGAN を用いた感情スタイル転送
深層学習によるFacebook広告のCTR予測
Linking Videos and Languages: Representations and Their Applications
Unreasonable Effectiveness of OCR in Visual Advertisement Understanding
Visually grounded paraphrase extraction via phrase grounding
Emotional Style Transfer for Stock Assets
Feedback-prop: Convolutional Neural Network Inference under Partial Evidence
Computer Vision meets Fashion
End-to-end learning potentials for structured attribute prediction
Recommending Outfits From Personal Closet