天天看点

多模态paper只看标题

  • Multi-modal Sentiment Analysis using Deep Canonical Correlation Analysis

标题:基于深度典型相关分析的多模态情感分析

作者: Zhongkai Sun, Erik P. Bucy

链接:https://arxiv.org/abs/1907.08696

看着感觉一般

  • VIFIDEL: Evaluating the Visual Fidelity of Image Descriptions

标题:VIFIDEL:评估图像描述的视觉逼真度

作者: Pranava Madhyastha, Lucia Specia

备注:Accepted for publication at ACL 2019

链接:https://arxiv.org/abs/1907.09340

多模态很火吧

  • M-BERT: Injecting Multimodal Information in the BERT Structure

标题:M-BERT:在BERT结构中注入多模态信息

作者: Wasifur Rahman, Mohammed Ehsan Hoque

链接:https://arxiv.org/abs/1908.05787

  • Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts

标题:红场大吗?MALeViC:利用视觉上下文对形容词进行建模

作者: Sandro Pezzelle, Raquel Fernández

备注:Accepted at EMNLP-IJCNLP 2019

链接:https://arxiv.org/abs/1908.10285

  • Probing Representations Learned by Multimodal Recurrent and Transformer Models

标题:通过多模态递归和迁移模型学习探测表示

作者: Jindřich Libovický, Pranava Madhyastha

链接:https://arxiv.org/abs/1908.11125

  • SIMMC: Situated Interactive Multi-Modal Conversational Data Collection And Evaluation Platform

标题:SIMMC:情境交互式多模态会话数据采集与评估平台

作者: Paul A. Crook, Rajen Subba

备注:ASRU 2019 (demonstration)

链接:https://arxiv.org/abs/1911.02690

继续阅读