Few-shot semantic segmentation uses a few annotated data of a specific class in the support set to segment the target of the same class in the query set. Most existing approaches fail to perform well when there are significant intra-class ...

• We propose a Query Prototype Generation Module to alleviate appearance discrepancy.
• We propose a Support Auxiliary Refinement Module to mine more class information.
• Extensive experiments prove the proposed model outperforms ...

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Although progress has been made recently by combining prototype-based metric learning, existing methods still face ...

Semi-supervised video object segmentation is the process of tracking and segmenting objects in a video sequence based on annotated masks for one or more frames. Recently, memory-based methods have attracted a significant amount of attention due ...

• Time-varying sensor and dynamic feature memory reduce redundancy but retain key data.
• Efficient memory reader has smaller footprint and reduces computational overhead.
• Spatial constraint module maintains response map to filter ...

Creating visualizations of multiple volumetric density fields is demanding in virtual reality (VR) applications, which often include divergent volumetric density distributions mixed with geometric models and physics-based simulations. Real-time rendering ...

Recently, memory-based methods have exhibited remarkable performance in Video Object Segmentation (VOS) by employing non-local pixel-wise matching between the query and memory. Nevertheless, these methods suffer from two limitations: 1) Non-local pixel-...

Chinese calligraphy is one of the excellent expressions of Chinese traditional art. But people without domain knowledge of calligraphy can hardly read, appreciate, or learn this art form, due to it contains many brush strokes with unique shapes ...

Existing lifting networks for regressing 3D human poses from 2D single-view poses are typically constructed with linear layers based on graph-structured representation learning. In sharp contrast to them, this paper presents Grid Convolution (GridConv), ...

Video object segmentation (VOS) has been widely used in the fields of computer vision. However, existing VOS algorithms have drawbacks, such as difficulty with object deformation, occlusion, and fast motion. We therefore propose an effective VOS ...

Adder Neural Network (AdderNet) provides a new way for developing energy-efficient neural networks by replacing the expensive multiplications in convolution with cheaper additions (i.e., ℓ₁-norm). To achieve higher hardware efficiency, it is necessary to ...

Network architecture plays a key role in the deep learning-based computer vision system. The widely-used convolutional neural network and transformer treat the image as a grid or sequence structure, which is not flexible to capture irregular and complex ...

Deep neural network models with strong feature extraction capacity are prone to overfitting and fail to adapt quickly to new tasks with few samples. Gradient-based meta-learning approaches can minimize overfitting and adapt to new tasks fast, but ...

Shadow removal is a challenging computer vision and multimedia task that aims to restore image content in shadow regions. The state-of-the-art shadow removal methods introduce artifacts near shadow boundaries or inconsistencies between shadow and ...

While data-driven fluid simulation methods greatly replace the physics-based fluid solver and achieve high quality results, it is a challenge to get enough realistic effect with less time. The Huge neural network models brought by the complexity ...

In this paper, we explore the spatial–temporal redundancy in video object segmentation (VOS) under semi-supervised context with the purpose to improve the computational efficiency. Recently, memory-based methods have attracted great attention for ...$\mathcal{}\mathcal{}$$\mathcal{}$

Deploying convolutional neural networks (CNNs) on mobile devices is difficult due to the limited memory and computation resources. We aim to design efficient neural networks for heterogeneous devices including CPU and GPU, by exploiting the ...

This paper presents a novel approach to anti-aliased ray marching by indirect shading in cube-map space. Our volume renderer firstly performs ray marching on each visible interior pixel of a maximum-resolution-limited cube map, and then resamples (...

Deep convolutional neural networks (CNNs) are often of sophisticated design with numerous learnable parameters for the accuracy reason. To alleviate the expensive costs of deploying them on mobile devices, recent works have made huge efforts for ...

Transformer is a new kind of neural architecture which encodes the input data as powerful features via the attention mechanism. Basically, the visual transformers first divide the input images into several local patches and then calculate both ...