arXiv subjects

Bo Hu

Publications and source records attributed to Bo Hu.

At least 127 records · Page 7Linked to original sources

arXiv2019

Locality-constrained Spatial Transformer Network for Video Crowd Counting

Compared with single image based crowd counting, video provides the spatial-temporal information of the crowd that would help improve the robustness of crowd counting. But translation, rotation and scaling of people lead to the change of density map of heads between neighbouring frames. Meanwhile, people walking in/out or being occluded in dynamic scenes leads to the change of head counts. To alleviate these issues in video crowd counting, a Locality-constrained Spatial Transformer Network (LSTN) is proposed. Specifically, we first leverage a Convolutional Neural Networks to estimate the density map for each frame. Then to relate the density maps between neighbouring frames, a Locality-constrained Spatial Transformer (LST) module is introduced to estimate the density map of next frame with that of current frame. To facilitate the performance evaluation, a large-scale video crowd counting dataset is collected, which contains 15K frames with about 394K annotated heads captured from 13 different scenes. As far as we know, it is the largest video crowd counting dataset. Extensive experiments on our dataset and other crowd counting datasets validate the effectiveness of our LSTN for crowd counting.

cs.CV↗

arXiv2019

Learning for Matching Game in Cooperative D2D Communication with Incomplete Information

This paper considers a cooperative device-to-device (D2D) communication system, where the D2D transmitters (DTs) act as relays to assist cellular users (CUs) in exchange for the opportunities to use licensed spectrum. Based on the interaction of each D2D pair and each CU, we formulate the pairing problem between multiple cues and multiple D2D pairs as a one-to-one matching game. Unlike most existing works, we consider a realistic scenario with incomplete channel information. Thus, each CU lacks enough information to establish its preference over D2D pairs. Therefore, traditional matching algorithms are not suitable for our scenario. To this end, we convert the matching game to an equivalent non-cooperative game, and then propose a novel learning algorithm, which converges to a stable matching.

cs.IT↗

arXiv2019

Parallaxes for star forming regions in the inner Perseus spiral arm

We report trigonometric parallax and proper motion measurements of 6.7-GHz CH3OH and 22-GHz H2O masers in eight high-mass star-forming regions (HMSFRs) based on VLBA observations as part of the BeSSeL Survey. The distances of these HMSFRs combined with their Galactic coordinates, radial velocities, and proper motions, allow us to assign them to a segment of the Perseus arm with ~< 70 deg. These HMSFRs are clustered in Galactic longitude from ~30 deg to ~50, neighboring a dirth of such sources between longitudes ~50 deg to ~90 deg.

astro-ph.GA↗

arXiv2019

Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos

Previous spatial-temporal action localization methods commonly follow the pipeline of object detection to estimate bounding boxes and labels of actions. However, the temporal relation of an action has not been fully explored. In this paper, we propose an end-to-end Progress Regression Recurrent Neural Network (PR-RNN) for online spatial-temporal action localization, which learns to infer the action by temporal progress regression. Two new action attributes, called progression and progress rate, are introduced to describe the temporal engagement and relative temporal position of an action. In our method, frame-level features are first extracted by a Fully Convolutional Network (FCN). Subsequently, detection results and action progress attributes are regressed by the Convolutional Gated Recurrent Unit (ConvGRU) based on all the observed frames instead of a single frame or a short clip. Finally, a novel online linking method is designed to connect single-frame results to spatial-temporal tubes with the help of the estimated action progress attributes. Extensive experiments demonstrate that the progress attributes improve the localization accuracy by providing more precise temporal position of an action in unconstrained videos. Our proposed PR-RNN achieves the stateof-the-art performance for most of the IoU thresholds on two benchmark datasets.

cs.CV↗

arXiv2019

Active Sampling for Approximately Bandlimited Graph Signals

This paper investigates the active sampling for estimation of approximately bandlimited graph signals. With the assistance of a graph filter, an approximately bandlimited graph signal can be formulated by a Gaussian random field over the graph. In contrast to offline sampling set design methods which usually rely on accurate prior knowledge about the model, unknown parameters in signal and noise distribution are allowed in the proposed active sampling algorithm. The active sampling process is divided into two alternating stages: unknown parameters are first estimated by Expectation Maximization (EM), with which the next node to sample is selected based on historical observations according to predictive uncertainty. Validated by simulations compared with related approaches, the proposed algorithm can reduce the sample size to reach a certain estimation accuracy.

eess.SP↗

arXiv2019

Surveys of Clumps, Cores, and Condensations in Cygnus X: I. a New Catalog of ~0.1 pc Massive Dense Cores

Using infrared to (sub)millimeter data from Spitzer, Herschel, the James Clerk Maxwell Telescope, and the IRAM 30-m telescope, we conducted an unbiased survey of the massive dense cores (MDCs) in the Cygnus X molecular cloud complex, aimed at characterizing the physical conditions of high-mass star formation (HMSF) at ~0.1 pc scales. We created 5 deg times 6 deg images of the 70-1200 um dust continuum, gas column density, and dust temperature of Cygnus X. A spatial relation between the dense regions (Av > 15) and the developed HII regions was found, indicating the impact of the latter on the global structures of Cygnus X. With a 35-Msun mass threshold implied by HMSF signposts, we identified 151 MDCs with sizes of ~0.1 pc, masses of 35-1762 Msun, and temperatures of 8-35 K. Our MDC sample is statistically complete in Cygnus X and is three times larger than that in Motte et al. (2007). The MDCs were classified into IR-bright/IR-quiet ones based on their mid-infrared fluxes and a large "IR-quiet" proportion (90%) was found in our sample. Two possible scenarios were proposed to interpret this: accelerated HMSF and the incapability of HMSF of the IR-quiet MDCs. We also found 26 starless MDCs by their lack of compact emissions at 21-70 um wavelengths, of which the most massive ones are probably the best candidates of initial HMSF sites in Cygnus X.

astro-ph.GA↗

arXiv2018

Cooperative Spectrum Sharing Between D2D Users and Edge-Users: A Matching Theory Perspective

The device-to-device (D2D) communication theoretically provides both the cellular traffic offloading and convenient content delivery directly among proximity users. However, in practice, no matter in underlay or overlay mode, the employment of D2D may impair the performance of the cellular links. Therefore, it is important to design a spectrum sharing scheme, under which the performance of both links can be improved simultaneously. In this paper, we consider the cell-edge user (CEU) scenario, where both sides have the demand to improve the quality of experience or service. Therefore, CEUs and D2D users both have intentions to form pairs, namely, CEU-D2D pairs, to cooperate mutually. Different from the conventional equilibrium point evaluation, the stable matching between D2D users and CEUs are formulated under matching theory framework instead. For each CEU-D2D pair, a two-stage pricing-based Stackelberg game is modeled to describe the willingness to cooperate, where the win-win goal is reached finally.

cs.IT↗

arXiv2018

A Cascaded Channel-Power Allocation for D2D Underlaid Cellular Networks Using Matching Theory

We consider a device-to-device (D2D) underlaid cellular network, where each cellular channel can be shared by several D2D pairs and only one channel can be allocated to each D2D pair. We try to maximize the sum rate of D2D pairs while limiting the interference to cellular links. Due to the lack of global information in large scale networks, resource allocation is hard to be implemented in a centralized way. Therefore, we design a novel distributed resource allocation scheme which is based on local information and requires little coordination and communication between D2D pairs. Specifically, we decompose the original problem into two cascaded subproblems, namely channel allocation and power control. The cascaded structure of our scheme enables us to cope with them respectively. Then a two-stage algorithm is proposed. In the first stage, we model the channel allocation problem as a many-to-one matching with externalities and try to find a strongly swap-stable matching. In the second stage, we adopt a pricing mechanism and develop an iterative two-step algorithm to solve the power control problem.

cs.IT↗

arXiv2018

Robust Beamforming for Downlink 3D-MIMO Systems with $l_1$-norm Bounded CSI Uncertainty

In this paper, a novel robust beamforming scheme is proposed in three dimensional multi-input multi-output (3D-MIMO) systems. As one of the typical deployments of massive MIMO, a 3D-MIMO system owns sparse channels in angular domain. Thus, various of sparse channel estimation algorithms produce sparse channel estimation errors which can be utilized to narrow down the perturbation region of imperfect CSI. We investigate a $l_1$-norm bounded channel uncertainty model for the robust beamforming problems, which captures the sparse nature of channel errors. Compared with the conventional spherical uncertainty, we prove that the scheme with $l_1$-norm bounded uncertainty consumes less beamforming power with the same signal to interference and noise ratio (SINR) thresholds. The proposed scheme is reformulated as a second-order cone programming (SOCP) and simulation results verify the effectiveness of our algorithm.

eess.SP↗

arXiv2018

Talent Search and Recommendation Systems at LinkedIn: Practical Challenges and Lessons Learned

LinkedIn Talent Solutions business contributes to around 65% of LinkedIn's annual revenue, and provides tools for job providers to reach out to potential candidates and for job seekers to find suitable career opportunities. LinkedIn's job ecosystem has been designed as a platform to connect job providers and job seekers, and to serve as a marketplace for efficient matching between potential candidates and job openings. A key mechanism to help achieve these goals is the LinkedIn Recruiter product, which enables recruiters to search for relevant candidates and obtain candidate recommendations for their job postings. In this work, we highlight a set of unique information retrieval, system, and modeling challenges associated with talent search and recommendation systems.

cs.AI↗

arXiv2018

Towards Deep and Representation Learning for Talent Search at LinkedIn

Talent search and recommendation systems at LinkedIn strive to match the potential candidates to the hiring needs of a recruiter or a hiring manager expressed in terms of a search query or a job posting. Recent work in this domain has mainly focused on linear models, which do not take complex relationships between features into account, as well as ensemble tree models, which introduce non-linearity but are still insufficient for exploring all the potential feature interactions, and strictly separate feature generation from modeling. In this paper, we present the results of our application of deep and representation learning models on LinkedIn Recruiter. Our key contributions include: (i) Learning semantic representations of sparse entities within the talent search domain, such as recruiter ids, candidate ids, and skill entity ids, for which we utilize neural network models that take advantage of LinkedIn Economic Graph, and (ii) Deep models for learning recruiter engagement and candidate response in talent search applications. We also explore learning to rank approaches applied to deep models, and show the benefits for the talent search use case. Finally, we present offline and online evaluation results for LinkedIn talent search and recommendation systems, and discuss potential challenges along the path to a fully deep model architecture. The challenges and approaches discussed generalize to any multi-faceted search engine.

cs.LG↗

arXiv2018

Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks

The visual attributes of cells, such as the nuclear morphology and chromatin openness, are critical for histopathology image analysis. By learning cell-level visual representation, we can obtain a rich mix of features that are highly reusable for various tasks, such as cell-level classification, nuclei segmentation, and cell counting. In this paper, we propose a unified generative adversarial networks architecture with a new formulation of loss to perform robust cell-level visual representation learning in an unsupervised setting. Our model is not only label-free and easily trained but also capable of cell-level unsupervised classification with interpretable visualization, which achieves promising results in the unsupervised classification of bone marrow cellular components. Based on the proposed cell-level visual representation learning, we further develop a pipeline that exploits the varieties of cellular elements to perform histopathology image classification, the advantages of which are demonstrated on bone marrow datasets.

cs.CV↗

arXiv2018

Deploying Deep Ranking Models for Search Verticals

In this paper, we present an architecture executing a complex machine learning model such as a neural network capturing semantic similarity between a query and a document; and deploy to a real-world production system serving 500M+users. We present the challenges that arise in a real-world system and how we solve them. We demonstrate that our architecture provides competitive modeling capability without any significant performance impact to the system in terms of latency. Our modular solution and insights can be used by other real-world search systems to realize and productionize recent gains in neural networks.

cs.IR↗

arXiv2017

Design of Sampling Set for Bandlimited Graph Signal Estimation

It is of particular interest to reconstruct or estimate bandlimited graph signals, which are smoothly varying signals defined over graphs, from partial noisy measurements. However, choosing an optimal subset of nodes to sample is NP-hard. We formularize the problem as the experimental design of a linear regression model if we allow multiple measurements on a single node. By relaxing it to a convex optimization problem, we get the proportion of sample for each node given the budget of total sample size. Then, we use a probabilistic quantization to get the number of each node to be sampled. Moreover, we analyze how the sample size influences whether our object function is well-defined by perturbation analysis. Finally, we demonstrate the performance of the proposed approach through various numerical experiments.

eess.SP↗

arXiv2017

Thermodynamics of Two-impurity Anderson Model with Dzyaloshinskii-Moriya Interaction

In this work, we use the numerical renormalization group (NRG) theory to study the thermodynamics of the two-impurity Anderson model. Two different methods are used to estimate the effect of the Dzyaloshiskii-Moriya (DM) interaction on the variation of the Kondo temperature. When the Ruderman-Kittel-Kasuya-Yosida (RKKY) interaction is vanishing, the two different estimations give different tendency. If we use the peak of the specific heat to identify the variation of the Kondo temperature versus the Dzyaloshiskii-Moriya interaction, we get an almost linear function. However, if we use the low temperature universal curve of the impurity entropy, we get a quadratic function. These results indicate that the previous debates about the influence of the spin-orbit coupling on the Kondo temperature may come from the different definitions of the Kondo temperature. When the RKKY interaction is ferromagnetic, there are two stages of the Kondo screening. Both the two estimations demonstrate that the second stage of the Kondo temperature is exponentially dependent on the DM interaction. There results are dramatically different from those calculated via perturbation theory.

cond-mat.str-el↗

arXiv2017

Traffic-Aware Transmission Mode Selection in D2D-enabled Cellular Networks with Token System

We consider a D2D-enabled cellular network where user equipments (UEs) owned by rational users are incentivized to form D2D pairs using tokens. They exchange tokens electronically to "buy" and "sell" D2D services. Meanwhile the devices have the ability to choose the transmission mode, i.e. receiving data via cellular links or D2D links. Thus taking the different benefits brought by diverse traffic types as a prior, the UEs can utilize their tokens more efficiently via transmission mode selection. In this paper, the optimal transmission mode selection strategy as well as token collection policy are investigated to maximize the long-term utility in the dynamic network environment. The optimal policy is proved to be a threshold strategy, and the thresholds have a monotonicity property. Numerical simulations verify our observations and the gain from transmission mode selection is observed.

cs.IT↗

arXiv2016

On the Relationship of UC H II Regions and Class II Methanol Masers: I. Source Catalogs

We conducted VLA C-configuration observations to measure positions and luminosities of Galactic Class II 6.7 GHz methanol masers and their associated ultra-compact H II regions. The spectral resolution was 3.90625 kHz and the continuum sensitivity reached 45 \uJypb. We mapped 372 methanol masers with peak flux densities of more than 2 Jy selected from the literature, 367 of them were detected. Absolute positions have nominal uncertainties of 0.3 arcsec. In this first paper on the data analysis, we present three catalogs, the first gives information on the strongest feature of 367 methanol maser sources, and the second on all detected maser spots. The third catalog present derived data of the 279 radio continuum sources found in the vicinity of maser sources. Among them, 140 show evidence of physical association with maser sources. Our catalogs list properties including distance, flux density, radial velocity and the distribution of masers on the Galactic plane is then provided as well. We found no significant relationship between luminosities of masers and their associated radio continuum counterparts.

astro-ph.GA↗

arXiv2016

QoE-Aware Proactive Caching of Scalable Videos Over Small Cell Networks

The explosion of mobile video traffic imposes tremendous challenges on present cellular networks. To alleviate the pressure on backhaul links and to enhance the quality of experience (QoE) of video streaming service, small cell base stations (SBS) with caching ability are introduced to assist the content delivery. In this paper, we present the first study on the optimal caching strategy of scalable video coding (SVC) streaming in small cell networks with the consideration of channel diversity and video scalability. We formulate an integer programming problem to maximize the average SVC QoE under the constraint of cache size at each SBS. By establishing connections between QoE and caching state of each video, we simplify the proactive caching of SVC as a multiple-choice knapsack problem (MCKP), and propose a low-complexity algorithm using dynamic programming. Our proactive caching strategy reveals the structural properties of cache allocation to each video based on their popularity profiles. Simulation results manifest that the SBSs with caching ability can greatly improve the average QoE of SVC streaming service, and that our proposed caching strategy acquires significant performance gain compared with other conventional caching policies.

cs.NI↗