相关论文: Learning Behavioral Representations of Human Mobil…

We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings:…

Robotic detection of people in crowded and/or cluttered human-centered environments including hospitals, long-term care, stores and airports is challenging as people can become occluded by other people or objects, and deform due to…

This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our…

Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new…

We propose an action-conditional human motion generation method using variational implicit neural representations (INR). The variational formalism enables action-conditional distributions of INRs, from which one can easily sample…

Urban region profiling can benefit urban analytics. Although existing studies have made great efforts to learn urban region representation from multi-source urban data, there are still three limitations: (1) Most related methods focused…

Considering the close connection between action recognition and human pose estimation, we design a Collaboratively Self-supervised Video Representation (CSVR) learning framework specific to action recognition by jointly factoring in…

Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial context, leading to…

We describe a novel metric-based learning approach that introduces a multimodal framework and uses deep audio and geophone encoders in siamese configuration to design an adaptable and lightweight supervised model. This framework eliminates…

Inspired by ideas in cognitive science, we propose a novel and general approach to solve human motion understanding via pattern completion on a learned latent representation space. Our model outperforms current state-of-the-art methods in…

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences…

Modeling and reproducing crowd behaviors are important in various domains including psychology, robotics, transport engineering and virtual environments. Conventional methods have focused on synthesizing momentary scenes, which have…

We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. Specifically, we propose a pretraining stage in which a motion…

Recently, learning effective representations of urban regions has gained significant attention as a key approach to understanding urban dynamics and advancing smarter cities. Existing approaches have demonstrated the potential of leveraging…

Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to extract representation…

Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected data and addressing the suboptimal nature of some…

Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised…

With increasing focus on privacy protection, alternative methods to identify vehicle operator without the use of biometric identifiers have gained traction for automotive data analysis. The wide variety of sensors installed on modern…

Large language models have become multimodal, and many of them are said to integrate their modalities using common representations. If this were true, a drawing of a car as an image, for instance, should map to a similar area in the latent…

This work presents a methodology for modeling and predicting human behavior in settings with N humans interacting in highly multimodal scenarios (i.e. where there are many possible highly-distinct futures). A motivating example includes…