Mingkui Tan

Latest

• Debiased Visual Question Answering from Feature and Sample Perspectives
• R-GAN: Exploring Human-like Way for Reasonable Text-to-Image Sythesis via Generative Adversarial Networks
• Towards Accurate Text-based Image Captioning with Content Diversity Exploration
• How to Train Your Agent to Read and Write?
• Length Controllable Image Captioning
• Modular Graph Attention Network for Complex Visual Relational Reasoning
• Attend and Imagine: Multi-label Image Classification with Visual Attention and Recurrent Neural Networks
• Cascade Reasoning Network for Text-based Visual Question Answering
• Visual Grounding via Accumulated Attention
• Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
• Scripted Video Generation with a Bottom-up Generative Adversarial Network
• Visual Grounding via Accumulated Attention