arXiv subjects

Qi Wu

Publications and source records attributed to Qi Wu.

At least 343 records · Page 19Linked to original sources

arXiv2020

MeisterMorxrc at SemEval-2020 Task 9: Fine-Tune Bert and Multitask Learning for Sentiment Analysis of Code-Mixed Tweets

Natural language processing (NLP) has been applied to various fields including text classification and sentiment analysis. In the shared task of sentiment analysis of code-mixed tweets, which is a part of the SemEval-2020 competition~\cite{patwa2020sentimix}, we preprocess datasets by replacing emoji and deleting uncommon characters and so on, and then fine-tune the Bidirectional Encoder Representation from Transformers(BERT) to perform the best. After exhausting top3 submissions, Our team MeisterMorxrc achieves an averaged F1 score of 0.730 in this task, and and our codalab username is MeisterMorxrc.

cs.CL↗

arXiv2020

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps

Texts appearing in daily scenes that can be recognized by OCR (Optical Character Recognition) tools contain significant information, such as street name, product brand and prices. Two tasks -- text-based visual question answering and text-based image captioning, with a text extension from existing vision-language applications, are catching on rapidly. To address these problems, many sophisticated multi-modality encoding frameworks (such as heterogeneous graph structure) are being used. In this paper, we argue that a simple attention mechanism can do the same or even better job without any bells and whistles. Under this mechanism, we simply split OCR token features into separate visual- and linguistic-attention branches, and send them to a popular Transformer decoder to generate answers or captions. Surprisingly, we find this simple baseline model is rather strong -- it consistently outperforms state-of-the-art (SOTA) models on two popular benchmarks, TextVQA and all three tasks of ST-VQA, although these SOTA models use far more complex encoding mechanisms. Transferring it to text-based image captioning, we also surpass the TextCaps Challenge 2020 winner. We wish this work to set the new baseline for this two OCR text related applications and to inspire new thinking of multi-modality encoder design. Code is available at https://github.com/ZephyrZhuQi/ssbaseline

cs.CV↗

arXiv2020

Referring Expression Comprehension: A Survey of Methods and Datasets

Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been pre-defined, the REC problem only can observe the queries during the test. It thus more challenging than a conventional computer vision problem. This task has attracted a lot of attention from both computer vision and natural language processing community, and several lines of work have been proposed, from CNN-RNN model, modular network to complex graph-based model. In this survey, we first examine the state of the art by comparing modern approaches to the problem. We classify methods by their mechanism to encode the visual and textual modalities. In particular, we examine the common approach of joint embedding images and expressions to a common feature space. We also discuss modular architectures and graph-based models that interface with structured graph representation. In the second part of this survey, we review the datasets available for training and evaluating REC systems. We then group results according to the datasets, backbone models, settings so that they can be fairly compared. Finally, we discuss promising future directions for the field, in particular the compositional referring expression comprehension that requires longer reasoning chain to address.

cs.CV↗

arXiv2020

Optimistic Agent: Accurate Graph-Based Value Estimation for More Successful Visual Navigation

We humans can impeccably search for a target object, given its name only, even in an unseen environment. We argue that this ability is largely due to three main reasons: the incorporation of prior knowledge (or experience), the adaptation of it to the new environment using the observed visual cues and most importantly optimistically searching without giving up early. This is currently missing in the state-of-the-art visual navigation methods based on Reinforcement Learning (RL). In this paper, we propose to use externally learned prior knowledge of the relative object locations and integrate it into our model by constructing a neural graph. In order to efficiently incorporate the graph without increasing the state-space complexity, we propose our Graph-based Value Estimation (GVE) module. GVE provides a more accurate baseline for estimating the Advantage function in actor-critic RL algorithm. This results in reduced value estimation error and, consequently, convergence to a more optimal policy. Through empirical studies, we show that our agent, dubbed as the optimistic agent, has a more realistic estimate of the state value during a navigation episode which leads to a higher success rate. Our extensive ablation studies show the efficacy of our simple method which achieves the state-of-the-art results measured by the conventional visual navigation metrics, e.g. Success Rate (SR) and Success weighted by Path Length (SPL), in AI2THOR environment.

cs.CV↗

arXiv2020

$D$ wave bottomonia production from $Z_b^{(\prime)}$ decay

In the present work, we investigate the dipion transitions between $Υ(5S)$ and $Υ_J(1D)$ with $J=1, 2, 3$. Our analysis indicates that the dominant sources of the anomalously large widths of $Υ(5S)\to Υ_J(1D) π^+ π^-$ should be $Z_b^{(\prime)}$, i.e., the dipion transitions occur via the cascade decays $Υ(5S)\to Z_b^{(\prime)\pm} π^\mp \to Υ_J(1D) π^+ π^-$. With the assumption that all the short ranged dynamics could be absorbed in a single cutoff with a model parameter $α$, the present estimations indicate that in a reasonable parameter range the measured branching ratios of $Υ(5S) \to Υ_J(1D) π^+ π^-$ can be reproduced in magnitude, which further proves that the decays via $Z_b^{(\prime)}$ dominate the dipion transitions of $Υ(5S)$ to $Υ_J(1D)$. Moreover, we also predict the ratios of the branching fractions of $Z_b^{(\prime)} \to Υ_J(1D) π$, which in our calculations are largely independent of the parameter $α$ and could be tested by further experiments in Belle II.

hep-ph↗

arXiv2020

P3-LOAM: PPP/LiDAR Loosely Coupled SLAM with Accurate Covariance Estimation and Robust RAIM in Urban Canyon Environment

Light Detection and Ranging (LiDAR) based Simultaneous Localization and Mapping (SLAM) has drawn increasing interests in autonomous driving. However, LiDAR-SLAM suffers from accumulating errors which can be significantly mitigated by Global Navigation Satellite System (GNSS). Precise Point Positioning (PPP), an accurate GNSS operation mode independent of base stations, gains more popularity in unmanned systems. Considering the features of the two technologies, LiDAR-SLAM and PPP, this paper proposes a SLAM system, namely P3-LOAM (PPP based LiDAR Odometry and Mapping) which couples LiDAR-SLAM and PPP. For better integration, we derive LiDAR-SLAM positioning covariance by using Singular Value Decomposition (SVD) Jacobian model, since SVD provides an explicit analytic solution of Iterative Closest Point (ICP), which is a key issue in LiDAR-SLAM. A novel method is then proposed to evaluate the estimated LiDAR-SLAM covariance. In addition, to increase the reliability of GNSS in urban canyon environment, we develop a LiDAR-SLAM assisted GNSS Receiver Autonomous Integrity Monitoring (RAIM) algorithm. Finally, we validate P$^3$-LOAM with UrbanNav, a challenging public dataset in urban canyon environment. Comprehensive test results prove that P3-LOAM outperforms benchmarks such as Single Point Positioning (SPP), PPP, LeGO-LOAM, SPP-LOAM, and loosely coupled navigation system proposed by the publisher of UrbanNav in terms of accuracy and availability.

cs.RO↗

arXiv2020

Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning

The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments according to the given language instruction. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments; second, during the training process, the agent usually imitate the shortest-path to the target location. Due to the discrepancy of action selection between training and inference, the agent solely on the basis of imitation learning does not perform well. Sampling the next action from its predicted probability distribution during the training process allows the agent to explore diverse routes from the environments, yielding higher success rates. Nevertheless, without being presented with the shortest navigation paths during the training process, the agent may arrive at the target location through an unexpected longer route. To overcome these challenges, we design a cross-modal grounding module, which is composed of two complementary attention mechanisms, to equip the agent with a better ability to track the correspondence between the textual and visual modalities. We then propose to recursively alternate the learning schemes of imitation and exploration to narrow the discrepancy between training and inference. We further exploit the advantages of both these two learning schemes via adversarial learning. Extensive experimental results on the Room-to-Room (R2R) benchmark dataset demonstrate that the proposed learning scheme is generalized and complementary to prior arts. Our method performs well against state-of-the-art approaches in terms of effectiveness and efficiency.

cs.CV↗

arXiv2020

Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering

Fact-based Visual Question Answering (FVQA) requires external knowledge beyond visible content to answer questions about an image, which is challenging but indispensable to achieve general VQA. One limitation of existing FVQA solutions is that they jointly embed all kinds of information without fine-grained selection, which introduces unexpected noises for reasoning the final answer. How to capture the question-oriented and information-complementary evidence remains a key challenge to solve the problem. In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features. On top of the multi-layer graph representations, we propose a modality-aware heterogeneous graph convolutional network to capture evidence from different layers that is most relevant to the given question. Specifically, the intra-modal graph convolution selects evidence from each modality and cross-modal graph convolution aggregates relevant information across different modalities. By stacking this process multiple times, our model performs iterative reasoning and predicts the optimal answer by analyzing all question-oriented evidence. We achieve a new state-of-the-art performance on the FVQA task and demonstrate the effectiveness and interpretability of our model with extensive experiments.

cs.CV↗

arXiv2020

Reemergence of superconductivity in pressurized quasi-one-dimensional superconductor K2Mo3As3

Here we report a pressure-induced reemergence of superconductivity in recently discovered superconductor K2Mo3As3, which is the first experimental case observed in quasi-one-dimensional superconductors. We find that, after full suppression of the ambient-pressure superconducting (SC-I) state at 8.7 GPa, an intermediary non-superconducting state sets in and prevails to the pressure up to 18.2 GPa, however, above this pressure a new superconducting (SC-II) state appears unexpectedly. High pressure x-ray diffraction measurements demonstrate that the pressure-induced dramatic change of the lattice parameter c contributes mainly to the emergence of the SC-II state. Combined with the theioretical calculations on band strcture, our results suggest that the reemergemce of superconductivity is associated with the change of the complicated interplay among different orbital electrons, driven by the pressure-induced unisotropic change of the lattice.

cond-mat.supr-con↗

arXiv2020

Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning

We propose a parsimonious quantile regression framework to learn the dynamic tail behaviors of financial asset returns. Our model captures well both the time-varying characteristic and the asymmetrical heavy-tail property of financial time series. It combines the merits of a popular sequential neural network model, i.e., LSTM, with a novel parametric quantile function that we construct to represent the conditional distribution of asset returns. Our model also captures individually the serial dependences of higher moments, rather than just the volatility. Across a wide range of asset classes, the out-of-sample forecasts of conditional quantiles or VaR of our model outperform the GARCH family. Further, the proposed approach does not suffer from the issue of quantile crossing, nor does it expose to the ill-posedness comparing to the parametric probability density function approach.

q-fin.RM↗

arXiv2020

MARS: Mixed Virtual and Real Wearable Sensors for Human Activity Recognition with Multi-Domain Deep Learning Model

Together with the rapid development of the Internet of Things (IoT), human activity recognition (HAR) using wearable Inertial Measurement Units (IMUs) becomes a promising technology for many research areas. Recently, deep learning-based methods pave a new way of understanding and performing analysis of the complex data in the HAR system. However, the performance of these methods is mostly based on the quality and quantity of the collected data. In this paper, we innovatively propose to build a large database based on virtual IMUs and then address technical issues by introducing a multiple-domain deep learning framework consisting of three technical parts. In the first part, we propose to learn the single-frame human activity from the noisy IMU data with hybrid convolutional neural networks (CNNs) in the semi-supervised form. For the second part, the extracted data features are fused according to the principle of uncertainty-aware consistency, which reduces the uncertainty by weighting the importance of the features. The transfer learning is performed in the last part based on the newly released Archive of Motion Capture as Surface Shapes (AMASS) dataset, containing abundant synthetic human poses, which enhances the variety and diversity of the training dataset and is beneficial for the process of training and feature transfer in the proposed method. The efficiency and effectiveness of the proposed method have been demonstrated in the real deep inertial poser (DIP) dataset. The experimental results show that the proposed methods can surprisingly converge within a few iterations and outperform all competing methods.

cs.CV↗

arXiv2020

Sub-Instruction Aware Vision-and-Language Navigation

Vision-and-language navigation requires an agent to navigate through a real 3D environment following natural language instructions. Despite significant advances, few previous works are able to fully utilize the strong correspondence between the visual and textual sequences. Meanwhile, due to the lack of intermediate supervision, the agent's performance at following each part of the instruction cannot be assessed during navigation. In this work, we focus on the granularity of the visual and language sequences as well as the traceability of agents through the completion of an instruction. We provide agents with fine-grained annotations during training and find that they are able to follow the instruction better and have a higher chance of reaching the target at test time. We enrich the benchmark dataset Room-to-Room (R2R) with sub-instructions and their corresponding paths. To make use of this data, we propose effective sub-instruction attention and shifting modules that select and attend to a single sub-instruction at each time-step. We implement our sub-instruction modules in four state-of-the-art agents, compare with their baseline models, and show that our proposed method improves the performance of all four agents. We release the Fine-Grained R2R dataset (FGR2R) and the code at https://github.com/YicongHong/Fine-Grained-R2R.

cs.CV↗

arXiv2020

RSAVS superconductors: materials with a superconducting state that is robust against large volume shrinkage

TThe transition temperature (TC) between normal and superconducting states usually exhibits a dramatic increase or decrease with increasing applied pressure. Here we present, in contrast, a new kind of superconductor that exhibits the exotic feature that TC is robust against large volume shrinkages induced by applied pressure (here naming them as "RSAVS superconductors"). Extraordinarily, the TC in these materials stays almost constant over a large pressure range, e.g. over 136 GPa in the (TaNb)0.67(HfZrTi)0.33 high entropy alloy and 141 GPa in the NbTi commercial alloy. We show that the RSAVS behavior also exists in another high entropy alloy (ScZrNbTa)0.6(RhPd)0.4, and in superconducting elemental Ta and Nb, indicating that this behavior, which has never previously been identified or predicted by theory, occurs universally in some conventional superconductors. Our electronic structure calculations indicate that although the electronic density of state (DOS) at the Fermi level in the RSAVS state is dominated by the electrons from the degenerate dxy, dxz and dyz orbitals, these electrons decrease in influence with increasing pressure. In contrast, however, the contribution of the degenerate dx2-y2 and dz2 orbital electrons remains almost unchanged at the Fermi level, suggesting that these are the electrons that may play a crucial role in stabilizing the TC in the RSAVS state.

cond-mat.supr-con↗

arXiv2020

Understanding Distributional Ambiguity via Non-robust Chance Constraint

This paper provides a non-robust interpretation of the distributionally robust optimization (DRO) problem by relating the distributional uncertainties to the chance probabilities. Our analysis allows a decision-maker to interpret the size of the ambiguity set, which is often lack of business meaning, through the chance parameters constraining the objective function. We first show that, for general $ϕ$-divergences, a DRO problem is asymptotically equivalent to a class of mean-deviation problems. These mean-deviation problems are not subject to uncertain distributions, and the ambiguity radius in the original DRO problem now plays the role of controlling the risk preference of the decision-maker. We then demonstrate that a DRO problem can be cast as a chance-constrained optimization (CCO) problem when a boundedness constraint is added to the decision variables. Without the boundedness constraint, the CCO problem is shown to perform uniformly better than the DRO problem, irrespective of the radius of the ambiguity set, the choice of the divergence measure, or the tail heaviness of the center distribution. Thanks to our high-order expansion result, a notable feature of our analysis is that it applies to divergence measures that accommodate well heavy tail distributions such as the student $t$-distribution and the lognormal distribution, besides the widely-used Kullback-Leibler (KL) divergence, which requires the distribution of the objective function to be exponentially bounded. Using the portfolio selection problem as an example, our comprehensive testings on multivariate heavy-tail datasets, both synthetic and real-world, shows that this business-interpretation approach is indeed useful and insightful.

math.OC↗

arXiv2020

Attention-SLAM: A Visual Monocular SLAM Learning from Human Gaze

This paper proposes a novel simultaneous localization and mapping (SLAM) approach, namely Attention-SLAM, which simulates human navigation mode by combining a visual saliency model (SalNavNet) with traditional monocular visual SLAM. Most SLAM methods treat all the features extracted from the images as equal importance during the optimization process. However, the salient feature points in scenes have more significant influence during the human navigation process. Therefore, we first propose a visual saliency model called SalVavNet in which we introduce a correlation module and propose an adaptive Exponential Moving Average (EMA) module. These modules mitigate the center bias to enable the saliency maps generated by SalNavNet to pay more attention to the same salient object. Moreover, the saliency maps simulate the human behavior for the refinement of SLAM results. The feature points extracted from the salient regions have greater importance in optimization process. We add semantic saliency information to the Euroc dataset to generate an open-source saliency SLAM dataset. Comprehensive test results prove that Attention-SLAM outperforms benchmarks such as Direct Sparse Odometry (DSO), ORB-SLAM, and Salient DSO in terms of efficiency, accuracy, and robustness in most test cases.

cs.CV↗

arXiv2020

Diva: A Declarative and Reactive Language for In-Situ Visualization

The use of adaptive workflow management for in situ visualization and analysis has been a growing trend in large-scale scientific simulations. However, coordinating adaptive workflows with traditional procedural programming languages can be difficult because system flow is determined by unpredictable scientific phenomena, which often appear in an unknown order and can evade event handling. This makes the implementation of adaptive workflows tedious and error-prone. Recently, reactive and declarative programming paradigms have been recognized as well-suited solutions to similar problems in other domains. However, there is a dearth of research on adapting these approaches to in situ visualization and analysis. With this paper, we present a language design and runtime system for developing adaptive systems through a declarative and reactive programming paradigm. We illustrate how an adaptive workflow programming system is implemented using our approach and demonstrate it with a use case from a combustion simulation.

cs.PL↗

arXiv2020

Give Me Something to Eat: Referring Expression Comprehension with Commonsense Knowledge

Conventional referring expression comprehension (REF) assumes people to query something from an image by describing its visual appearance and spatial location, but in practice, we often ask for an object by describing its affordance or other non-visual attributes, especially when we do not have a precise target. For example, sometimes we say 'Give me something to eat'. In this case, we need to use commonsense knowledge to identify the objects in the image. Unfortunately, these is no existing referring expression dataset reflecting this requirement, not to mention a model to tackle this challenge. In this paper, we collect a new referring expression dataset, called KB-Ref, containing 43k expressions on 16k images. In KB-Ref, to answer each expression (detect the target object referred by the expression), at least one piece of commonsense knowledge must be required. We then test state-of-the-art (SoTA) REF models on KB-Ref, finding that all of them present a large drop compared to their outstanding performance on general REF datasets. We also present an expression conditioned image and fact attention (ECIFA) network that extract information from correlated image regions and commonsense knowledge facts. Our method leads to a significant improvement over SoTA REF models, although there is still a gap between this strong baseline and human performance. The dataset and baseline models will be released.

cs.CV↗

arXiv2020

Data-driven Meta-set Based Fine-Grained Visual Classification

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method for fine-grained visual recognition. However, label noise in the web training set can severely degrade the model performance. To this end, we propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition. Specifically, guided by a small amount of clean meta-set, we train a selection net in a meta-learning manner to distinguish in- and out-of-distribution noisy images. To further boost the robustness of model, we also learn a labeling net to correct the labels of in-distribution noisy data. In this way, our proposed method can alleviate the harmful effects caused by out-of-distribution noise and properly exploit the in-distribution noisy samples for training. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is much superior to state-of-the-art noise-robust methods.

cs.CV↗