In this paper, we propose CODESCRIBE to model the hierarchical syntax structure of code by introducing a novel triplet position for code summarization.
Stack Overflow is one of the most popular programming communities where developers can seek help for their encountered problems.
Therefore, we propose a semantic decomposition network (SDNet) that introduces two single-task branches to separately address the segmentation of teeth and dental plaque and designs additional constraints to learn category-specific features for each branch, thus facilitating the semantic decomposition and improving the performance of dental plaque segmentation.
Deep learning recommendation models (DLRMs) have been widely applied in Internet companies.
Knowledge graph-to-text (KG-to-text) generation aims to generate easy-to-understand sentences from the KG, and at the same time, maintains semantic consistency between generated sentences and the KG.
Specifically, we first extract multiple code views using compiler tools, and learn the complementary information among them under a contrastive learning framework.
This paper introduces a classification framework to aid ASD diagnosis based on rs-fMRI.
First, a multi-task learning network is proposed to implement AD detection and MMSE score prediction, which exploits feature correlation by adding three multi-task interaction layers between the backbones of the two tasks.
Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering.
Experiments over publicly available datasets demonstrate that our method can help models generate better responses, even such training data are usually impressed as low-quality data.
The two types of features are entered into the parallel encoders paths with residual attention for extracting feature representation, and then fused into a channel-spatial attention module to adaptively focus on the important features between channel and spatial part for the classification task.
Ranked #3 on Audio Classification on ICBHI Respiratory Sound Database (using extra training data)
However, KGs are always incomplete, especially the new constructed COVID-19 KGs.
Based on the RPC warping, we propose the deep learning based satellite MVS (SatMVS) framework for large-scale and wide depth range Earth surface reconstruction.
Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence.
This paper tries to address the problem of stock market prediction leveraging artificial intelligence (AI) strategies.
Face reenactment is a challenging task, as it is difficult to maintain accurate expression, pose and identity simultaneously.
We propose an end-to-end deep learning approach, DeepMI, to classify MI from normal cases as well as identifying the time-occurrence of MI (defined as acute, recent and old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level.
At the population level, we formulate the ideal representation learning task as that of finding a nonlinear map that minimizes the sum of losses characterizing conditional independence (with RKHS) and disentanglement (with GAN).
Ranked #3 on Image Classification on STL-10 (using extra training data)
We provide strong statistical guarantees for the learned representation by establishing an upper bound on the excess error of the objective function and show that it reaches the nonparametric minimax rate under mild conditions.
A multi-grained trajectory graph convolutional networks based and lightweight framework is proposed for habit-unrelated human motion prediction.
The realization of multimode optomechanical interactions in the single-photon strong-coupling regime is a desired task in cavity optomechanics, but it remains a challenge in realistic physical systems.
In this paper, we propose a novel Contextual Alignment Enhanced Cross Graph Attention Network (CAECGAT) for the task of cross-lingual entity alignment, which is able to jointly learn the embeddings in different KGs by propagating cross-KG information through pre-aligned seed alignments.
In this paper, we take the benefits of ConvE and KBGAT together and propose a Relation-aware Inception network with joint local-global structural information for knowledge graph Embedding (ReInceptionE).
We propose a deep dimension reduction approach to learning representations with these characteristics.
We present the proposed model by simulation studies and a real-world data analysis.
In this paper, we present a synthetic aerial dataset, called the WHU dataset, we created for MVS tasks, which, to our knowledge, is the first large-scale multi-view aerial dataset.
We then solve the McKean-Vlasov equation numerically using the forward Euler iteration, where the forward Euler map depends on the density ratio (density difference) between the distribution at current iteration and the underlying target distribution.
Based on this KKT system, a built-in working set with a relatively small size is first determined using the sum of primal and dual variables generated from the previous iteration, then the primal variable is updated by solving a least-squares problem on the working set and the dual variable updated based on a closed-form expression.
Feature selection is important for modeling high-dimensional data, where the number of variables can be much larger than the sample size.
And the global temporal co-occurrence features represent the co-occurrence relationship that different subsequences in a complex motion sequence are appeared simultaneously, which can be obtained automatically with our proposed TrajectoryNet by reorganizing the temporal information as the depth dimension of the input tensor.
To address the challenges in learning deep generative models (e. g., the blurriness of variational auto-encoder and the instability of training generative adversarial networks, we propose a novel deep generative model, named Wasserstein-Wasserstein auto-encoders (WWAE).
In this paper, we first propose a simple method for sure screening interactions (SSI).
On this basis, a special layer, Collinear Equation Layer, is added next to region layer to output the 2D projections of the 3D bounding boxs corners.
Our system trains a novel convolutional neural network to regress the unit quaternion, which represents the 3D rotation, from the partial image inside the bounding box returned by 2D detection systems.
To address this problem, we consider variational inference for bi-level variable selection (BIVAS).
In this novel model, we first map each pixel value of an image into a Hilbert space by using a nonlinear map, and then define a coupled image of an original image in order to construct a kernel function.
We show that the linear combination of structured labels can well model the saliency distribution in local regions.
Through such analysis, we summarized some characteristics and problems which are reflected by people with different levels of knowledge on the comprehension of difficult science and technology literature, which can be modeled in semantic link network.
On this basis, the mechanism of the BSR system response to MPAM signal inputs is elucidated, and a corresponding decoding scheme is proposed.
In this study, we present an adaptive Simulated Annealing based scheduling algorithm aggregated with a dynamic task clustering strategy (or ASA-DTC for short) for satellite observation scheduling problems (SOSPs).
In this paper, we consider the problem of recovering a sparse signal based on penalized least squares formulations.