Related papers: DDNet: Dual-path Decoder Network for Occlusion Rel…
Recent work by Lakshminarayanan and Singh [2020] provided a dual view for fully connected deep neural networks (DNNs) with rectified linear units (ReLU). It was shown that (i) the information in the gates is analytically characterised by a…
Convolutional neural networks model the transformation of the input sensory data at the bottom of a network hierarchy to the semantic information at the top of the visual hierarchy. Feedforward processing is sufficient for some object…
Recently, dense connections have attracted substantial attention in computer vision because they facilitate gradient flow and implicit deep supervision during training. Particularly, DenseNet, which connects each layer to every other layer…
Background objects occluded in some views of a light field (LF) camera can be seen by other views. Consequently, occluded surfaces are possible to be reconstructed from LF images. In this paper, we handle the LF de-occlusion (LF-DeOcc)…
Proper segmentation of organs-at-risk is important for radiation therapy, surgical planning, and diagnostic decision-making in medical image analysis. While deep learning-based segmentation architectures have made significant progress, they…
Recently, Deep Convolution Networks (DCNNs) have been applied to the task of face alignment and have shown potential for learning improved feature representations. Although deeper layers can capture abstract concepts like pose, it is…
Occlusion Boundary Estimation (OBE) identifies boundaries arising from both inter-object occlusions and self-occlusion within individual objects. This task is closely related to Monocular Depth Estimation (MDE), which infers depth from a…
Deep learning is typically performed by learning a neural network solely from data in the form of input-output pairs ignoring available domain knowledge. In this work, the Constraint Guided Gradient Descent (CGGD) framework is proposed that…
High-performance deep neural network (DNN)-based systems are in high demand in edge environments. Due to its high computational complexity, it is challenging to deploy DNNs on edge devices with strict limitations on computational resources.…
With the development of deep learning, the structure of convolution neural network is becoming more and more complex and the performance of object recognition is getting better. However, the classification mechanism of convolution neural…
A new data-driven method for operator learning of stochastic differential equations(SDE) is proposed in this paper. The central goal is to solve forward and inverse stochastic problems more effectively using limited data. Deep operator…
Aspect term extraction is one of the important subtasks in aspect-based sentiment analysis. Previous studies have shown that using dependency tree structure representation is promising for this task. However, most dependency tree structures…
In recent years, deep convolutional neural networks have shown fascinating performance in the field of image denoising. However, deeper network architectures are often accompanied with large numbers of model parameters, leading to high…
Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not…
Nowadays, service robots are appearing more and more in our daily life. For this type of robot, open-ended object category learning and recognition is necessary since no matter how extensive the training data used for batch learning, the…
Multimodal emotion recognition in conversations aims to infer utterance-level emotions by jointly modeling textual, acoustic, and visual cues within context. Despite recent progress, key challenges remain, including redundant cross-modal…
To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions…
Graph Neural Networks (GNNs) with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressiveness ability is limited by: (1) Existing methods often…
Micro-expression recognition (\textbf{MER}) has attracted lots of researchers' attention in a decade. However, occlusion will occur for MER in real-world scenarios. This paper deeply investigates an interesting but unexplored challenging…
Causal representation learning seeks to uncover causal relationships among high-level latent variables from low-level, entangled, and noisy observations. Existing approaches often either rely on deep neural networks, which lack…