Related papers: MMRDN: Consistent Representation for Multi-View Ma…
The drone navigation requires the comprehensive understanding of both visual and geometric information in the 3D world. In this paper, we present a Visual-Geometric Fusion Network(VGF-Net), a deep network for the fusion analysis of…
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…
Small object detection is challenging because small objects do not contain detailed information and may even disappear in the deep network. Usually, feeding high-resolution images into a network can alleviate this issue. However, simply…
Deep learning based fusion methods have been achieving promising performance in image fusion tasks. This is attributed to the network architecture that plays a very important role in the fusion process. However, in general, it is hard to…
Robust 3D object detection in extreme weather and illumination conditions is a challenging task. While radars and thermal cameras are known for their resilience to these conditions, few studies have been conducted on radar-thermal fusion…
Multiview network embedding aims at projecting nodes in the network to low-dimensional vectors, while preserving their multiple relations and attribute information. Contrastive learning approaches have shown promising performance in this…
Robotic grasping is facing a variety of real-world uncertainties caused by non-static object states, unknown object properties, and cluttered object arrangements. The difficulty of grasping increases with the presence of more uncertainties,…
Predicting smartphone users activity using WiFi fingerprints has been a popular approach for indoor positioning in recent years. However, such a high dimensional time-series prediction problem can be very tricky to solve. To address this…
Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input. However, in real applications, a complete and correct past motion sequence can be too expensive to achieve. In this…
We present Manifold Alignment Determination (MAD), an algorithm for learning alignments between data points from multiple views or modalities. The approach is capable of learning correspondences between views as well as correspondences…
Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to…
Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each…
Despite encouraging progress in 3D scene understanding, it remains challenging to develop an effective Large Multi-modal Model (LMM) that is capable of understanding and reasoning in complex 3D environments. Most previous methods typically…
Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for context encoding or rely on pre-defined scene templates for…
Deep learning based medical image segmentation models usually require large datasets with high-quality dense segmentations to train, which are very time-consuming and expensive to prepare. One way to tackle this challenge is by using the…
Generating high-quality novel view renderings of 3D Gaussian Splatting (3DGS) in scenes featuring transient objects is challenging. We propose a novel hybrid representation, termed as HybridGS, using 2D Gaussians for transient objects per…
Autonomous systems not only need to understand their current environment, but should also be able to predict future actions conditioned on past states, for instance based on captured camera frames. However, existing models mainly focus on…
Goal-conditioned rearrangement of deformable objects (e.g. straightening a rope and folding a cloth) is one of the most common deformable manipulation tasks, where the robot needs to rearrange a deformable object into a prescribed goal…
Collective behaviors that emerge from interactions are fundamental to numerous biological systems. To learn such interacting forces from observations, we introduce a measure-valued neural network that infers measure-dependent interaction…
Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome…