相关论文: HVIS: A Human-like Vision and Inference System for…

Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target…

Vision based human pose estimation is an non-invasive technology for Human-Computer Interaction (HCI). Direct use of the hand as an input device provides an attractive interaction method, with no need for specialized sensing equipment, such…

While current vision algorithms excel at many challenging tasks, it is unclear how well they understand the physical dynamics of real-world environments. Here we introduce Physion, a dataset and benchmark for rigorously evaluating the…

Human Motion Segmentation (HMS), which aims to partition a video into non-overlapping segments corresponding to different human motions, has recently attracted increasing research attention. Existing HMS approaches are predominantly based…

We present Sapiens, a family of models for four fundamental human-centric vision tasks -- 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference…

Understanding the relationship between different parts of an image is crucial in a variety of applications, including object recognition, scene understanding, and image classification. Despite the fact that Convolutional Neural Networks…

Human motion detection is getting considerable attention in the field of Artificial Intelligence (AI) driven healthcare systems. Human motion can be used to provide remote healthcare solutions for vulnerable people by identifying particular…

Human motion prediction is crucial for human-centric multimedia understanding and interacting. Current methods typically rely on ground truth human poses as observed input, which is not practical for real-world scenarios where only raw…

For safe navigation around pedestrians, automated vehicles (AVs) need to plan their motion by accurately predicting pedestrians trajectories over long time horizons. Current approaches to AV motion planning around crosswalks predict only…

We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks. In contrast to previous models, UViM has the same functional form for all tasks; it requires no task-specific modifications which require…

We propose a framework for vision-based human pose estimation and motion prediction that gives conformal prediction guarantees for certifiably safe human-robot collaboration. Our framework combines aleatoric uncertainty estimation with OOD…

The anticipation of human behavior is a crucial capability for robots to interact with humans safely and efficiently. We employ a smart edge sensor network to provide global observations, future predictions, and goal information to…

We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…

We demonstrate an improved vision system that learns a model of its environment using a self-supervised, predictive learning method. The system includes a pan-tilt camera, a foveated visual input, a saccading reflex to servo the foveated…

A Human Computer Interface (HCI) System for playing games is designed here for more natural communication with the machines. The system presented here is a vision-based system for detection of long voluntary eye blinks and interpretation of…

The capabilities of automated vehicles are advancing rapidly, yet achieving full autonomy remains a significant challenge, requiring ongoing human cognition in decision-making processes. Incorporating human cognition into control algorithms…

Gaze-following in child-robot interaction improves attention, recall, and learning, but requires expensive platforms (\$30,000+), sensors, algorithms, and raises privacy concerns. We propose a framework that avoids sensors and computation…

Existing models of human visual attention are generally unable to incorporate direct task guidance and therefore cannot model an intent or goal when exploring a scene. To integrate guidance of any downstream visual task into attention…

Reconstructing physically plausible human motion from monocular videos remains a challenging problem in computer vision and graphics. Existing methods primarily focus on kinematics-based pose estimation, often leading to unrealistic results…

Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos. However, compared to using appearance, it has some blind spots, such as the fact that objects become invisible if they do not…