Yaya Shi's Projects
Research code for CVPR 2022 paper: "EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching"
common visual captioning evaluation metrics
A faster pytorch implementation of faster r-cnn
Pytorch implementation of Feature Pyramid Network (FPN) for Object Detection
links to conference publications in graph-based deep learning
A pytorch replementation for "Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling"
Pytorch code for our ECCV 2018 paper "Graph R-CNN for Scene Graph Generation"
Video Grounding and Captioning
A dataset of crowdsourced ratings for machine-generated image captions
Notes on preparing for coding interviews during my PhD
Download DeepMind's Kinetics dataset.
Convolutional neural network model for video classification trained on the Kinetics dataset.
Inflated i3d network with inception backbone, weights transfered from tensorflow
Lanczos Network, Graph Neural Networks, Deep Graph Convolutional Networks, Deep Learning on Graph Structured Data, QM8 Quantum Chemistry Benchmark, ICLR 2019
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
PyTorch implementation of Multiple-instance learning
with reinforcement learning
Pytorch code of for our CVPR 2018 paper "Neural Baby Talk"
Oscar and VinVL
i3d model fine-tune on charades, the fine-tuned models in models directory