Related papers: EDSL: An Encoder-Decoder Architecture with Symbol-…

Dense prediction infers per-pixel values from a single image and is fundamental to 3D perception and robotics. Although real-world scenes exhibit strong structure, existing methods treat it as an independent pixel-wise prediction, often…

Symbolic Regression (SR) is a type of regression analysis to automatically find the mathematical expression that best fits the data. Currently, SR still basically relies on various searching strategies so that a sample-specific model is…

Symbolic regression seeks to uncover physical laws from experimental data by searching for closed-form expressions, which is an important task in AI-driven scientific discovery. Yet the exponential growth of the search space of expression…

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with…

Implicit neural representations (INRs) are increasingly being used as tools to map coordinates to signals, encompassing applications from neural fields to texture compression, shape representations, and beyond. Most INR methods are based on…

Micro expression recognition (MER) is a very challenging area of research due to its intrinsic nature and fine-grained changes. In the literature, the problem of MER has been solved through handcrafted/descriptor-based techniques. However,…

Aberration-corrected environmental transmission electron microscopy (ETEM) enables atomic-resolution imaging of dynamic catalytic processes. Correlating atomic-scale structural changes with reaction products detected by mass spectrometry…

Electronic structure simulation (ESS) has been used for decades to provide quantitative scientific insights on an atomistic scale, enabling advances in chemistry, biology, and materials science, among other disciplines. Following standard…

Semantic segmentation requires per-pixel prediction for a given image. Typically, the output resolution of a segmentation network is severely reduced due to the downsampling operations in the CNN backbone. Most previous methods employ…

Design patterns (DPs) are recognised as a good practice in software development. However, the lack of appropriate documentation often hampers traceability, and their benefits are blurred among thousands of lines of code. Automatic methods…

The segmentation and interpretation of the Martian surface play a pivotal role in Mars exploration, providing essential data for the trajectory planning and obstacle avoidance of rovers. However, the complex topography, similar surface…

Fine-tuning Pre-trained protein language models (PLMs) has emerged as a prominent strategy for enhancing downstream prediction tasks, often outperforming traditional supervised learning approaches. As a widely applied powerful technique in…

Deep learning has significantly advanced image edge detection (ED), primarily through improved feature extraction. However, most existing ED models apply uniform feature fusion across all pixels, ignoring critical differences between…

Recent studies on semi-supervised learning (SSL) have achieved great success. Despite their promising performance, current state-of-the-art methods tend toward increasingly complex designs at the cost of introducing more network components…

Code retrieval aims to provide users with desired code snippets based on users' natural language queries. With the development of deep learning technologies, adopting pre-trained models for this task has become mainstream. Considering the…

High-resolution segmentation is critical for precise disease diagnosis by extracting fine-grained morphological details. Existing hierarchical encoder-decoder frameworks have demonstrated remarkable adaptability across diverse medical…

One-shot medical image segmentation (MIS) is crucial for medical analysis due to the burden of medical experts on manual annotation. The recent emergence of the segment anything model (SAM) has demonstrated remarkable adaptation in MIS but…

Change detection is a critical task in earth observation applications. Recently, deep learning-based methods have shown promising performance and are quickly adopted in change detection. However, the widely used multiple encoder and single…

Handwritten Mathematical Expression Recognition (HMER) has extensive applications in automated grading and office automation. However, existing sequence-based decoding methods, which directly predict $\LaTeX$ sequences, struggle to…

We study the 3D object understanding task for manipulating everyday objects with different material properties (diffuse, specular, transparent and mixed). Existing monocular and RGB-D methods suffer from scale ambiguity due to missing or…