Searcharxiv⌕ Search

arXiv subjects

Hao Fang

Publications and source records attributed to Hao Fang.

At least 145 records · Page 8Linked to original sources
arXiv2021

Salient Object Ranking with Position-Preserved Attention

Instance segmentation can detect where the objects are in an image, but hard to understand the relationship between them. We pay attention to a typical relationship, relative saliency. A closely related task, salient object detection, predicts a binary map highlighting a visually salient region while hard to distinguish multiple objects. Directly combining two tasks by post-processing also leads to poor performance. There is a lack of research on relative saliency at present, limiting the practical applications such as content-aware image cropping, video summary, and image labeling. In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency. We propose the first end-to-end framework of the SOR task and solve it in a multi-task learning fashion. The framework handles instance segmentation and salient object ranking simultaneously. In this framework, the SOR branch is independent and flexible to cooperate with different detection methods, so that easy to use as a plugin. We also introduce a Position-Preserved Attention (PPA) module tailored for the SOR branch. It consists of the position embedding stage and feature interaction stage. Considering the importance of position in saliency comparison, we preserve absolute coordinates of objects in ROI pooling operation and then fuse positional information with semantic features in the first stage. In the feature interaction stage, we apply the attention mechanism to obtain proposals' contextualized representations to predict their relative ranking orders. Extensive experiments have been conducted on the ASR dataset. Without bells and whistles, our proposed method outperforms the former state-of-the-art method significantly. The code will be released publicly available.

cs.CV↗
arXiv2021

Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease

Speech disorders often occur at the early stage of Parkinson's disease (PD). The speech impairments could be indicators of the disorder for early diagnosis, while motor symptoms are not obvious. In this study, we constructed a new speech corpus of Mandarin Chinese and addressed classification of patients with PD. We implemented classical machine learning methods with ranking algorithms for feature selection, convolutional and recurrent deep networks, and an end to end system. Our classification accuracy significantly surpassed state-of-the-art studies. The result suggests that free talk has stronger classification power than standard speech tasks, which could help the design of future speech tasks for efficient early diagnosis of the disease. Based on existing classification methods and our natural speech study, the automatic detection of PD from daily conversation could be accessible to the majority of the clinical population.

eess.AS↗
arXiv2021

RESA: Recurrent Feature-Shift Aggregator for Lane Detection

Lane detection is one of the most important tasks in self-driving. Due to various complex scenarios (e.g., severe occlusion, ambiguous lanes, etc.) and the sparse supervisory signals inherent in lane annotations, lane detection task is still challenging. Thus, it is difficult for the ordinary convolutional neural network (CNN) to train in general scenes to catch subtle lane feature from the raw image. In this paper, we present a novel module named REcurrent Feature-Shift Aggregator (RESA) to enrich lane feature after preliminary feature extraction with an ordinary CNN. RESA takes advantage of strong shape priors of lanes and captures spatial relationships of pixels across rows and columns. It shifts sliced feature map recurrently in vertical and horizontal directions and enables each pixel to gather global information. RESA can conjecture lanes accurately in challenging scenarios with weak appearance clues by aggregating sliced feature map. Moreover, we propose a Bilateral Up-Sampling Decoder that combines coarse-grained and fine-detailed features in the up-sampling stage. It can recover the low-resolution feature map into pixel-wise prediction meticulously. Our method achieves state-of-the-art results on two popular lane detection benchmarks (CULane and Tusimple). Code has been made available at: https://github.com/ZJULearning/resa.

cs.CV↗
arXiv2021

Task-Oriented Dialogue as Dataflow Synthesis

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people. Experiments show that dataflow graphs and metacomputation substantially improve representability and predictability in these natural dialogues. Additional experiments on the MultiWOZ dataset show that our dataflow representation enables an otherwise off-the-shelf sequence-to-sequence model to match the best existing task-specific state tracking model. The SMCalFlow dataset and code for replicating experiments are available at https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines.

cs.CL↗
arXiv2020

Building A User-Centric and Content-Driven Socialbot

To build Sounding Board, we develop a system architecture that is capable of accommodating dialog strategies that we designed for socialbot conversations. The architecture consists of a multi-dimensional language understanding module for analyzing user utterances, a hierarchical dialog management framework for dialog context tracking and complex dialog control, and a language generation process that realizes the response plan and makes adjustments for speech synthesis. Additionally, we construct a new knowledge base to power the socialbot by collecting social chat content from a variety of sources. An important contribution of the system is the synergy between the knowledge base and the dialog management, i.e., the use of a graph structure to organize the knowledge base that makes dialog control very efficient in bringing related content to the discussion. Using the data collected from Sounding Board during the competition, we carry out in-depth analyses of socialbot conversations and user ratings which provide valuable insights in evaluation methods for socialbots. We additionally investigate a new approach for system evaluation and diagnosis that allows scoring individual dialog segments in the conversation. Finally, observing that socialbots suffer from the issue of shallow conversations about topics associated with unstructured data, we study the problem of enabling extended socialbot conversations grounded on a document. To bring together machine reading and dialog control techniques, a graph-based document representation is proposed, together with methods for automatically constructing the graph. Using the graph-based representation, dialog control can be carried out by retrieving nodes or moving along edges in the graph. To illustrate the usage, a mixed-initiative dialog strategy is designed for socialbot conversations on news articles.

cs.CL↗
arXiv2020

Solving A Class of Nonsmooth Resource Allocation Problems with Directed Graphs though Distributed Smooth Multi-Proximal Algorithms

In this paper, two distributed multi-proximal primal-dual algorithms are proposed to deal with a class of distributed nonsmooth resource allocation problems. In these problems, the global cost function is the summation of local convex and nonsmooth cost functions, each of which consists of one twice differentiable function and multiple nonsmooth functions. Communication graphs of underling multi-agent systems are directed and strongly connected but not necessarily weighted-balanced. The multi-proximal splitting is designed to deal with the difficulty caused by the unproximable property of the summation of those nonsmooth functions. Moreover, it can also guarantee the smoothness of proposed algorithms. Auxiliary variables in the multi-proximal splitting are introduced to estimate subgradients of nonsmooth functions. Theoretically, the convergence analysis is conducted by employing Lyapunov stability theory and integral input-to-state stability (iISS) theory with respect to set. It shows that proposed algorithms can make states converge to the optimal point that satisfies resource allocation conditions.

math.OC↗
arXiv2020

Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation

Data sharing for medical research has been difficult as open-sourcing clinical data may violate patient privacy. Traditional methods for face de-identification wipe out facial information entirely, making it impossible to analyze facial behavior. Recent advancements on whole-body keypoints detection also rely on facial input to estimate body keypoints. Both facial and body keypoints are critical in some medical diagnoses, and keypoints invariability after de-identification is of great importance. Here, we propose a solution using deepfake technology, the face swapping technique. While this swapping method has been criticized for invading privacy and portraiture right, it could conversely protect privacy in medical video: patients' faces could be swapped to a proper target face and become unrecognizable. However, it remained an open question that to what extent the swapping de-identification method could affect the automatic detection of body keypoints. In this study, we apply deepfake technology to Parkinson's disease examination videos to de-identify subjects, and quantitatively show that: face-swapping as a de-identification approach is reliable, and it keeps the keypoints almost invariant, significantly better than traditional methods. This study proposes a pipeline for video de-identification and keypoint preservation, clearing up some ethical restrictions for medical data sharing. This work could make open-source high quality medical video datasets more feasible and promote future medical research that benefits our society.

cs.CV↗
arXiv2019

An Investigation of Magnetic Hysteresis Error in Kibble Balances

Yoke-based permanent magnetic circuits are widely used in Kibble balance experiments. In these magnetic systems, the coil current, with positive and negative signs in two steps of the weighing measurement, can cause an additional magnetic flux in the circuit and hence a magnetic field change at the coil position. The magnetic field change due to the coil current and related systematic effects have been studied with the assumption that the yoke material does not contain any magnetic hysteresis. In this paper, we present an explanation of the magnetic hysteresis error in Kibble balance measurements. An evaluation technique based on measuring yoke minor hysteresis loops is proposed to estimate the effect. The dependence of the magnetic hysteresis effect and some possible optimizations for suppressing this effect are discussed.

physics.ins-det↗
arXiv2019

Distributed Global Output-Feedback Control for a Class of Euler-Lagrange Systems

This published paper investigates the distributed tracking control problem for a class of Euler-Lagrange multi-agent systems when the agents can only measure the positions. In this case, the lack of the separation principle and the strong nonlinearity in unmeasurable states pose severe technical challenges to global output-feedback control design. To overcome these difficulties, a global nonsingular coordinate transformation matrix in the upper triangular form is firstly proposed such that the nonlinear dynamic model can be partially linearized with respect to the unmeasurable states. And, a new type of velocity observers is designed to estimate the unmeasurable velocities for each system. Then, based on the outputs of the velocity observers, we propose distributed control laws that enable the coordinated tracking control system to achieve uniform global exponential stability (UGES). Both theoretical analysis and numerical simulations are presented to validate the effectiveness of the proposed control scheme. Followed by the original paper, a typo and a mistake is corrected.

eess.SY↗
arXiv2019

Distributed Nonsmooth Robust Resource Allocation with Cardinality Constrained Uncertainty

A distributed nonsmooth robust resource allocation problem with cardinality constrained uncertainty is investigated in this paper. The global objective is consisted of local objectives, which are convex but nonsmooth. Each agent is constrained in its private convex set and has only the information of its corresponding local objective. The resource allocation condition is subject to the cardinality constrained uncertainty sets. By employing the duality theory of convex optimization, a dual problem of the robust resource allocation problem is presented. For solving this dual problem, a distributed primal-dual projected algorithm is proposed. Theoretically, the convergence analysis by using stability theory of differential inclusions is conducted. It shows that the algorithm can steer the multi-agent system to satisfy resource allocation condition at the optimal solution. In the end, a nontrivial simulation is shown and the results demonstrate the efficiency of the proposed algorithm.

math.OC↗
arXiv2019

$σ_2$ Yamabe problem on conic 4-spheres

We discuss the constant $σ_{2}$ problem for conic 4-spheres. Based on earlier works of Chang-Han-Yang and Han-Li-Teixeira, we are able to find a necessary condition for the existence problem. In particular, when the condition is sharp, we have the uniqueness result similar to that of Troyanov in dimension 2. It indicates that the boundary of the moduli of all conic 4-spheres with constant $σ_{2}$ metrics consists of conic spheres with 2 conic points and rotational symmetry.

math.DG↗
arXiv2018

A Smooth Double Proximal Primal-Dual Algorithm for a Class of Distributed Nonsmooth Optimization Problem

This technical note studies a class of distributed nonsmooth convex consensus optimization problem. The cost function is a summation of local cost functions which are convex but nonsmooth. Each of the local cost functions consists of a twice differentiable convex function and two lower semi-continuous convex functions. We call this problem as single-smooth plus double-nonsmooth (SSDN) problem. Under mild conditions, we propose a distributed double proximal primal-dual optimization algorithm. The double proximal operator is designed to deal with the difficulty caused by the unproximable property of the summation of those two nonsmooth functions. Besides, it can also guarantee that the proposed algorithm is locally Lipschitz continuous. An auxiliary variable in the double proximal operator is introduced to estimate the subgradient of the second nonsmooth function. Theoretically, we conduct the convergence analysis by employing Lyapunov stability theory. It shows that the proposed algorithm can make the states achieve consensus at the optimal point. In the end, nontrivial simulations are presented and the results demonstrate the effectiveness of the proposed algorithm.

math.OC↗
arXiv2018

Sounding Board: A User-Centric and Content-Driven Social Chatbot

We present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize. The system architecture consists of several components including spoken language processing, dialogue management, language generation, and content management, with emphasis on user-centric and content-driven design. We also share insights gained from large-scale online logs based on 160,000 conversations with real-world users.

cs.HC↗
arXiv2016

Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions

Many social media platforms offer a mechanism for readers to react to comments, both positively and negatively, which in aggregate can be thought of as community endorsement. This paper addresses the problem of predicting community endorsement in online discussions, leveraging both the participant response structure and the text of the comment. The different types of features are integrated in a neural network that uses a novel architecture to learn latent modes of discussion structure that perform as well as deep neural networks but are more interpretable. In addition, the latent modes can be used to weight text features thereby improving prediction accuracy.

cs.SI↗
arXiv2016

Bi-directional Attention with Agreement for Dependency Parsing

We develop a novel bi-directional attention model for dependency parsing, which learns to agree on headword predictions from the forward and backward parsing directions. The parsing procedure for each direction is formulated as sequentially querying the memory component that stores continuous headword embeddings. The proposed parser makes use of {\it soft} headword embeddings, allowing the model to implicitly capture high-order parsing history without dramatically increasing the computational complexity. We conduct experiments on English, Chinese, and 12 other languages from the CoNLL 2006 shared task, showing that the proposed model achieves state-of-the-art unlabeled attachment scores on 6 languages.

cs.CL↗