Licheng Yu

refer. Referring Expression Datasets API

MAttNet. MAttNet: Modular Attention Network for Referring Expression Comprehension

mask-faster-rcnn. Mask R-CNN

pretrain-vl-data. Pre-trained V+L Data Preparation

vist_api. Visual Storytelling API

speaker_listener_reinforcer. Torch Implementation of Speaker-Listener-Reinforcer for Referring Expression Generation and Comprehension

refer-parser2. Referring Expression Parser

vist_eval. vist story telling evaluation tool

mteqa. Multi-Target Embodied Question Answering

referit-game-code-app. ReferIt Game Code

refer2. refer API for new (full) dataset with new evaluation

pytorch-vgg. VggNet Caffe-to-PyTorch Conversion

detectron2. Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

MAttNetDemo. Web demo for MAttNet

transferlearning-tutorial. 《迁移学习简明手册》LaTex源码

lichengunc.github.io. Personal Website

mmf. A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

House3D. C++