thaolmk54
Computer Vision, Visual Reasoning, Machine Learning, Machine Reasoning. @A2I2, Deakin University, Australia.
Pinned Repositories
Advanced-System-Software
Source code for Music Player demo
anticipatr
bottom-up-attention.pytorch
An PyTorch reimplementation of bottom-up-attention models
consistent_gqa
Train a consistent general question and answer machine
CRAFT-Box2D
The simulator that we used to render 2D physics simulations for CRAFT dataset generation.
DensePose
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
EDABK1MakeFriendEasily
QR code and decode to exchange contact
graph-primal-dual
hcrn-videoqa
Implementation for the paper "Hierarchical Conditional Relation Networks for Video Question Answering" (Le et al., CVPR 2020, Oral)
LOGNet-VQA
Implementation for the paper "Dynamic Language Binding in Relational Visual Reasoning" (Le et al., IJCAI 2020)
thaolmk54's Repositories
thaolmk54/hcrn-videoqa
Implementation for the paper "Hierarchical Conditional Relation Networks for Video Question Answering" (Le et al., CVPR 2020, Oral)
thaolmk54/LOGNet-VQA
Implementation for the paper "Dynamic Language Binding in Relational Visual Reasoning" (Le et al., IJCAI 2020)
thaolmk54/Advanced-System-Software
Source code for Music Player demo
thaolmk54/anticipatr
thaolmk54/bottom-up-attention.pytorch
An PyTorch reimplementation of bottom-up-attention models
thaolmk54/consistent_gqa
Train a consistent general question and answer machine
thaolmk54/CRAFT-Box2D
The simulator that we used to render 2D physics simulations for CRAFT dataset generation.
thaolmk54/DensePose
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
thaolmk54/EDABK1MakeFriendEasily
QR code and decode to exchange contact
thaolmk54/graph-primal-dual
thaolmk54/hcrn-long-short-videoqa
Implementation for the paper "Hierarchical Conditional Relation Networks for Long–Short-Form Video Question Answering"
thaolmk54/thaolmk54.github.io
Thao Minh Le personal site
thaolmk54/VQA2.0-Recent-Approachs-2018.pytorch
A pytroch reimplementation of "Bilinear Attention Network", "Intra- and Inter-modality Attention", "Learning Conditioned Graph Structures", "Learning to count object", "Bottom-up top-down" for Visual Question Answering 2.0
thaolmk54/VideoPose3D
Efficient 3D human pose estimation in video using 2D keypoint trajectories
thaolmk54/VSU-Dataset
ARVSU dataset - Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances