Related papers: GenCape: Structure-Inductive Generative Modeling f…

Enterprise relational databases increasingly contain vast amounts of non-semantic data - IP addresses, product identifiers, encoded keys, and timestamps - that challenge traditional semantic analysis. This paper introduces a novel…

This paper studies the problem of multi-person pose estimation in a bottom-up fashion. With a new and strong observation that the localization issue of the center-offset formulation can be remedied in a local-window search scheme in an…

The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity. Current CNN-Transformer hybrids use static…

Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles incompatible…

In human-computer interaction, head pose estimation profoundly influences application functionality. Although utilizing facial landmarks is valuable for this purpose, existing landmark-based methods prioritize precision over simplicity and…

Convolutional neural network (CNN) models for computer vision are powerful but lack explainability in their most basic form. This deficiency remains a key challenge when applying CNNs in important domains. Recent work on explanations…

Establishing dense correspondence between two images is a fundamental computer vision problem, which is typically tackled by matching local feature descriptors. However, without global awareness, such local features are often insufficient…

Deep research agents integrate fragmented evidence through multi-step tool use. BrowseComp offers a text-only testbed for such agents, but existing multimodal benchmarks rarely require both weak visual cues composition and BrowseComp-style…

Positional encoding is a vital component of Transformer architectures, enabling models to incorporate sequence order into self-attention mechanisms. Rotary Positional Embeddings (RoPE) have become a widely adopted solution due to their…

Image generation tasks are traditionally undertaken using Convolutional Neural Networks (CNN) or Transformer architectures for feature aggregating and dispatching. Despite the frequent application of convolution and attention structures,…

Textual Attribute Graphs (TAGs) are critical for modeling complex networks like citation networks, but effective node classification remains challenging due to difficulties in integrating rich semantics from text with structural graph…

In this paper, we focus on unsupervised representation learning for skeleton-based action recognition. Existing approaches usually learn action representations by sequential prediction but they suffer from the inability to fully learn…

Suboptimal generalization of machine learning models on unseen data is a key challenge which hampers the clinical applicability of such models to medical imaging. Although various methods such as domain adaptation and domain generalization…

Attention has long been proposed by psychologists as important for effectively dealing with the enormous sensory stimulus available in the neocortex. Inspired by the visual attention models in computational neuroscience and the need of…

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels…

With the rapid development of autonomous driving and extended reality, efficient transmission of point clouds (PCs) has become increasingly important. In this context, we propose a novel channel-adaptive cross-modal generative semantic…

Recent research on learned visual descriptors has shown promising improvements in correspondence estimation, a key component of many 3D vision tasks. However, existing descriptor learning frameworks typically require ground-truth…

Learning a generalized prior for natural image restoration is an important yet challenging task. Early methods mostly involved handcrafted priors including normalized sparsity, l_0 gradients, dark channel priors, etc. Recently, deep neural…

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime. However, these features often lack the spatial resolution to…

Few-shot image classification remains difficult under limited supervision and visual domain shift. Recent cache-based adaptation approaches (e.g., Tip-Adapter) address this challenge to some extent by learning lightweight residual adapters…