相关论文: Localized Trajectories for 2D and 3D Action Recogn…
Human motion prediction is an essential part for human-robot collaboration. Unlike most of the existing methods mainly focusing on improving the effectiveness of spatiotemporal modeling for accurate prediction, we take effectiveness and…
Gait disabilities are among the most frequent worldwide. Their treatment relies on rehabilitation therapies, in which smart walkers are being introduced to empower the user's recovery and autonomy, while reducing the clinicians effort. For…
Place embeddings generated from human mobility trajectories have become a popular method to understand the functionality of places. Place embeddings with high spatial resolution are desirable for many applications, however, downscaling the…
In this paper, we study the problem of adapting manipulation trajectories involving grasped objects (e.g. tools) defined for a single grasp pose to novel grasp poses. A common approach to address this is to define a new trajectory for each…
Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation…
Generating temporal action proposals remains a very challenging problem, where the main issue lies in predicting precise temporal proposal boundaries and reliable action confidence in long and untrimmed real-world videos. In this paper, we…
Human action recognition from well-segmented 3D skeleton data has been intensively studied and has been attracting an increasing attention. Online action detection goes one step further and is more challenging, which identifies the action…
Skeleton data carries valuable motion information and is widely explored in human action recognition. However, not only the motion information but also the interaction with the environment provides discriminative cues to recognize the…
Human action recognition is regarded as a key cornerstone in domains such as surveillance or video understanding. Despite recent progress in the development of end-to-end solutions for video-based action recognition, achieving…
Generative video editing has enabled several intuitive editing operations for short video clips that would previously have been difficult to achieve, especially for non-expert editors. Existing methods focus on prescribing an object's 3D or…
Most of the existing 3D human pose estimation approaches mainly focus on predicting 3D positional relationships between the root joint and other human joints (local motion) instead of the overall trajectory of the human body (global…
Generalization remains one of the most important desiderata for robust robot learning systems. While recently proposed approaches show promise in generalization to novel objects, semantic concepts, or visual distribution shifts,…
Navigating mobile robots through environments shared with humans is challenging. From the perspective of the robot, humans are dynamic obstacles that must be avoided. These obstacles make the collision-free space nonconvex, which leads to…
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…
This paper uses the capabilities of latent diffusion models (LDMs) to generate realistic RGB human-object interaction scenes to guide humanoid loco-manipulation planning. To do so, we extract from the generated images both the contact…
Tracking objects that move within dynamic environments is a core challenge in robotics. Recent research has advanced this topic significantly; however, many existing approaches remain inefficient due to their reliance on heavy foundation…
Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+D-based action…
Computer vision was long a tool used for aiding visually impaired people to move around their environment and avoid obstacles and falls. Solutions are limited to either indoor or outdoor scenes, which limits the kind of places and scenes…
This study addresses the challenge of performing visual localization in demanding conditions such as night-time scenarios, adverse weather, and seasonal changes. While many prior studies have focused on improving image-matching performance…
Recent advances in tracking sensors and pose estimation software enable smart systems to use trajectories of skeleton joint locations for supervised learning. We study the problem of accurately recognizing sign language words, which is key…