Related papers: CAGE: Continuity-Aware edGE Network Unlocks Robust…
Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part…
The Kolmogorov-Arnold Network (KAN) has recently gained attention as an alternative to traditional multi-layer perceptrons (MLPs), offering improved accuracy and interpretability by employing learnable activation functions on edges. In this…
Country-level temporal panels are widely used in empirical analysis. Researchers often need to audit how different entities respond to historical signals over different time horizons. Current approaches typically do not provide directly…
We present UniPlane, a novel method that unifies plane detection and reconstruction from posed monocular videos. Unlike existing methods that detect planes from local observations and associate them across the video for the final…
Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences. However, spatial and temporal cues are often unreliable in real-world…
In this paper, we introduce a deep learning solution for video activity recognition that leverages an innovative combination of convolutional layers with a linear-complexity attention mechanism. Moreover, we introduce a novel quantization…
Recognition of floor plans has been a challenging and popular task. Despite that many recent approaches have been proposed for this task, they typically fail to make the room-level unified prediction. Specifically, multiple semantic…
We introduce the Cooperative Network Architecture (CNA), a model that represents sensory signals using structured, recurrently connected networks of neurons, termed "nets." Nets are dynamically assembled from overlapping net fragments,…
Volume-based indoor scene reconstruction methods offer superior generalization capability and real-time deployment potential. However, existing methods rely on multi-view pixel back-projection ray intersections as weak geometric constraints…
Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications. The most cutting-edge methods are attentional encoder-decoder frameworks that learn the alignment…
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the…
In this paper, a new data-driven multiscale material modeling method, which we refer to as deep material network, is developed based on mechanistic homogenization theory of representative volume element (RVE) and advanced machine learning…
Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainable deep network, (CDeC-Net) for detecting tables present in…
Network alignment, the process of finding correspondences between nodes in different graphs, has many scientific and industrial applications. Existing unsupervised network alignment methods find suboptimal alignments that break up node…
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access broader knowledge sources, yet factual inconsistencies persist due to noise in retrieved documents-even with advanced retrieval methods. We demonstrate that…
Ultra-high-definition (UHD) image restoration often faces computational bottlenecks and information loss due to its extremely high resolution. Existing studies based on Variational Autoencoders (VAE) improve efficiency by transferring the…
Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'.…
Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…
Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that…
Machine learning applications require fast and reliable per-sample uncertainty estimation. A common approach is to use predictive distributions from Bayesian or approximation methods and additively decompose uncertainty into aleatoric…