Related papers: Rejoining fragmented ancient bamboo slips with phy…

Embedding graphs in continous spaces is a key factor in designing and developing algorithms for automatic information extraction to be applied in diverse tasks (e.g., learning, inferring, predicting). The reliability of graph embeddings…

Advances in computational pathology increasingly rely on extracting meaningful representations from Whole Slide Images (WSIs) to support various clinical and biological tasks. In this study, we propose a generalizable deep learning…

We are facing a real challenge when coping with the continuous acceleration of scientific production and the increasingly changing nature of science. In this article, we extend the classical framework of co-word analysis to the study of…

Backpropagation is widely used to train artificial neural networks, but its relationship to synaptic plasticity in the brain is unknown. Some biological models of backpropagation rely on feedback projections that are symmetric with…

The ability to visually re-identify objects is a fundamental capability in vision systems. Oftentimes, it relies on collections of visual signatures based on descriptors, such as SIFT or SURF. However, these traditional descriptors were…

Residual connections are one of the most important components in neural network architectures for mitigating the vanishing gradient problem and facilitating the training of much deeper networks. One possible explanation for how residual…

We introduce a model for bidirectional retrieval of images and sentences through a multi-modal embedding of visual and natural language data. Unlike previous models that directly map images or sentences into a common embedding space, our…

We present principled approaches to train and deploy dyadic neural embedding models at the billion scale, focusing our investigation on the application of semantic product search. When training a dyadic model, one seeks to embed two…

Multi-modal learning combines various modalities to provide a comprehensive understanding of real-world problems. A common strategy is to directly bind different modalities together in a specific joint embedding space. However, the…

Volumetric depth map fusion based on truncated signed distance functions has become a standard method and is used in many 3D reconstruction pipelines. In this paper, we are generalizing this classic method in multiple ways: 1) Semantics:…

Improving the automatic and timely recognition of construction and demolition waste composition is crucial for enhancing business returns, economic outcomes and sustainability. While deep learning models show promise in recognizing and…

Accurate and robust disassembly of stripped binaries is challenging. The root of the difficulty is that high-level structures, such as instruction and function boundaries, are absent in stripped binaries and must be recovered based on…

Deep Research agents predominantly optimize search policies to maximize retrieval probability. However, we identify a critical bottleneck: the retrieval-utilization gap, where models fail to use gold evidence even after it is retrieved, due…

This study introduces a physics-based machine learning framework for modeling both brittle and ductile fractures. Unlike physics-informed neural networks, which solve partial differential equations by embedding physical laws as soft…

In recent years, deep learning has made significant progress in wood panel defect detection. However, there are still challenges such as low detection , slow detection speed, and difficulties in deploying embedded devices on wood panel…

With the increasing use of plastic, the challenges associated with managing plastic waste have become more challenging, emphasizing the need of effective solutions for classification and recycling. This study explores the potential of deep…

Medical images used in clinical practice are heterogeneous and not the same quality as scans studied in academic research. Preprocessing breaks down in extreme cases when anatomy, artifacts, or imaging parameters are unusual or protocols…

The inapplicability of amino acid covariation methods to small protein families has limited their use for structural annotation of whole genomes. Recently, deep learning has shown promise in allowing accurate residue-residue contact…

In terms of 3D imaging speed and system cost, the single-camera system projecting single-frequency patterns is the ideal option among all proposed Fringe Projection Profilometry (FPP) systems. This system necessitates a robust spatial phase…

In this paper, we develop a deep learning approach for the accurate solution of challenging problems of near-field microscopy that leverages the powerful framework of physics-informed neural networks (PINNs) for the inversion of the complex…