Related papers: Motion2Motion: Cross-topology Motion Transfer with…
Detecting small targets at range is difficult because there is not enough spatial information present in an image sub-region containing the target to use correlation-based methods to differentiate it from dynamic confusers present in the…
Existing Graph Convolutional Networks to achieve human motion prediction largely adopt a one-step scheme, which output the prediction straight from history input, failing to exploit human motion patterns. We observe that human motions have…
Motion retargeting from a human demonstration to a robot is an effective way to reduce the professional requirements and workload of robot programming, but faces the challenges resulting from the differences between humans and robots.…
Today's touch sensors come in many shapes and sizes. This has made it challenging to develop general-purpose touch processing methods since models are generally tied to one specific sensor design. We address this problem by performing…
Collaborative transport of objects via pushing by multiple robots has many applications, ranging from construction and warehouse environments to post disaster debris clean-up. Achieving collaborative transport over surfaces with different…
Generalist humanoid motion trackers have recently achieved strong simulation metrics by scaling data and training, yet often remain brittle on hardware during sustained teleoperation due to interface- and dynamics-induced errors. We present…
Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally ambiguous for fine-grained motion control, while explicit…
We propose a method to learn, even using a dataset where objects appear only in sparsely sampled views (e.g. Pix3D), the ability to synthesize a pose trajectory for an arbitrary reference image. This is achieved with a cross-modal pose…
Optimizing the morphologies and the controllers that adapt to various tasks is a critical issue in the field of robot design, aka. embodied intelligence. Previous works typically model it as a joint optimization problem and use search-based…
We introduce Temporal Residual Jacobians as a novel representation to enable data-driven motion transfer. Our approach does not assume access to any rigging or intermediate shape keyframes, produces geometrically and temporally consistent…
Segmenting both bone surface and the corresponding acoustic shadow are fundamental tasks in ultrasound (US) guided orthopedic procedures. However, these tasks are challenging due to minimal and blurred bone surface response in US images,…
Accurately reconstructing full-body poses from sparse head and hand trajectories is a foundational challenge for immersive AR/VR telepresence. Current methods often struggle with error accumulation and unnatural joint coordination,…
The cognitive system for human action and behavior has evolved into a deep learning regime, and especially the advent of Graph Convolution Networks has transformed the field in recent years. However, previous works have mainly focused on…
Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional…
Traversing risky terrains with sparse footholds presents significant challenges for legged robots, requiring precise foot placement in safe areas. To acquire comprehensive exteroceptive information, prior studies have employed motion…
Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause a malformed action sequence. Most existing methods borrow ideas from video generation, which naively treat…
Touch data from mobile devices are collected at scale but reveal little about the interactions that produce them. While biomechanical simulations can illuminate motor control processes, they have not yet been developed for touch…
Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely focused on single-image or temporally dense video settings. In…
Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-based action recognition, leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjacency matrix. However,…
Effective human behavior modeling is critical for successful human-robot interaction. Current state-of-the-art approaches for predicting listening head behavior during dyadic conversations employ continuous-to-discrete representations,…