Related papers: LACE: Latent Visual Representation for Cross-Embod…

Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…

Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…

Understanding vision and language representations of product content is vital for search and recommendation applications in e-commerce. As a backbone for online shopping platforms and inspired by the recent success in representation…

As robots are increasingly deployed in real-world scenarios, a key question is how to best transfer knowledge learned in one environment to another, where shifting constraints and human preferences render adaptation challenging. A central…

We propose a method to facilitate exploration and analysis of new large data sets. In particular, we give an unsupervised deep learning approach to learning a latent representation that captures semantic similarity in the data set. The core…

Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods are reminiscent of the well-known word2vec embedding…

Human demonstrations offer rich environmental diversity and scale naturally, making them an appealing alternative to robot teleoperation. While this paradigm has advanced robot-arm manipulation, its potential for the more challenging,…

Zero-shot learning (ZSL) aims at recognizing unseen classes with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space (FS) shared by both seen and unseen classes, i.e., attributes or…

Supervised deep learning models depend on massive labeled data. Unfortunately, it is time-consuming and labor-intensive to collect and annotate bitemporal samples containing desired changes. Transfer learning from pre-trained models is…

To act in the world, robots rely on a representation of salient task aspects: for example, to carry a coffee mug, a robot may consider movement efficiency or mug orientation in its behavior. However, if we want robots to act for and with…

Although self-/un-supervised methods have led to rapid progress in visual representation learning, these methods generally treat objects and scenes using the same lens. In this paper, we focus on learning representations for objects and…

We investigate a reinforcement approach for distributed sensing based on the latent space derived from multi-modal deep generative models. Our contribution provides insights to the following benefits: Detections can be exchanged effectively…

With large language models, robots can understand language more flexibly and more capable than ever before. This survey reviews and situates recent literature into a spectrum with two poles: 1) mapping between language and some manually…

Self-supervised learning (SSL) has attracted much interest in remote sensing and earth observation due to its ability to learn task-agnostic representations without human annotation. While most of the existing SSL works in remote sensing…

Robots need both visual and contact sensing to effectively estimate the state of their environment. Camera RGBD data provides rich information of the objects surrounding the robot, and shape priors can help correct noise and fill in gaps…

We propose a novel deep training algorithm for joint representation of audio and visual information which consists of a single stream network (SSNet) coupled with a novel loss function to learn a shared deep latent space representation of…

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if…

Solving the camera-to-robot pose is a fundamental requirement for vision-based robot control, and is a process that takes considerable effort and cares to make accurate. Traditional approaches require modification of the robot via markers,…

Learning new robot tasks on new platforms and in new scenes from only a handful of demonstrations remains challenging. While videos of other embodiments - humans and different robots - are abundant, differences in embodiment, camera, and…

Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, such degrees of intelligence are not easy to obtain.…