Related papers: Single-stage Multi-human Parsing via Point Sets an…

Compared to joint position, the accuracy of joint rotation and shape estimation has received relatively little attention in the skinned multi-person linear model (SMPL)-based human mesh reconstruction from multi-view images. The work in…

Even though convolutional neural networks (CNNs) are driving progress in medical image segmentation, standard models still have some drawbacks. First, the use of multi-scale approaches, i.e., encoder-decoder architectures, leads to a…

We propose a scalable neural network framework to reconstruct the 3D mesh of a human body from multi-view images, in the subspace of the SMPL model. Use of multi-view images can significantly reduce the projection ambiguity of the problem,…

We develop a robust multi-scale structure-aware neural network for human pose estimation. This method improves the recent deep conv-deconv hourglass models with four key improvements: (1) multi-scale supervision to strengthen contextual…

Human skeletons and RGB sequences are both widely-adopted input modalities for human action recognition. However, skeletons lack appearance features and color data suffer large amount of irrelevant depiction. To address this, we introduce…

Millimeter-wave (mmWave) radar offers robust sensing capabilities in diverse environments, making it a highly promising solution for human body reconstruction due to its privacy-friendly and non-intrusive nature. However, the significant…

Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure…

Multi-person pose estimation generally follows top-down and bottom-up paradigms. Both of them use an extra stage ($\boldsymbol{e.g.,}$ human detection in top-down paradigm or grouping process in bottom-up paradigm) to build the relationship…

Mass spectrometry imaging (MSI) enables label-free visualization of molecular distributions across tissue samples but generates large and complex datasets that require effective peak picking to reduce data size while preserving meaningful…

In biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures. However, it is slow, expensive, and harmful to cells. In this paper, we model it as a deep learning task…

Accurate microscopic medical image segmentation plays a crucial role in diagnosing various cancerous cells and identifying tumors. Driven by advancements in deep learning, convolutional neural networks (CNNs) and transformer-based models…

Despite the noticeable progress in perceptual tasks like detection, instance segmentation and human parsing, computers still perform unsatisfactorily on visually understanding humans in crowded scenes, such as group behavior analysis,…

Existing alignment-based methods have to employ the pretrained human parsing models to achieve the pixel-level alignment, and cannot identify the personal belongings (e.g., backpacks and reticule) which are crucial to person re-ID. In this…

Communities are of great importance for understanding graph structures in social networks. Some existing community detection algorithms use a single prototype to represent each group. In real applications, this may not adequately model the…

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic…

Medical image segmentation has been significantly advanced by deep learning (DL) techniques, though the data scarcity inherent in medical applications poses a great challenge to DL-based segmentation methods. Self-supervised learning offers…

Deep learning-based point cloud modeling has been widely investigated as an indispensable component of general shape analysis. Recently, transformer and state space model (SSM) have shown promising capacities in point cloud learning.…

Human pose estimation is a fundamental yet challenging task in computer vision. Although deep learning techniques have made great progress in this area, difficult scenarios (e.g., invisible keypoints, occlusions, complex multi-person…

The objective of this work is to explore how to effectively and efficiently adapt pre-trained visual foundation models to various downstream tasks of semantic segmentation. Previous methods usually fine-tuned the entire networks for each…

Human instance matting aims to estimate an alpha matte for each human instance in an image, which is challenging as it easily fails in complex cases requiring disentangling mingled pixels belonging to multiple instances along hairy and thin…