Related papers: Structural Resolution with Co-inductive Loop Detec…
This work addresses the task of open world semantic segmentation using RGBD sensing to discover new semantic classes over time. Although there are many types of objects in the real-word, current semantic segmentation methods make a closed…
Many real-world applications are associated with structured data, where not only input but also output has interplay. However, typical classification and regression models often lack the ability of simultaneously exploring high-order…
Super-resolution theory aims to estimate the discrete components lying in a continuous space that constitute a sparse signal with optimal precision. This work investigates the potential of recent super-resolution techniques for spectral…
To precisely measure and evaluate X-ray generation and evolution in a hohlraum during an implosion process, we present a two-dimensional (2D) time- and space-resolved diagnostic method by combining a compressed ultrafast photography (CUP)…
Single image super-resolution (SISR) is a very popular topic nowadays, which has both research value and practical value. In daily life, we crop a large image into sub-images to do super-resolution and then merge them together. Although…
Interactive development environments like Jupyter Notebooks enable incremental coding through cells with immediate feedback, but their linear structure and global namespace limit scalability for large software projects. We present CodePod,…
RSDs (Resistive AC-Coupled Silicon Detectors) are n-in-p silicon sensors based on the LGAD (Low-Gain Avalanche Diode) technology, featuring a continuous gain layer over the whole sensor area. The truly innovative feature of these sensors is…
Concurrent Speaker Detection (CSD), the task of identifying active speakers and their overlaps in an audio signal, is essential for various audio applications, including meeting transcription, speaker diarization, and speech separation.…
Simultaneous localization and mapping (SLAM) is a fundamental capability required by most autonomous systems. In this paper, we address the problem of loop closing for SLAM based on 3D laser scans recorded by autonomous cars. Our approach…
We exploit (co)inductive specifications and proofs to approach the evaluation of low-level programs for the Unlimited Register Machine (URM) within the Coq system, a proof assistant based on the Calculus of (Co)Inductive Constructions type…
Supervised classification and representation learning are two widely used classes of methods to analyze multivariate images. Although complementary, these methods have been scarcely considered jointly in a hierarchical modeling. In this…
Improving the interpretability of deep neural networks has recently gained increased attention, especially when the power of deep learning is leveraged to solve problems in physics. Interpretability helps us understand a model's ability to…
Retrieval-Augmented Language Models (RALMs) face significant challenges in reducing factual errors, particularly in document relevance evaluation and knowledge integration. We introduce a framework for structured relevance assessment that…
In this paper we propose a vision system that performs image Super Resolution (SR) with selectivity. Conventional SR techniques, either by multi-image fusion or example-based construction, have failed to capitalize on the intrinsic…
This paper proposes a super-resolution harmonic retrieval method for uncorrelated strictly non-circular signals, whose covariance and pseudo-covariance present Toeplitz and Hankel structures, respectively. Accordingly, the augmented…
Real-time scene reconstruction from depth data inevitably suffers from occlusion, thus leading to incomplete 3D models. Partial reconstructions, in turn, limit the performance of algorithms that leverage them for applications in the context…
Relating entities and events in text is a key component of natural language understanding. Cross-document coreference resolution, in particular, is important for the growing interest in multi-document analysis tasks. In this work we propose…
Word embeddings induced from local context are prevalent in NLP. A simple and effective context-based multilingual embedding learner is Levy et al. (2017)'s S-ID (sentence ID) method. Another line of work induces high-performing…
Besides standard cameras, autonomous vehicles typically include multiple additional sensors, such as lidars and radars, which help acquire richer information for perceiving the content of the driving scene. While several recent works focus…
Robust efficient loop closure detection is essential for large-scale real-time SLAM. In this paper, we propose a novel unsupervised deep neural network architecture of a feature embedding for visual loop closure that is both reliable and…