• Publications
  • Influence
Single Shot Text Detector with Regional Attention
TLDR
A novel single-shot text detector that directly outputs word-level bounding boxes in a natural image and develops a hierarchical inception module which efficiently aggregates multi-scale inception features.
DeepDefense: Identifying DDoS Attack via Deep Learning
TLDR
A recurrent deep neural network to learn patterns from sequences of network traffic and trace network attack activities and reduces the error rate compared with conventional machine learning method in the larger data set.
DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization
TLDR
This paper proposes a novel dense bottom-up framework: DEnse Bottom-Up Grounding (DEBUG), which regards all frames falling in the ground truth segment as foreground, and each foreground frame regresses the unique distances from its location to bi-directional ground truth boundaries.
Guoguo: enabling fine-grained indoor localization via smartphone
TLDR
This paper designs and implements an indoor localization ecosystem Guoguo, which consists of an anchor network with a coordination protocol to transmit modulated localization beacons using high-band acoustic signals, a realtime processing app in a smartphone, and a backend server for indoor contexts and location-based services.
Rethinking the Bottom-Up Framework for Query-Based Video Localization
TLDR
It is argued that the performance of bottom-up framework is severely underestimated by current unreasonable designs, including both the backbone and head network, and designed a novel top-up model: Graph-FPN with Dense Predictions (GDP).
SinkTrail: A Proactive Data Reporting Protocol for Wireless Sensor Networks
TLDR
This work proposes two energy-efficient proactive data reporting protocols, S sinkTrail and SinkTrail-S, for mobile sink-based data collection, which feature low-complexity and reduced control overheads and demonstrate satisfactory performance in finding shorter routing paths.
IncMR: Incremental Data Processing Based on MapReduce
TLDR
Experiments show that non-iterative algorithms running in MapReduce framework can be migrated to IncMR directly to get efficient incremental and continuous processing without any modification.
GRAM-CNN: a deep learning approach with local context for named entity recognition in biomedical text
TLDR
This work proposes a novel end-to-end deep learning approach for biomedical NER tasks that leverages the local contexts based on n-gram character and word embeddings via Convolutional Neural Network (CNN), called GRAM-CNN.
MySurgeryRisk: Development and Validation of a Machine-learning Risk Algorithm for Major Complications and Death After Surgery
TLDR
An automated predictive analytics framework for machine-learning algorithm with high discriminatory ability for assessing the risk of surgical complications and death using readily available preoperative electronic health records data is constructed.
Adaptive Adversarial Attack on Scene Text Recognition
TLDR
This work proposes an adaptive approach to speed up adversarial attacks, especially on sequential learning tasks, by leveraging the uncertainty of each task to directly learn the adaptive multi-task weightings, without manually searching hyper-parameters.
...
...