arXiv subjects

Qi Wu

Publications and source records attributed to Qi Wu.

At least 397 records · Page 22Linked to original sources

arXiv2017

Learning Semantic Concepts and Order for Image and Sentence Matching

Image and sentence matching has made great progress recently, but it remains challenging due to the large visual-semantic discrepancy. This mainly arises from that the representation of pixel-level image usually lacks of high-level semantic information as in its matched sentence. In this work, we propose a semantic-enhanced image and sentence matching model, which can improve the image representation by learning semantic concepts and then organizing them in a correct semantic order. Given an image, we first use a multi-regional multi-label CNN to predict its semantic concepts, including objects, properties, actions, etc. Then, considering that different orders of semantic concepts lead to diverse semantic meanings, we use a context-gated sentence generation scheme for semantic order learning. It simultaneously uses the image global context containing concept relations as reference and the groundtruth semantic order in the matched sentence as supervision. After obtaining the improved image representation, we learn the sentence representation with a conventional LSTM, and then jointly perform image and sentence matching and sentence generation for model learning. Extensive experiments demonstrate the effectiveness of our learned semantic concepts and order, by achieving the state-of-the-art results on two public benchmark datasets.

cs.CV↗

arXiv2017

Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning

The Visual Dialogue task requires an agent to engage in a conversation about an image with a human. It represents an extension of the Visual Question Answering task in that the agent needs to answer a question about an image, but it needs to do so in light of the previous dialogue that has taken place. The key challenge in Visual Dialogue is thus maintaining a consistent, and natural dialogue while continuing to answer questions correctly. We present a novel approach that combines Reinforcement Learning and Generative Adversarial Networks (GANs) to generate more human-like responses to questions. The GAN helps overcome the relative paucity of training data, and the tendency of the typical MLE-based approach to generate overly terse answers. Critically, the GAN is tightly integrated into the attention mechanism that generates human-interpretable reasons for each answer. This means that the discriminative model of the GAN has the task of assessing whether a candidate answer is generated by a human or not, given the provided reason. This is significant because it drives the generative model to produce high quality answers that are well supported by the associated reasoning. The method also generates the state-of-the-art results on the primary benchmark.

cs.CV↗

arXiv2017

Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards

Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge. Towards this end, we propose a Deep Reinforcement Learning framework based on three new intermediate rewards, namely goal-achieved, progressive and informativeness that encourage the generation of succinct questions, which in turn uncover valuable information towards the overall goal. By directly optimizing for questions that work quickly towards fulfilling the overall goal, we avoid the tendency of existing methods to generate long series of insane queries that add little value. We evaluate our model on the GuessWhat?! dataset and show that the resulting questions can help a standard Guesser identify a specific object in an image at a much higher success rate.

cs.CV↗

arXiv2017

Kill Two Birds with One Stone: Weakly-Supervised Neural Network for Image Annotation and Tag Refinement

The number of social images has exploded by the wide adoption of social networks, and people like to share their comments about them. These comments can be a description of the image, or some objects, attributes, scenes in it, which are normally used as the user-provided tags. However, it is well-known that user-provided tags are incomplete and imprecise to some extent. Directly using them can damage the performance of related applications, such as the image annotation and retrieval. In this paper, we propose to learn an image annotation model and refine the user-provided tags simultaneously in a weakly-supervised manner. The deep neural network is utilized as the image feature learning and backbone annotation model, while visual consistency, semantic dependency, and user-error sparsity are introduced as the constraints at the batch level to alleviate the tag noise. Therefore, our model is highly flexible and stable to handle large-scale image sets. Experimental results on two benchmark datasets indicate that our proposed model achieves the best performance compared to the state-of-the-art methods.

cs.CV↗

arXiv2017

Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries

Recognising objects according to a pre-defined fixed set of class labels has been well studied in the Computer Vision. There are a great many practical applications where the subjects that may be of interest are not known beforehand, or so easily delineated, however. In many of these cases natural language dialog is a natural way to specify the subject of interest, and the task achieving this capability (a.k.a, Referring Expression Comprehension) has recently attracted attention. To this end we propose a unified framework, the ParalleL AttentioN (PLAN) network, to discover the object in an image that is being referred to in variable length natural expression descriptions, from short phrases query to long multi-round dialogs. The PLAN network has two attention mechanisms that relate parts of the expressions to both the global visual content and also directly to object candidates. Furthermore, the attention mechanisms are recurrent, making the referring process visualizable and explainable. The attended information from these dual sources are combined to reason about the referred object. These two attention mechanisms can be trained in parallel and we find the combined system outperforms the state-of-art on several benchmarked datasets with different length language input, such as RefCOCO, RefCOCO+ and GuessWhat?!.

cs.CV↗

arXiv2017

Anomalous connection between antiferromagnetic and superconducting phases in pressurized non-centrosymmetric heavy fermion compound CeRhGe3

Unconventional superconductivity frequently emerges as the transition temperature of a magnetic phase, typically antiferromagnetic, is suppressed continuously toward zero temperature. Here, we report contrary behavior in pressurized CeRhGe3, a non-centrosymmetric heavy fermion compound. We find that its pressure-tuned antiferromagnetic transition temperature (TN) appears to avoid a continuous decrease to zero temperature by terminating abruptly above a dome of pressure-induced superconductivity. Near 21.5 GPa, evidence for TN suddenly vanishes, the electrical resistance becomes linear in temperature and the superconducting transition reaches a maximum. In light of X-ray absorption spectroscopy measurements, these characteristics appear to be related to a pressured-induced Ce valence instability, which reveals as a sharp increase in the rate of change of Ce valence with applied pressure.

cond-mat.supr-con↗

arXiv2017

Non-static ground state in SmB6: a form of time crystal?

Here we propose the existence of a non-static ground state in the Kondo insulator SmB6, with a unique accompany-type valence fluctuation of Sm ions in its bulk. Whether SmB6 is a fashion of time crystal is an intriguing issue.

cond-mat.str-el↗

arXiv2017

Pressure-induced melting of magnetic order and emergence of new quantum state in alpha-RuCl3

Here we report the observation of pressure-induced melting of antiferromagnetic (AFM) order and emergence of a new quantum state in the honeycomb-lattice halide alpha-RuCl3, a candidate compound in the proximity of quantum spin liquid state. Our high-pressure heat capacity measurements demonstrate that the AFM order smoothly melts away at a critical pressure (Pc) of 0.7 GPa. Intriguingly, the AFM transition temperature displays an increase upon applying pressure below the Pc, in stark contrast to usual phase diagrams, for example in pressurized parent compounds of unconventional superconductors. Furthermore, in the high-pressure phase an unusual steady of magnetoresistance is observed. These observations suggest that the high-pressure phase is in an exotic gapped quantum state which is robust against pressure up to ~140 GPa.

cond-mat.str-el↗

arXiv2017

Zero resistance from one atmosphere to the pressure of earth's outer core in a superconducting high entropy alloy

We report the observation of extraordinarily robust zero-resistance superconductivity in the pressurized (TaNb)0.67(HfZrTi)0.33 high entropy alloy - a new kind of material with a body-centered cubic crystal structure made from five randomly distributed transition metal elements. The transition to superconductivity (TC) increases from an initial temperature of 7.7 K at ambient pressure to 10 K at ~ 60 GPa, and then slowly decreases to 9 K by 190.6 GPa, a pressure that falls within that of the outer core of the earth. We infer that the continuous existence of the zero-resistance superconductivity from one atmosphere up to such a high pressure requires a special combination of electronic and mechanical characteristics. This high entropy alloy superconductor thus may have a bright future for applications under extreme conditions, and also poses a challenge for understanding the underlying quantum physics.

cond-mat.supr-con↗

arXiv2017

Superconductivity in pressurized CeRhGe3 and related non-centrosymmetric compounds

We report the discovery of superconductivity in pressurized CeRhGe3, until now the only remaining non-superconducting member of the isostructural family of non-centrosymmetric heavy-fermion compounds CeTX3 (T = Co, Rh, Ir and X = Si, Ge). Superconductivity appears in CeRhGe3 at a pressure of 19.6 GPa and the transition temperature Tc reaches a maximum value of 1.3 K at 21.5 GPa. This finding provides an opportunity to establish systematic correlations between superconductivity and materials properties within this family. Though ambient-pressure unit-cell volumes and critical pressures for superconductivity vary substantially across the series, all family members reach a maximum Tcmax at a common critical cell volume Vcrit, and Tcmax at Vcrit increases with increasing spin-orbit coupling strength of the d-electrons. These correlations show that substantial Kondo hybridization and spin-orbit coupling favor superconductivity in this family, the latter reflecting the role of broken centro-symmetry.

cond-mat.supr-con↗

arXiv2017

FVQA: Fact-based Visual Question Answering

Visual Question Answering (VQA) has attracted a lot of attention in both Computer Vision and Natural Language Processing communities, not least because it offers insight into the relationships between two important sources of information. Current datasets, and the models built upon them, have focused on questions which are answerable by direct analysis of the question and image alone. The set of such questions that require no external information to answer is interesting, but very limited. It excludes questions which require common sense, or basic factual knowledge to answer, for example. Here we introduce FVQA, a VQA dataset which requires, and supports, much deeper reasoning. FVQA only contains questions which require external information to answer. We thus extend a conventional visual question answering dataset, which contains image-question-answerg triplets, through additional image-question-answer-supporting fact tuples. The supporting fact is represented as a structural triplet, such as . We evaluate several baseline models on the FVQA dataset, and describe a novel model which is capable of reasoning about an image on the basis of supporting facts.

cs.CV↗

arXiv2017

Classification of Medical Images and Illustrations in the Biomedical Literature Using Synergic Deep Learning

The Classification of medical images and illustrations in the literature aims to label a medical image according to the modality it was produced or label an illustration according to its production attributes. It is an essential and challenging research hotspot in the area of automated literature review, retrieval and mining. The significant intra-class variation and inter-class similarity caused by the diverse imaging modalities and various illustration types brings a great deal of difficulties to the problem. In this paper, we propose a synergic deep learning (SDL) model to address this issue. Specifically, a dual deep convolutional neural network with a synergic signal system is designed to mutually learn image representation. The synergic signal is used to verify whether the input image pair belongs to the same category and to give the corrective feedback if a synergic error exists. Our SDL model can be trained 'end to end'. In the test phase, the class label of an input can be predicted by averaging the likelihood probabilities obtained by two convolutional neural network components. Experimental results on the ImageCLEF2016 Subfigure Classification Challenge suggest that our proposed SDL model achieves the state-of-the art performance in this medical image classification problem and its accuracy is higher than that of the first place solution on the Challenge leader board so far.

cs.CV↗

arXiv2017

Care about you: towards large-scale human-centric visual relationship detection

Visual relationship detection aims to capture interactions between pairs of objects in images. Relationships between objects and humans represent a particularly important subset of this problem, with implications for challenges such as understanding human behaviour, and identifying affordances, amongst others. In addressing this problem we first construct a large-scale human-centric visual relationship detection dataset (HCVRD), which provides many more types of relationship annotation (nearly 10K categories) than the previous released datasets. This large label space better reflects the reality of human-object interactions, but gives rise to a long-tail distribution problem, which in turn demands a zero-shot approach to labels appearing only in the test set. This is the first time this issue has been addressed. We propose a webly-supervised approach to these problems and demonstrate that the proposed model provides a strong baseline on our HCVRD dataset.

cs.CV↗

arXiv2017

Study on the radiative decays of $h_c$ via intermediate meson loops model

Recently, the BESIII Collaboration reported two new decay processes $h_c(1P)\to γη$ and $γη^\prime$. Inspired by this measurement, we propose to study the radiative decays of $h_c$ via intermediate charmed meson loops in an effective Lagrangian approach. With the acceptable cutoff parameter range, the calculated branching ratios of $h_c(1P)\to γη$ and $γη^\prime$ are orders of $10^{-4}\sim 10^{-3}$ and $10^{-3} \sim 10^{-2}$, respectively. The ratio $R_{h_c}= \mathcal{B}( h_c\to γη)/\mathcal{B}( h_c\to γη^\prime )$ can reproduce the experimental measurements with the commonly acceptable $α$ range. This ratio provide us some information on the $η-η^\prime$ mixing, which may be helpful for us to test SU(3)-flavor symmetries in QCD.

hep-ph↗

arXiv2017

Multi-Label Image Classification with Regional Latent Semantic Dependencies

Deep convolution neural networks (CNN) have demonstrated advanced performance on single-label image classification, and various progress also have been made to apply CNN methods on multi-label image classification, which requires to annotate objects, attributes, scene categories etc. in a single shot. Recent state-of-the-art approaches to multi-label image classification exploit the label dependencies in an image, at global level, largely improving the labeling capacity. However, predicting small objects and visual concepts is still challenging due to the limited discrimination of the global visual features. In this paper, we propose a Regional Latent Semantic Dependencies model (RLSD) to address this problem. The utilized model includes a fully convolutional localization architecture to localize the regions that may contain multiple highly-dependent labels. The localized regions are further sent to the recurrent neural networks (RNN) to characterize the latent semantic dependencies at the regional level. Experimental results on several benchmark datasets show that our proposed model achieves the best performance compared to the state-of-the-art models, especially for predicting small objects occurred in the images. In addition, we set up an upper bound model (RLSD+ft-RPN) using bounding box coordinates during training, the experimental results also show that our RLSD can approach the upper bound without using the bounding-box annotations, which is more realistic in the real world.

cs.CV↗

arXiv2016

Image Captioning and Visual Question Answering Based on Attributes and External Knowledge

Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism can be used to incorporate external knowledge, which is critically important for answering high level visual questions. Specifically, we design a visual question answering model that combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions. It particularly allows questions to be asked about the contents of an image, even when the image itself does not contain a complete answer. Our final model achieves the best reported results on both image captioning and visual question answering on several benchmark datasets.

cs.CV↗

arXiv2016

The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions

One of the most intriguing features of the Visual Question Answering (VQA) challenge is the unpredictability of the questions. Extracting the information required to answer them demands a variety of image operations from detection and counting, to segmentation and reconstruction. To train a method to perform even one of these operations accurately from {image,question,answer} tuples would be challenging, but to aim to achieve them all with a limited set of such training data seems ambitious at best. We propose here instead a more general and scalable approach which exploits the fact that very good methods to achieve these operations already exist, and thus do not need to be trained. Our method thus learns how to exploit a set of external off-the-shelf algorithms to achieve its goal, an approach that has something in common with the Neural Turing Machine. The core of our proposed method is a new co-attention model. In addition, the proposed approach generates human-readable reasons for its decision, and can still be trained end-to-end without ground truth reasons being given. We demonstrate the effectiveness on two publicly available datasets, Visual Genome and VQA, and show that it produces the state-of-the-art results in both cases.

cs.CV↗

arXiv2016

Pressuring the low-temperature orthorhombic phase with a non-trivial topological state of Ru2Sn3 to room temperature

We report high pressure studies of the structural stability of Ru2Sn3, a new type of three dimensional topological insulator (3D-TI) with unique quasi-one dimensional Dirac electron states throughout the surface Brillouin zone of its one-atmosphere low temperature orthorhombic form. Our in-situ high-pressure synchrotron x-ray diffraction and electrical resistance measurements reveal that upon increasing pressure the tetragonal to orthorhombic shifts to higher temperature. We find that the stability of the orthorhombic phase that hosts the non-trivial topological ground state can be pushed up to room temperature by an applied pressure of ~ 20 GPa. This is in contrast to the commonly known 3D-TIs whose ground state is usually destroyed under pressure. Our results indicate that pressure provides a possible pathway for realizing a room-temperature topological insulating state in Ru2Sn3.

cond-mat.str-el↗