Related papers: ConvFormer: Parameter Reduction in Transformer Mod…

Dynamic representation learning plays a pivotal role in understanding the evolution of linguistic content over time. On this front both context and time dynamics as well as their interplay are of prime importance. Current approaches model…

Video-based 3D human pose and shape estimations are evaluated by intra-frame accuracy and inter-frame smoothness. Although these two metrics are responsible for different ranges of temporal consistency, existing state-of-the-art methods…

Line features are valid complements for point features in man-made environments. 3D-2D constraints provided by line features have been widely used in Visual Odometry (VO) and Structure-from-Motion (SfM) systems. However, how to accurately…

The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…

This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in…

Monocular 3D human pose estimation (HPE) methods estimate the 3D positions of joints from individual images. Existing 3D HPE approaches often use the cropped image alone as input for their models. However, the relative depths of joints…

This paper introduces a novel framework, i.e., RFPose-OT, to enable the 3D human pose estimation from Radio Frequency (RF) signals. Different from existing methods that predict human poses from RF signals on the signal level directly, we…

Recently, the vision transformer and its variants have played an increasingly important role in both monocular and multi-view human pose estimation. Considering image patches as tokens, transformers can model the global dependencies within…

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…

In recent years, a plethora of diverse methods have been proposed for 3D pose estimation. Among these, self-attention mechanisms and graph convolutions have both been proven to be effective and practical methods. Recognizing the strengths…

Estimating 3D human poses only from a 2D human pose sequence is thoroughly explored in recent years. Yet, prior to this, no such work has attempted to unify 2D and 3D pose representations in the shared feature space. In this paper, we…

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been…

Spatio-temporal traffic forecasting is challenging due to complex temporal patterns, dynamic spatial structures, and diverse input formats. Although Transformer-based models offer strong global modeling, they often struggle with rigid…

3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occlusion, noise interference, and missing viewpoints can…

3D human pose estimation (HPE) is crucial in many fields, such as human behavior analysis, augmented reality/virtual reality (AR/VR) applications, and self-driving industry. Videos that contain multiple potentially occluded people captured…

Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One…

3D human pose estimation is fundamental to understanding human behavior. Recently, promising results have been achieved by graph convolutional networks (GCNs), which achieve state-of-the-art performance and provide rather light-weight…

We present a novel method for monocular hand shape and pose estimation at unprecedented runtime performance of 100fps and at state-of-the-art accuracy. This is enabled by a new learning based architecture designed such that it can make use…

3D hand pose is an underexplored modality for action recognition. Poses are compact yet informative and can greatly benefit applications with limited compute budgets. However, poses alone offer an incomplete understanding of actions, as…

The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting. While the uplifting methods themselves are rather efficient, the true computational complexity depends on the…