T
Ting Wang
Researcher at Westlake University
Publications - 6
Citations - 23
Ting Wang is an academic researcher from Westlake University. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 2, co-authored 4 publications receiving 8 citations. Previous affiliations of Ting Wang include Zhejiang University.
Papers
More filters
Posted Content
Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning
TL;DR: This brief proposes a visual perception generalization strategy based on meta-learning, which enables the agent to fast adapt to a new camera configuration and compares two meta- learning algorithms for better generalization in seen and unseen environments.
Journal ArticleDOI
Improved Speaker and Navigator for Vision-and-Language Navigation
TL;DR: This article proposes novel Transformer-based multimodal frameworks for the navigator and speaker, respectively, where the multihead self-attention with the residual connection is used to carry the information flow.
Proceedings ArticleDOI
Improved Graph-Based Semi-Supervised Learning for Fingerprint-Based Indoor Localization
TL;DR: An improved graph-based semi-supervised learning (I-GSSL) algorithm is proposed to better overcome the labor intensity and time consumption of data collection in fingerprint based localization.
Proceedings ArticleDOI
WiFi Fingerprint Based Indoor Localization with Iterative Weighted KNN for WiFi AP Missing
TL;DR: A dedicated data preprocessing algorithm to solve the singular-collection problem is proposed and experimental results shows the proposed scheme achieves a competitive localization accuracy.
Journal ArticleDOI
Graph based Environment Representation for Vision-and-Language Navigation in Continuous Environments
TL;DR: Zhang et al. as discussed by the authors proposed an Environment Representation Graph (ERG) through object detection to express the environment in semantic level, and the relational representations of object-object, object-agent in ERG are learned through GCN, so as to obtain a continuous expression about ERG.