Related papers: Ego2Hands: A Dataset for Egocentric Two-hand Segme…
Accurate hand pose estimation at joint level has several uses on human-robot interaction, user interfacing and virtual reality applications. Yet, it currently is not a solved problem. The novel deep learning techniques could make a great…
The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large,…
Robotic grasping plays an important role in the field of robotics. The current state-of-the-art robotic grasping detection systems are usually built on the conventional vision, such as RGB-D camera. Compared to traditional frame-based…
Understanding human behavior from complementary egocentric (ego) and exocentric (exo) points of view enables the development of systems that can support workers in industrial environments and enhance their safety. However, progress in this…
The absence of large scale datasets with pixel-level supervisions is a significant obstacle for the training of deep convolutional networks for scene text segmentation. For this reason, synthetic data generation is normally employed to…
Smart glass is emerging as an useful device since it provides plenty of insights under hands-busy, eyes-on-task situations. To understand the context of the wearer, 6D object pose estimation in egocentric view is becoming essential.…
The surgical usage of Mixed Reality (MR) has received growing attention in areas such as surgical navigation systems, skill assessment, and robot-assisted surgeries. For such applications, pose estimation for hand and surgical instruments…
Egocentric temporal action segmentation in videos is a crucial task in computer vision with applications in various fields such as mixed reality, human behavior analysis, and robotics. Although recent research has utilized advanced…
We present EMBED (Egocentric Models Built with Exocentric Data), a method designed to transform exocentric video-language data for egocentric video representation learning. Large-scale exocentric data covers diverse activities with…
We address the challenging task of detecting the precise moment when hands make contact with objects in egocentric videos. This frame-level detection is crucial for augmented reality, human-computer interaction, assistive technologies, and…
The rapid advancement of generative AI has raised concerns about the authenticity of digital images, as highly realistic fake images can now be generated at low cost, potentially increasing societal risks. In response, several datasets have…
In this paper, we introduce DA$^2$, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects. The dataset contains about 9M pairs of parallel-jaw grasps,…
Face performance capture and reenactment techniques use multiple cameras and sensors, positioned at a distance from the face or mounted on heavy wearable devices. This limits their applications in mobile and outdoor environments. We present…
Understanding affect is central to anticipating human behavior, yet current egocentric vision benchmarks largely ignore the person's emotional states that shape their decisions and actions. Existing tasks in egocentric perception focus on…
Different video understanding tasks are typically treated in isolation, and even with distinct types of curated data (e.g., classifying sports in one dataset, tracking animals in another). However, in wearable cameras, the immersive…
Remote sensing imagery has attracted significant attention in recent years due to its instrumental role in global environmental monitoring, land usage monitoring, and more. As image databases grow each year, performing automatic…
Designing egocentric 3D hand pose estimation systems that can perform reliably in complex, real-world scenarios is crucial for downstream applications. Previous approaches using RGB or NIR imagery struggle in challenging conditions: RGB…
This paper performs comprehensive analysis on datasets for occlusion-aware face segmentation, a task that is crucial for many downstream applications. The collection and annotation of such datasets are time-consuming and labor-intensive.…
Annotating images with pixel-wise labels is a time-consuming and costly process. Recently, DatasetGAN showcased a promising alternative - to synthesize a large labeled dataset via a generative adversarial network (GAN) by exploiting a small…
Human skin segmentation is a crucial task in computer vision and biometric systems, yet it poses several challenges such as variability in skin color, pose, and illumination. This paper presents a robust data-driven skin segmentation method…