Haojian Jin


MobiPurpose: Inferring the Purposes of Network Traffic in Mobile Apps
Haojian Jin, Minyi Liu, Kevan Dohia, Yuanchun Li, Gaurav Kumar Srivastava, Matthew Fredrikson, Yuvraj Agarwal and Jason Hong. (IMWUT '18 / UbiComp '19). [paper] [data set] [traffic harness tools]

Many smartphone apps collect potentially sensitive personal data and send it to cloud servers. However, it can be difficult to understand what data is being collected, where it is being sent to, and why. MobiPurpose infers fine-grained privacy attributes of outgoing smartphone network traffic, regarding who, where, what (e.g., location, tracking ID, email address, etc.), and why (e.g., advertising, marketing analytics, maps, etc.).


WiSh: Towards a Wireless Shape-aware World using Passive RFIDs
Haojian Jin*, Jingxian Wang*, Zhijian Yang, Swarun Kumar, and Jason Hong (MobiSys '18).
*co-primary authors. [paper] [presentation] [talk video] [project video]

WiSh makes ordinary surfaces "shape-aware" using attached inexpensive, light-weight and battery-free RFID tags. WiSh can enable many new applications: shape-aware clothing that can detect a user's posture, interactive shape-aware toys or even shape-aware bridges that report their structural health.

RFWear: Towards Wearable Everyday Body-Frame Tracking using Passive RFIDs.
Haojian Jin, Zhijian Yang, Swarun Kumar, and Jason Hong (IMWUT '17 / UbiComp '18).
[paper] [presentation] [video]
Ubicomp & ISWC 2018 Best Demo Honorable Mention (2/51)

RFWear is a first-of-its-kind body-frame tracking mechanism that is lightweight and convenient for day-to-day use, without relying on external infrastructure. RFWear processes wireless signals reflected off passive RFID tags to track movements of a user’s body.

ElasticPlay: Interactive Video Summarization with Dynamic Time Budgets.
Haojian Jin, Yale Song, and Koji Yatani (ACMMM '17). [paper] [video] [presentation] [live demo]
Oral presentation - top 7%

We argue that video summarization should be an interactive, mixed-initiative process in which users have control over the summarization procedure, while algorithms help users achieve their goal via video understanding.

Corona: Positioning Adjacent Device with Asymmetric Bluetooth Low Energy RSSI Distributions.
Haojian Jin, Cheng Xu, and Kent Lyons (UIST '15). [paper] [presentation] [video] [open source by ota42y]

Corona is a novel spatial sensing technique that implicitly locates adjacent mobile devices by examining asymmetric Bluetooth Low Energy RSSI distributions. The phenomenon underlying Corona is that the Bluetooth RSSI distributions around the device are distinguishable because of the off-center antenna and asymmetric radio frequency field pattern.

Tracko: Ad-hoc Mobile 3D Tracking Using BLE and Inaudible Signals for Cross-Device Interaction.
Haojian Jin, Christian Holz, Kasper Hornbæk (UIST '15). [paper] [presentation] [video]

Tracko is a relative 3D tracking system between two or more commodity devices without added components or device synchronization. Tracko achieves this by fusing three signal types: bluetooth low energy, inaudible stereo sounds and onboard inertial sensors.

ReviewCollage: A Mobile Interface for Direct Comparison Using Online Reviews.
Haojian Jin, Tetsuya Sakai, and Koji Yatani (MobileHCI 2014). [paper] [presentation] [video]
Best Paper Honorable Mention Award, top 5%

Review comments posted in online websites can help the user decide a product to purchase or place to visit. They can also be useful to closely compare a couple of candidate entities. However, the user may have to read different webpages back and forth for comparison, and this is not desirable particularly when she is using a mobile device. We present ReviewCollage, a mobile interface that aggregates information about two reviewed entities in a one-page view.

Mobile HCI
Mining Touch Interaction Data in Mobile Search
Qi Guo, Haojian Jin, Dmitry Lagun, Shuai Yuan, and Eugene Agichtein.

"Mining touch interaction data on mobile devices to predict web search result relevance," In Proceedings of SIGIR 2013 [paper]
"Towards estimating web search result relevance from touch interactions on mobile devices," In SIGCHI 2013 Extended Abstracts [paper].

acm computing reviews
Mobile HCI

Finding Weather Photos: Community-Supervised Methods for Editorial Curation of Online Sources
David A. Shamma, Lyndon Kennedy, Jia Li, Bart Thomee, Haojian Jin, Jeff Yuan (CSCW'16). [paper]

Yahoo Project Weather is an ecosystem that surfaces beautiful weather photos from around the world that could potentially be used in the Yahoo Weather app as a representation of weather conditions in a given area. In this work, we present a large-scale system implementation on a real-world curative task for weather images on a web-scale dataset. Researchers Explain the Science Powering Yahoo Weather.


The Cohort and Speechify Libraries for Rapid Construction of Speech Enabled Applications
Tejaswi Kasturi, Haojian Jin, Aasish Pappu, Sungjin Lee, Beverly Harrison, Ramana Murthy, Amanda Stent (SIGDIAL 2015) [paper]

Despite the prevalence of libraries that provide speech recognition and text-to-speech synthesis “in the cloud”, it remains difficult for developers to create user-friendly, consistent spoken language interfaces to their mobile applications. In this paper, we present the Speechify / Cohort libraries for rapid speech enabling of Android applications.

The Cohort library, built on a stripped-down version of OpenDial, facilitates flexible interaction between and within various “Speechified” Yahoo mobile applications.

memory impairment detection
Web-based Behavioral Diagnostics for early detection of memory impairment

Deficits in memory are the clinical hallmark of Alzheimer's disease. Visual Paired Comparison (VPC) task is a recognition memory task that assesses the proportion of time an individual spends viewing a novel picture compared to a recently seen (familiar) picture. This project proposed a web-based test to measures visual recognition memory by observing how a patient views familiar or novel images which has been shown to be effective in the clinical setting.

[project page]

A continuously improving search engine with Click-through data

Sharp Search is a personalized search engine which can automatically optimize the retrieval quality of search using clickthrough data. In this project, I focused on the clickthough data in a search engine, and re-calculate the relevance score based on my click history. From May 3rd to June 3rd 2010, I hosted Sharp search on my laptop and collected all my search queries and behavior data for this experiment.

[project page]

Chinese word segmentation

This project was a part of the project "Culture Grid - Dunhuang" in Knowledge Grid Group. "Dunhuang" is an important tourist attraction and the subject of lots of ongoing archaeological projects. The goal of "Culture Grid" is to manage the continuous research progress in Archaeology research and improve the sociologists' collaboration. Since most manuscripts are written in classical Chinese, this project was to implement the information extraction in classical Chinese.

[project page]