Related papers: EMO-X: Efficient Multi-Person Pose and Shape Estim…
We propose a novel approach for generating text-guided human-object interactions (HOIs) that achieves explicit joint-level interaction modeling in a computationally efficient manner. Previous methods represent the entire human body as a…
Millimeter-wave radar offers a privacy-preserving and lighting-invariant alternative to RGB sensors for Human Pose Estimation (HPE) task. However, the radar signals are often sparse due to specular reflection, making the extraction of…
3D human pose lifting is a promising research area that leverages estimated and ground-truth 2D human pose data for training. While existing approaches primarily aim to enhance the performance of estimated 2D poses, they often struggle when…
Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. However, naively learning a mapping between egocentric videos and human motions is…
State Space Model (SSM)-based machine learning architectures have recently gained significant attention for processing sequential data. Mamba, a recent sequence-to-sequence SSM, offers competitive accuracy with superior computational…
We propose embodied scene-aware human pose estimation where we estimate 3D poses based on a simulated agent's proprioception and scene awareness, along with external third-person observations. Unlike prior methods that often resort to…
In recent years, with the development of deep learning, electroencephalogram (EEG) classification networks have achieved certain progress. Transformer-based models can perform well in capturing long-term dependencies in EEG signals.…
Recently, State Space Models (SSMs), with Mamba as a prime example, have shown great promise for long-range dependency modeling with linear complexity. Then, Vision Mamba and the subsequent architectures are presented successively, and they…
EEG-based emotion recognition holds significant potential in the field of brain-computer interfaces. A key challenge lies in extracting discriminative spatiotemporal features from electroencephalogram (EEG) signals. Existing studies often…
With intelligent room-side sensing and service robots widely deployed, human motion prediction (HMP) is essential for safe, proactive assistance. However, many existing HMP methods either produce a single, deterministic forecast that…
Transformer-based methods for 3D human pose estimation face significant computational challenges due to the quadratic growth of self-attention mechanism complexity with sequence length. Recently, the Mamba model has substantially reduced…
Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal…
Human pose estimation methods work well on isolated people but struggle with multiple-bodies-in-proximity scenarios. Previous work has addressed this problem by conditioning pose estimation by detected bounding boxes or keypoints, but…
Comprehensively and flexibly capturing the complex spatio-temporal dependencies of human motion is critical for multi-person motion prediction. Existing methods grapple with two primary limitations: i) Inflexible spatiotemporal…
Human body fitting, which aligns parametric body models such as SMPL to raw 3D point clouds of clothed humans, serves as a crucial first step for downstream tasks like animation and texturing. An effective fitting method should be both…
Transformers have proven effective in language modeling but are limited by high computational and memory demands that grow quadratically with input sequence length. State space models (SSMs) offer a promising alternative by reducing…
Human pose and shape estimation methods continue to suffer in situations where one or more parts of the body are occluded. More importantly, these methods cannot express when their predicted pose is incorrect. This has serious consequences…
Micro-expressions are typically regarded as unconscious manifestations of a person's genuine emotions. However, their short duration and subtle signals pose significant challenges for downstream recognition. We propose a multi-task learning…
Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human…
In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While…