HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs

1 code implementation • 22 Nov 2019 • Fangyu Liu, Rongtian Ye, Xun Wang, Shuaipeng Li

The hubness problem widely exists in high-dimensional embedding space and is a fundamental source of error for cross-modal matching tasks.

A Strong and Robust Baseline for Text-Image Matching

no code implementations • ACL 2019 • Fangyu Liu, Rongtian Ye

We review the current schemes of text-image matching models and propose improvements for both training and inference.

3D Depthwise Convolution: Reducing Model Parameters in 3D Vision Tasks

no code implementations • 5 Aug 2018 • Rongtian Ye, Fangyu Liu, Liqiang Zhang

Standard 3D convolution operations require much larger amounts of memory and computation cost than 2D convolution operations.

General Classification

3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Clouds

no code implementations • ICCV 2017 • Fangyu Liu, Shuaipeng Li, Liqiang Zhang, Chenghu Zhou, Rongtian Ye, Yuebin Wang, Jiwen Lu

Our method provides an automatic process that maps the raw data to the classification results.

Classification General Classification +4