roadjiang

e3d_lstm

e3d-lstm; Eidetic 3D LSTM A Model for Video Prediction and Beyond

graph_distillation

Graph Distillation for Action Detection

mentornet

Code for MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks

tirg

deep learning, image retrieval, vision and language

Awesome-Visual-Transformer

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

FVTA_memoryqa

Real-world photo sequence question answering system

memexqa

MemexQA Dataset

Multiverse

Dataset, code and model for the CVPR'20 paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction"

roadjiang.github.io

sg2im

Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 2018

roadjiang/memexqa

MemexQA Dataset

roadjiang/FVTA_memoryqa

Real-world photo sequence question answering system

roadjiang/roadjiang.github.io

roadjiang/Awesome-Visual-Transformer

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

roadjiang/Multiverse

Dataset, code and model for the CVPR'20 paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction"

roadjiang/sg2im

Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 2018

roadjiang/paper-reading