Self-supervised Multi-view stereo (MVS) with a pretext task of image reconstruction has achieved significant progress recently. However, previous methods are built upon intuitions, lacking comprehensive explanations about the effectiveness of the pre
text task in self-supervised MVS. To this end, we propose to estimate epistemic uncertainty in self-supervised MVS, accounting for what the model ignores. Specially, the limitations can be categorized into two types: ambiguious supervision in foreground and invalid supervision in background. To address these issues, we propose a novel Uncertainty reduction Multi-view Stereo (UMVS) framework for self-supervised learning. To alleviate ambiguous supervision in foreground, we involve extra correspondence prior with a flow-depth consistency loss. The dense 2D correspondence of optical flows is used to regularize the 3D stereo correspondence in MVS. To handle the invalid supervision in background, we use Monte-Carlo Dropout to acquire the uncertainty map and further filter the unreliable supervision signals on invalid regions. Extensive experiments on DTU and Tank&Temples benchmark show that our U-MVS framework achieves the best performance among unsupervised MVS methods, with competitive performance with its supervised opponents.
Traffic forecasting is a core element of intelligent traffic monitoring system. Approaches based on graph neural networks have been widely used in this task to effectively capture spatial and temporal dependencies of road networks. However, these app
roaches can not effectively define the complicated network topology. Besides, their cascade network structures have limitations in transmitting distinct features in the time and space dimensions. In this paper, we propose a Multi-adaptive Spatiotemporal-flow Graph Neural Network (MAF-GNN) for traffic speed forecasting. MAF-GNN introduces an effective Multi-adaptive Adjacency Matrices Mechanism to capture multiple latent spatial dependencies between traffic nodes. Additionally, we propose Spatiotemporal-flow Modules aiming to further enhance feature propagation in both time and space dimensions. MAF-GNN achieves better performance than other models on two real-world datasets of public traffic network, METR-LA and PeMS-Bay, demonstrating the effectiveness of the proposed approach.
To achieve high device performance and high reliability for the gallium nitride (GaN)-based high electron mobility transistors (HEMTs), efficient heat dissipation is important but remains challenging. Enormous efforts have been made to transfer a GaN
device layer onto a diamond substrate with a high thermal conductivity by bonding. In this work, two GaN-diamond bonded composites are prepared via modified surface activated bonding (SAB) at room temperature with silicon interlayers of different thicknesses (15 nm and 22 nm). Before and after post-annealing process at 800 oC, thermal boundary conductance (TBC) across the bonded interface including the interlayer and the stress of GaN layer are investigated by time-domain thermoreflectance and Raman spectroscopy, respectively. After bonding, the 15 nm Si interlayer achieved a higher TBC. The post-annealing significantly increased the TBC of both interfaces, while the TBC of 22 nm silicon interlayer increased greater and became higher than that of 15 nm. Detailed investigation of the microstructure and composition of the interfaces were carried out to understand the difference in interfacial thermal conduction. The obtained stress was no more than 230 MPa for both before and after the annealing, and this high thermal stability of the bonded composites indicates that the room temperature bonding can realize a GaN-on-diamond template suitable for further epitaxial growth or device process. This work brings a novel strategy of SAB followed by high-temperature annealing to fabricate a GaN-on-diamond device with a high TBC.
In this paper, we show the scattering of the solution for the focusing inhomogenous nonlinear Schrodinger equation with a potential begin{align*} ipartial_t u+Delta u- Vu=-|x|^{-b}|u|^{p-1}u end{align*} in the energy space $H^1(mathbb R^3)$. We pro
ve a scattering criterion, and then we use it together with Morawetz estimate to show the scattering theory.
In this paper, we study the solutions to the energy-critical quadratic nonlinear Schrodinger system in ${dot H}^1times{dot H}^1$, where the sign of its potential energy can not be determined directly. If the initial data ${rm u}_0$ is radial or non-r
adial but satisfies the mass-resonance condition, and its energy is below that of the ground state, using the compactness/rigidity method, we give a complete classification of scattering versus blowing-up dichotomies depending on whether the kinetic energy of ${rm u}_0$ is below or above that of the ground state.
Extractive Reading Comprehension (ERC) has made tremendous advances enabled by the availability of large-scale high-quality ERC training data. Despite of such rapid progress and widespread application, the datasets in languages other than high-resour
ce languages such as English remain scarce. To address this issue, we propose a Cross-Lingual Transposition ReThinking (XLTT) model by modelling existing high-quality extractive reading comprehension datasets in a multilingual environment. To be specific, we present multilingual adaptive attention (MAA) to combine intra-attention and inter-attention to learn more general generalizable semantic and lexical knowledge from each pair of language families. Furthermore, to make full use of existing datasets, we adopt a new training framework to train our model by calculating task-level similarities between each existing dataset and target dataset. The experimental results show that our XLTT model surpasses six baselines on two multilingual ERC benchmarks, especially more effective for low-resource languages with 3.9 and 4.1 average improvement in F1 and EM, respectively.
Although there are a small number of work to conduct patent research by building knowledge graph, but without constructing patent knowledge graph using patent documents and combining latest natural language processing methods to mine hidden rich sema
ntic relationships in existing patents and predict new possible patents. In this paper, we propose a new patent vacancy prediction approach named PatentMiner to mine rich semantic knowledge and predict new potential patents based on knowledge graph (KG) and graph attention mechanism. Firstly, patent knowledge graph over time (e.g. year) is constructed by carrying out named entity recognition and relation extrac-tion from patent documents. Secondly, Common Neighbor Method (CNM), Graph Attention Networks (GAT) and Context-enhanced Graph Attention Networks (CGAT) are proposed to perform link prediction in the constructed knowledge graph to dig out the potential triples. Finally, patents are defined on the knowledge graph by means of co-occurrence relationship, that is, each patent is represented as a fully connected subgraph containing all its entities and co-occurrence relationships of the patent in the knowledge graph; Furthermore, we propose a new patent prediction task which predicts a fully connected subgraph with newly added prediction links as a new pa-tent. The experimental results demonstrate that our proposed patent predic-tion approach can correctly predict new patents and Context-enhanced Graph Attention Networks is much better than the baseline. Meanwhile, our proposed patent vacancy prediction task still has significant room to im-prove.
Few-shot Named Entity Recognition (NER) exploits only a handful of annotations to identify and classify named entity mentions. Prototypical network shows superior performance on few-shot NER. However, existing prototypical methods fail to differentia
te rich semantics in other-class words, which will aggravate overfitting under few shot scenario. To address the issue, we propose a novel model, Mining Undefined Classes from Other-class (MUCO), that can automatically induce different undefined classes from the other class to improve few-shot NER. With these extra-labeled undefined classes, our method will improve the discriminative ability of NER classifier and enhance the understanding of predefined classes with stand-by semantic knowledge. Experimental results demonstrate that our model outperforms five state-of-the-art models in both 1-shot and 5-shots settings on four NER benchmarks. We will release the code upon acceptance. The source code is released on https: //github.com/shuaiwa16/OtherClassNER.git.
In this paper, we prove a limiting absorption principle for high-order Schrodinger operators with a large class of potentials which generalize some results by A. Ionescu and W. Schlag. Our main idea is to handle the boundary operators by the restrict
ion theorem of Fourier transform. Two key tools we use in this paper are the Stein--Tomas theorem in Lorentz spaces and a sharp trace lemma given by S. Agmon and L. Hormander
Transformer model architectures have become an indispensable staple in deep learning lately for their effectiveness across a range of tasks. Recently, a surge of X-former models have been proposed which improve upon the original Transformer architect
ure. However, most of these variants make changes only around the quadratic time and memory complexity of self-attention, i.e. the dot product between the query and the key. Whats more, they are calculate solely in Euclidean space. In this work, we propose a novel Transformer with Hyperbolic Geometry (THG) model, which take the advantage of both Euclidean space and Hyperbolic space. THG makes improvements in linear transformations of self-attention, which are applied on the input sequence to get the query and the key, with the proposed hyperbolic linear. Extensive experiments on sequence labeling task, machine reading comprehension task and classification task demonstrate the effectiveness and generalizability of our model. It also demonstrates THG could alleviate overfitting.
