Name: Hirano
Type: User
Company: Shandong University
Bio: A Third-Year Master Student in Shandong University , focusing on Multimodal Computing (VQA, VR, TSVG, etc.), and Low-level Restoration (SR, Denoising)
Location: Qingdao
Hirano's Projects
Reading list for research topics in multimodal machine learning
Awesome Person Re-Identification
Temporal Sentence Grounding in Videos / Natural Language Video Localization / Video Moment Retrieval的相关工作
This repository focus on Image Captioning & Video Captioning & Seq-to-Seq Learning & NLP
Official implementation of "Dynamic Mixed-order Laplacian Deep Network for Image Restoration".
Official implementation of "Discrete Optimal Graph Clustering", TCYB 2020.
These are learning notes for torch_geometric (Updating).
An Incremental Learning, Continual Learning, and Life-Long Learning Repository
Official implementation of "Focal and Composed Vision-Semantic Modeling for Visual Question Answering".
This is implementation of paper "Perturbation-aware Instance Discriminative Learning for Visual Question Answering" The code will be released after Accept!
A New Try of Semantic Map on Low-level Restoration Task (Focus on Denoising)
Official implementation of "Semantic-aware Modular Capsule Routing for Visual Question Answering", TIP 2023.
Minimalist implementation of VQ-VAE in Pytorch
Pytorch implementation of "Explainable and Explicit Visual Reasoning over Scene Graphs "