3DQA has gained considerable attention due to its enhanced spatial understanding capabilities compared to image-based VQA. However, existing 3DQA methods have explicitly focused on integrating text and color-coded point cloud features, thereby ...

Image-based virtual try-on aims to fit a target garment to a reference person. Most existing methods are limited to solving the Garment-To-Person (G2P) try-on task that transfers a garment from a clean product image to the reference person and do not ...

Generating high-quality and diverse human images presents a substantial difficulty within the field of computer vision, especially in developing controllable generative models that can utilize input from various modalities. Such models could ...

• A novel framework for controllable human image generation with multimodal controls is proposed. The framework’s flexibility lies in its ability to incorporate different types of control signals, which can be modified to suit the ...

Image-based virtual try-on aims at transferring a target in-shop garment onto a reference person, and has garnered significant attention from the research communities recently. However, previous methods have faced severe challenges in handling occlusion ...

Recent GCN-based works have achieved remarkable results for skeleton-based human action recognition. Nevertheless, while existing approaches extensively investigate pairwise joint relationships, only a limited number of models explore the ...

Existing cross-modal frameworks have achieved impressive performance in point cloud object representations learning, where a 2D image encoder is employed to transfer knowledge to a 3D point cloud encoder. However, the local structures between ...

Point cloud upsampling has been extensively studied, however, the existing approaches suffer from the losing of structural information due to neglect of spatial dependencies between points. In this work, we propose PU-GAT, a novel 3D point cloud ...

Display Omitted

Subspace clustering has attracted much attention because of its ability to group unlabeled high-dimensional data into multiple subspaces. Existing graph-based subspace clustering methods focus on either the sparsity of data affinity or the low rank of ...

Few-shot colorization aims to learn a model to colorize images with little training data. Yet, existing models often fail to keep color consistency due to ignored patch correlations of the images. In this paper, we propose PCCNet, a novel Patch-...

Graph Convolutional Networks (GCNs) have been widely used in skeleton‐based action recognition. Though significant performance has been achieved, it is still challenging to effectively model the complex dynamics of skeleton sequences. A novel ...

A novel position‐aware graph convolutional networks for skeleton‐based action recognition is proposed. Our model investigated the position encoding modules and the subgraph masking operator to address some defects holding in existing models, such as the ...

Recent multimodal sentiment analysis works focus on establishing sophisticated fusion strategies for better performance. However, a major limitation of these works is that they ignore effective modality representation learning before ...

• Before multimodal fusion, we must perform modality representation learning.
• ...

The recently developed pure transformer architectures have attained promising accuracy on point cloud learning benchmarks compared to convolutional neural networks. However, existing point cloud Transformers are computationally expensive because ...

Display Omitted

In recent years, approaches based on graph convolutional networks (GCNs) have achieved state-of-the-art performance in point cloud learning. The typical pipeline of GCNs is modeled as a two-stage learning process: graph construction ...

Following the success of 2D human pose estimation from a single image, a lot of work focus on video-based 3D human pose estimation by exploiting temporal information. In this scenario, several recent works have achieved significant advances via ...

In this work, we present a novel end-to-end semantic segmentation framework for multi-human parsing, which integrates both the high- and low-level features. Our framework includes three modules: segmentation module, pose estimation module, and ...

• We present co-skeletons, a new method that computes consistent curve skeletons for 3D shapes from a given family.

Display Omitted

We present co-skeletons, a new method that computes consistent curve skeletons for 3D shapes from a given family. We compute co-skeletons in terms of sampling density and semantic relevance, while preserving the desired characteristics ...

Computer aided modeling and simulation of nanomaterials can describe the correlation between the material’s microstructure and its macroscopic properties quantitatively. In this paper, we propose an integrated modeling, simulation, and visualization ...

In this paper, we present an interactive approach for near-isometric shape correspondence. Our key motivation is that the intention of the users in the correspondence problem is valuable, which helps to not only reduce search space for finding the ...

In this paper, we present an interactive approach for shape co-segmentation via label propagation. Our intuitive approach is able to produce error-free results and is very effective at handling out-of-sample data. Specifically, we start by over-...

Many shape co-segmentation methods employ multiple descriptors to measure the similarities between parts of a set of shapes in a descriptor space. Different shape descriptors characterize a shape in different aspects. Simply concatenating them into a ...