Related papers: MotionAGFormer: Enhancing 3D Human Pose Estimation…

Although the application of Transformers in 3D point cloud processing has achieved significant progress and success, it is still challenging for existing 3D Transformer methods to efficiently and accurately learn both valuable global…

Traffic forecasting is a cornerstone of smart city management, enabling efficient resource allocation and transportation planning. Deep learning, with its ability to capture complex nonlinear patterns in spatiotemporal (ST) data, has…

Capturing the dependencies between joints is critical in skeleton-based action recognition task. Transformer shows great potential to model the correlation of important joints. However, the existing Transformer-based methods cannot capture…

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…

Human motion prediction is a challenging task due to the stochasticity and aperiodicity of future poses. Recently, graph convolutional network has been proven to be very effective to learn dynamic relations among pose joints, which is…

While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares…

The escalating threat of weapon-related violence necessitates automated detection systems capable of pixel-level precision for accurate threat assessment in real-time security applications. Traditional weapon detection approaches rely on…

Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer…

A novel 4K video frame interpolator based on bilateral transformer (BiFormer) is proposed in this paper, which performs three steps: global motion estimation, local motion refinement, and frame synthesis. First, in global motion estimation,…

Convolutional neural network (CNN) based methods have achieved great successes in medical image segmentation, but their capability to learn global representations is still limited due to using small effective receptive fields of convolution…

Medical image segmentation plays an important role in computer-aided diagnosis. Existing methods mainly utilize spatial attention to highlight the region of interest. However, due to limitations of medical imaging devices, medical images…

Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in Transformers can be…

In person re-identification (re-ID), extracting part-level features from person images has been verified to be crucial to offer fine-grained information. Most of the existing CNN-based methods only locate the human parts coarsely, or rely…

We propose a new loss function, called motion loss, for the problem of monocular 3D Human pose estimation from 2D pose. In computing motion loss, a simple yet effective representation for keypoint motion, called pairwise motion encoding, is…

Multi-modal human action segmentation is a critical and challenging task with a wide range of applications. Nowadays, the majority of approaches concentrate on the fusion of dense signals (i.e., RGB, optical flow, and depth maps). However,…

Convolutional neural networks (CNNs) have been the consensus for medical image segmentation tasks. However, they suffer from the limitation in modeling long-range dependencies and spatial correlations due to the nature of convolution…

Multimodal MRI is essential for brain tumor segmentation, yet missing modalities in clinical practice cause existing methods to exhibit >40% performance variance across modality combinations, rendering them clinically unreliable. We propose…

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences…

3D occupancy, an advanced perception technology for driving scenarios, represents the entire scene without distinguishing between foreground and background by quantifying the physical space into a grid map. The widely adopted…

Multi-modal MR imaging is routinely used in clinical practice to diagnose and investigate brain tumors by providing rich complementary information. Previous multi-modal MRI segmentation methods usually perform modal fusion by concatenating…