Name: Daqing Liu
Type: User
Company: JD.com Inc
Bio: Research Scientist@JD Explore Academy, JD.com. Focusing on Multi-Modality Learning (MML), including representation, alignment, generation, and decision-making.
Location: Beijing, China
Blog: https://daqingliu.github.io
Daqing Liu's Projects
🇫🇷 Oh my tmux! My self-contained, pretty & versatile tmux configuration made with ❤️
awesome grounding: A curated list of research papers in visual grounding
A curated list of research papers in Referring Expression Comprehension (REC)
A curated list of research papers in Vision-Language Navigation (VLN)
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
Code release for Context-Aware Visual Policy Network for Sequence-Level Image Captioning (MM 2018) and Context-Aware Visual Policy Network for Fine-Grained Image Captioning (TPAMI 2019)
A python3 version of cider.
A python3 version of coco-caption with spice.
MAttNet: Modular Attention Network for Referring Expression Comprehension
Code release for Learning to Assemble Neural Module Tree Networks for Visual Grounding (ICCV 2019)
A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).