相关论文: Merging and Disentangling Views in Visual Reinforc…
The vast majority of visual animals actively control their eyes, heads, and/or bodies to direct their gaze toward different parts of their environment. In contrast, recent applications of reinforcement learning in robotic manipulation…
Various factors, such as identities, views (poses), and illuminations, are coupled in face images. Disentangling the identity and view representations is a major challenge in face recognition. Existing face recognition systems either use…
Humans rely on the synergy of their senses for most essential tasks. For tasks requiring object manipulation, we seamlessly and effectively exploit the complementarity of our senses of vision and touch. This paper draws inspiration from…
The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…
We introduce a novel representation learning method to disentangle pose-dependent as well as view-dependent factors from 2D human poses. The method trains a network using cross-view mutual information maximization (CV-MIM) which maximizes…
Can we endow visuomotor robots with generalization capabilities to operate in diverse open-world scenarios? In this paper, we propose \textbf{Maniwhere}, a generalizable framework tailored for visual reinforcement learning, enabling the…
Multi-view clustering, a long-standing and important research problem, focuses on mining complementary information from diverse views. However, existing works often fuse multiple views' representations or handle clustering in a common…
With the rapid advancement of autonomous driving technology, there is a growing need for enhanced safety and efficiency in the automatic environmental perception of vehicles during their operation. In modern vehicle setups, cameras and…
Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion…
How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. delivering a package)? We study this question by integrating a generic perceptual skill set…
Deep reinforcement learning has been applied successfully to solve various real-world problems and the number of its applications in the multi-agent settings has been increasing. Multi-agent learning distinctly poses significant challenges…
Multi-view clustering (MVC) can explore common semantics from unsupervised views generated by different sources, and thus has been extensively used in applications of practical computer vision. Due to the spatio-temporal asynchronism,…
Multi-View Reinforcement Learning (MVRL) seeks to provide agents with multi-view observations, enabling them to perceive environment with greater effectiveness and precision. Recent advancements in MVRL focus on extracting latent…
3D human pose estimation is a key enabling technology for applications such as healthcare monitoring, human-robot collaboration, and immersive gaming, but real-world deployment remains challenged by viewpoint variations. Existing methods…
Visual-inertial sensors have a wide range of applications in robotics. However, good performance often requires different sophisticated motion routines to accurately calibrate camera intrinsics and inter-sensor extrinsics. This work…
In recent years, many mammographic image analysis methods have been introduced for improving cancer classification tasks. Two major issues of mammogram classification tasks are leveraging multi-view mammographic information and…
We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together. Based on the MAD paradigm, we design a…
Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…
Learning effective joint representations has been a central task in multi-modal sentiment analysis. Previous works addressing this task focus on exploring sophisticated fusion techniques to enhance performance. However, the inherent…
Visual observations from different viewpoints can significantly influence the performance of visuomotor policies in robotic manipulation. Among these, egocentric (in-hand) views often provide crucial information for precise control.…