Search

We present an end-to-end trainable framework for P-frame compression in this paper. A joint motion vector (MV) and residual prediction network MV-Residual is designed to extract the ensembled features of motion representations and residual information by treating the two successive frames as inputs. The prior probability of the latent representations is modeled by a hyperprior autoencoder and trained jointly with the MV-Residual network. Specially, the spatially-displaced convolution is applied for video frame prediction, in which a motion kernel for each pixel is learned to generate predicted pixel by applying the kernel at a displaced location in the source image. Finally, novel rate allocation and post-processing strategies are used to produce the final compressed bits, considering the bits constraint of the challenge. The experimental results on validation set show that the proposed optimized framework can generate the highest MS-SSIM for P-frame compression competition.

Graph similarity computation aims to predict a similarity score between one pair of graphs to facilitate downstream applications, such as finding the most similar chemical compounds similar to a query compound or Fewshot 3D Action Recognition. Recently, some graph similarity computation models based on neural networks have been proposed, which are either based on graph-level interaction or node-level comparison. However, when the number of nodes in the graph increases, it will inevitably bring about reduced representation ability or high computation cost. Motivated by this observation, we propose a graph partitioning and graph neural network-based model, called PSimGNN, to effectively resolve this issue. Specifically, each of the input graphs is partitioned into a set of subgraphs to extract the local structural features directly. Next, a novel graph neural network with an attention mechanism is designed to map each subgraph into an embedding vector. Some of these subgraph pairs are automatically selected for node-level comparison to supplement the subgraph-level embedding with fine-grained information. Finally, coarse-grained interaction information among subgraphs and fine-grained comparison information among nodes in different subgraphs are integrated to predict the final similarity score. Experimental results on graph datasets with different graph sizes demonstrate that PSimGNN outperforms state-of-the-art methods in graph similarity computation tasks using approximate Graph Edit Distance (GED) as the graph similarity metric.

The ability to compute similarity scores between graphs based on metrics such as Graph Edit Distance (GED) is important in many real-world applications. Computing exact GED values is typically an NP-hard problem and traditional algorithms usually achieve an unsatisfactory trade-off between accuracy and efficiency. Recently, Graph Neural Networks (GNNs) provide a data-driven solution for this task, which is more efficient while maintaining prediction accuracy in small graph (around 10 nodes per graph) similarity computation. Existing GNN-based methods, which either respectively embeds two graphs (lack of low-level cross-graph interactions) or deploy cross-graph interactions for whole graph pairs (redundant and time-consuming), are still not able to achieve competitive results when the number of nodes in graphs increases. In this paper, we focus on similarity computation for large-scale graphs and propose the "embedding-coarsening-matching" framework CoSimGNN, which first embeds and coarsens large graphs with adaptive pooling operation and then deploys fine-grained interactions on the coarsened graphs for final similarity scores. Furthermore, we create several synthetic datasets which provide new benchmarks for graph similarity computation. Detailed experiments on both synthetic and real-world datasets have been conducted and CoSimGNN achieves the best performance while the inference time is at most 1/3 of that of previous state-of-the-art.

Multivariate time series (MTS) forecasting is an essential problem in many fields. Accurate forecasting results can effectively help decision-making. To date, many MTS forecasting methods have been proposed and widely applied. However, these methods assume that the predicted value of a single variable is affected by all other variables, which ignores the causal relationship among variables. To address the above issue, we propose a novel end-to-end deep learning model, termed graph neural network with Neural Granger Causality (CauGNN) in this paper. To characterize the causal information among variables, we introduce the Neural Granger Causality graph in our model. Each variable is regarded as a graph node, and each edge represents the casual relationship between variables. In addition, convolutional neural network (CNN) filters with different perception scales are used for time series feature extraction, which is used to generate the feature of each node. Finally, Graph Neural Network (GNN) is adopted to tackle the forecasting problem of graph structure generated by MTS. Three benchmark datasets from the real world are used to evaluate the proposed CauGNN. The comprehensive experiments show that the proposed method achieves state-of-the-art results in the MTS forecasting task.

Low-surface-brightness galaxies(LSBGs) are defined as galaxies that are fainter than dark night sky and are important for studying our universe. Particularly, edge-on galaxies are useful for the study of rotational velocity and dynamical properties of galaxies. Hence here we focus on searching for edge-on LSBGs. In order to find these edge-on dim galaxies, a series of effects caused by inclination, including the surface brightness profile, internal extinction, and scale length, have been corrected. In this work, we present a catalog of 281 edge-on LSBG candidates, which are selected from the cross-match between SDSS DR7 and the 40% ALFALFA catalog. We also present the properties of these edge-on LSBG candidates including absolute magnitude, central surface brightness, B-V color, scale length, and relative thickness. Our result suggests that the correction of inclination effects is very important for obtaining a complete sample of LSBGs., Comment: 14 pages, 7 figures, 2 tables

We present a pipeline for modeling spatially varying BRDFs (svBRDFs) of planar materials which only requires a mobile phone for data acquisition. With a minimum of two photos under the ambient and point light source, our pipeline produces svBRDF parameters, a normal map and a tangent map for the material sample. The BRDF fitting is achieved via a pixel clustering strategy and an optimization based scheme. Our method is light-weight, easy-to-use and capable of producing high-quality BRDF textures.

By using Dazzler system and tilting compressor grating, we provide an effective way of using the laser group delay dispersion (GDD) to continuously steer the high energy electron beam which is accelerated by asymmetric laser-wakefield. The deviation angle of electrons is as the same as the angular chirped laser pulse from its initial optical axis, which is determined by the laser pulse-front-tilt (PFT). This unique method can be continuously used to control over the pointing direction of electron-pulses to the requisite trajectories, especially for the alignment sensitive devices such as electron-positron collider or undulator. Besides, the effect of PFT on the qualities of electron beam has been investigated.

This paper presents the result of $H\alpha$ imaging for luminous infrared galaxies (LIRGs) and ultra-luminous infrared galaxies (ULIRGs). \textbf{It is } a \textbf{complete subsample of Great Observatories All-sky LIRG Survery (GOALS) with $Dec. \ge -30^{\circ}$}, \textbf{and} consists 148 galaxies with $log(L_{IR}/L_{\odot}) \ge 11.0$. All the $H\alpha$ images were carried out using the 2.16-m telescope \textbf{at the Xinglong Station of the} National Astronomy Observatories, Chinese Academy of Sciences\textbf{ (NAOC),} during the year from 2006 to 2009. We obtained pure $H\alpha$ luminosity for each galaxy and corrected the luminosity for $[NII]$ emission, filter transmission and extinction. We also classified these galaxies based on their morphology and interaction. We found that the distribution of star-forming \textbf{regions} in these galaxies is related to this classification. As the merging process advanced, these galaxies tend to have a more compact distribution of star-forming region, higher \textbf{$L_{IR}$} and warmer IR-color ($f_{60}/f_{100}$). \textbf{These} results imply that the degree of dynamical disturbance plays an important role in determining the distribution of star-forming region.

We demonstrate an all-optical method for controlling the transverse motion of ionization injected electron beam, by utilizing the transversely asymmetrical wakefield via adjusting the shape of the laser focal spot. When the laser spot shape is changed from the circular to the obliquely elliptic in experiment, the electron beam shape becomes from elliptic to three different shapes. The 3D-PIC simulation results agree well with experiment, and it shows the trajectories of the accelerated electrons change from undulation to helix. Such an all-optical method could be useful for convenient control of the transverse motion of an electron beam which results in synchrotron radiation with orbit angular momentum.