Vision and Language Intelligence

Établi : June 28, 2017

Invited Talks

Multimodal Learning for Image Captioning and Visual Question Answering (invited talk at UC Berkeley, BVLC) (opens in new tab), Xiaodong He, invited talk at UC Berkeley, BVLC, April 1, 2016, View abstract (opens in new tab), Download PDF (opens in new tab)
Towards Human-level Quality Image Captioning: Deep Semantic Learning of Text and Images (Invited Talk) (opens in new tab), Xiaodong He, Invited Talk at INNS Deep Learning Workshop, August 1, 2015, View abstract (opens in new tab), Download PDF (opens in new tab)
Deep Semantic Learning: Teach machines to understand text, image, and knowledge graph (Invited talk at CVPR DeepVision workshop) (opens in new tab), Invited talk at CVPR DeepVision workshop, Xiaodong He, June 1, 2015, View abstract (opens in new tab), Download PDF (opens in new tab)

Tutorial

Deep Learning and Continuous Representations for NLP (opens in new tab), Tutorial, Scott Wen-tau Yih, Xiaodong He, Jianfeng Gao, July, IJCAI 2016, PDF (opens in new tab)