Learn More
Click modeling aims to interpret the users' search click data in order to predict their clicking behavior. Existing models can well characterize the position bias of documents and snippets in relation to users' mainstream click behavior. Yet, current advances depict users' search actions only in a general setting by implicitly assuming that all users act in(More)
Modeling a user's click-through behavior in click logs is a challenging task due to the well-known position bias problem. Recent advances in click models have adopted the examination hypothesis which distinguishes document relevance from position bias. In this paper, we revisit the examination hypothesis and observe that user clicks cannot be completely(More)
How to accurately interpret user click behaviour in search log is a key but challenging problem for search relevance. In this paper, we describe our solution to the relevance prediction challenge which achieves the first place among eligible teams. There are three stages in our solution: feature generation, feature augmentation and learning a ranking(More)
Recent advances in <i>click model</i> have positioned it as an effective approach to estimate document relevance based on user behavior in web search. Yet, few works have been conducted to explore the use of click model to help web search ranking. In this paper, we focus on learning a ranking function by taking the results from a click model into account.(More)
In this paper, we propose a novel control structure that can achieve fast, safe and precise landing of a VTOL (vertical takeoff and landing) UAV onto a vertically oscillating landing pad. The control structure consists of three modules to achieve these goals: a motion estimation module, a trajectory generation module and a tracking control module. In the(More)
The problem of de-anonymizing social networks is to identify the same users between two anonymized social networks [7] (Figure 1). Network de-anonymization task is of multifold significance, with user profile enrichment as one of its most promising applications. After the deanonymization and alignment, we can aggregate and enrich user profile information(More)
In this paper, the problem of landing an unmanned aerial vehicle (UAV) on a platform with unknown oscillating motion is investigated. A control architecture that enables fast, safe and precise landing process is proposed. This control architecture consists of three modules: a tracking control module, a trajectory generation module and a vision-based motion(More)
Hybrid Underwater Gliders (HUGs) integrate advantages of Autonomous Underwater Gliders (AUGs) with those of Autonomous Underwater Vehicles (AUVs). HUGs with buoyancy engine and the auxiliary propeller, compared with traditional AUGs, get more various and optimal motion modes, including glide in a saw tooth path with single buoyancy engine, thrust as(More)