In dyadic interactions, observing physical contact between interactants is crucial to understand the nature and quality of their interaction. To facilitate the systematic annotation of physical contact from images, we developed Human Contact Annotator, ...

In parent-child interactions (PCIs), there is frequent physical contact between the two actors. Quantifying this contact provides valuable input to assess the nature of the interaction or the relation between parent and child. Here, we explore the ...

Despite researchers having extensively studied various ways to track body pose on-the-go, most prior work does not take into account wheelchair users, leading to poor tracking performance. Wheelchair users could greatly benefit from this pose ...

In recent years, there has been a growing interest in multimodal and multi-source data due to their ability to introduce heterogeneous information. Studies have demonstrated that combining such information enhances the performance of Recommender Systems ...

Accurate pose estimation of surgical instruments is crucial for analyzing robotic surgery videos using computer vision techniques. However, the scarcity of suitable public datasets poses a challenge in this regard. To address this issue, we have ...

The utilization of the triplane-based radiance fields has gained attention in recent years due to its ability to effectively disentangle 3D scenes with a high-quality representation and low computation cost. A key requirement of this method is the ...

Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that may ...

Implicit scene representation has attracted a lot of attention in recent research of computer vision and graphics. Most prior methods focus on how to reconstruct 3D scene representation from a set of images. In this work, we demonstrate the ...

Learning visual features from unlabeled images has proven successful for semantic categorization, often by mapping different views of the same object to the same feature to achieve recognition invariance. However, visual recognition involves not ...

Automatic estimation of 3D human pose from monocular RGB images is a challenging and unsolved problem in computer vision. In a supervised manner, approaches heavily rely on laborious annotations and present hampered generalization ability due to ...

Underground coal mines face the threat of gas explosions, where drill pipes play a crucial role in reducing natural gas concentration, directly impacting coal mine safety. In this study, Matching DPC model, which simplifies and enhances the ...

The robust human representation embedding is the key challenge of the person-identification task. Although the previous methods achieve competitive results, they still depend on the appearance feature which can be failed in the pedestrian surveillance ...

Video matting is a core but arduous task in computer vision and digital image processing. Our research specifically targets the improvement of human matting performance in the hand region, a notoriously difficult aspect due to factors, e.g., motion ...

Existing pose estimation models perform poorly on wheelchair users due to a lack of representation in training data. We present a data synthesis pipeline to address this disparity in data collection and subsequently improve pose estimation performance ...

The development of advanced robotic systems that can be operated effortlessly by humans is crucial for expanding the capabilities of human-robot interaction and collaboration. In this work, we propose a system that enables real-time and non-...

Estimating the pose of multiple objects has improved substantially since deep learning became widely used. However, the performance deteriorates when the objects are highly similar in appearance or when occlusions are present. This issue is ...

Pose estimation is a computer vision task used to estimate a skeleton of dynamic systems to predict future movements. Most of the research in this direction is based on a supervised learning approach which requires a massive amount of labeled ...

Pose Estimation is an important component of many real-world computer vision systems. Most existing pose estimation algorithms need a large number of point correspondences to accurately determine the pose of an object. Since the number of point ...

To address the difficulty in expressing the correlation between different local features extracted by the current person re-identification feature extraction methods, and the challenge of effectively integrating local features with global features,...

Robust feature matching is a fundamental capability for visual SLAM. It remains, however, a challenging task, particularly for changed environments. Some researchers use semantic segmentation to remove potentially dynamic objects which cause ...