Search Results for author: Wei-Shinn Ku

Found 9 papers, 6 papers with code

Multi-modal Transformer Path Prediction for Autonomous Vehicle

no code implementations15 Aug 2022 Chia Hong Tseng, Jie Zhang, Min-Te Sun, Kazuya Sakai, Wei-Shinn Ku

To better utilize the lane information, the lanes which are in opposite direction to target agent are not likely to be taken by the target agent and are consequently filtered out.

Autonomous Driving Trajectory Forecasting

RFID-Based Indoor Spatial Query Evaluation with Bayesian Filtering Techniques

1 code implementation2 Apr 2022 Bo Hui, Wenlu Wang, Jiao Yu, Zhitao Gong, Wei-Shinn Ku, Min-Te Sun, Hua Lu

Based on the inference method and tracking models, we develop innovative indoor range and k nearest neighbor (kNN) query algorithms.

Deep Multi-attribute Graph Representation Learning on Protein Structures

no code implementations22 Dec 2020 Tian Xia, Wei-Shinn Ku

To address the above challenges, we propose a new graph neural network architecture to represent the proteins as 3D graphs and predict both distance geometric graph representation and dihedral geometric graph representation together.

Graph Representation Learning

SpatialNLI: A Spatial Domain Natural Language Interface to Databases Using Spatial Comprehension

no code implementations28 Aug 2019 Jingjing Li, Wenlu Wang, Wei-Shinn Ku, Yingtao Tian, Haixun Wang

A natural language interface (NLI) to databases is an interface that translates a natural language question to a structured query that is executable by database management systems (DBMS).

Management Reading Comprehension

Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects

1 code implementation CVPR 2019 Michael A. Alcorn, Qi Li, Zhitao Gong, Chengfei Wang, Long Mai, Wei-Shinn Ku, Anh Nguyen

Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects in ImageNet.

A Transfer-Learnable Natural Language Interface for Databases

2 code implementations7 Sep 2018 Wenlu Wang, Yingtao Tian, Hongyu Xiong, Haixun Wang, Wei-Shinn Ku

In this work, we introduce a general purpose transfer-learnable NLI with the goal of learning one model that can be used as NLI for any relational database.

Management Natural Language Queries

Adversarial Texts with Gradient Methods

1 code implementation22 Jan 2018 Zhitao Gong, Wenlu Wang, Bo Li, Dawn Song, Wei-Shinn Ku

In addition, we empirically show that WMD is closely related to the quality of adversarial texts.

Adversarial and Clean Data Are Not Twins

1 code implementation17 Apr 2017 Zhitao Gong, Wenlu Wang, Wei-Shinn Ku

Adversarial attack has cast a shadow on the massive success of deep neural networks.

Adversarial Attack

Cannot find the paper you are looking for? You can Submit a new open access paper.