相关论文: HiT: Building Mapping with Hierarchical Transforme…

It is always well believed that parsing an image into constituent visual patterns would be helpful for understanding and representing an image. Nevertheless, there has not been evidence in support of the idea on describing an image with a…

This work describes algorithms for performing discrete object detection, specifically in the case of buildings, where usually only low quality RGB-only geospatial reflective imagery is available. We utilize new candidate search and feature…

Accurate geometry representation is essential in developing finite element models. Although generally good, deep-learning segmentation approaches with only few data have difficulties in accurately segmenting fine features, e.g., gaps and…

This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly in a network.…

Label hierarchies widely exist in many vision-related problems, ranging from explicit label hierarchies existed in image classification to latent label hierarchies existed in semantic segmentation. Nevertheless, state-of-the-art methods…

Embedding visual representations within original hierarchical tables can mitigate additional cognitive load stemming from the division of users' attention. The created hierarchical table visualizations can help users understand and explore…

General object detectors use powerful backbones that uniformly extract features from images for enabling detection of a vast amount of object types. However, utilization of such backbones in object detection applications developed for…

One of the crucial challenges taken in document analysis is mathematical expression recognition. Unlike text recognition which only focuses on one-dimensional structure images, mathematical expression recognition is a much more complicated…

Time series forecasting is a critical and challenging task in practical application. Recent advancements in pre-trained foundation models for time series forecasting have gained significant interest. However, current methods often overlook…

In this paper, we present a novel method called PolyTrack for fast multi-object tracking and segmentation using bounding polygons. Polytrack detects objects by producing heatmaps of their center keypoint. For each of them, a rough…

Constructing a high-quality dense map in real-time is essential for robotics, AR/VR, and digital twins applications. As Neural Radiance Field (NeRF) greatly improves the mapping performance, in this paper, we propose a NeRF-based mapping…

We propose Beat Transformer, a novel Transformer encoder architecture for joint beat and downbeat tracking. Different from previous models that track beats solely based on the spectrogram of an audio mixture, our model deals with demixed…

Effectively measuring the similarity between two human motions is necessary for several computer vision tasks such as gait analysis, person identi- fication and action retrieval. Nevertheless, we believe that traditional approaches such as…

Single Image Reflection Removal (SIRR) technique plays a crucial role in image processing by eliminating unwanted reflections from the background. These reflections, often caused by photographs taken through glass surfaces, can…

In remote sensing there exists a common need for learning scale invariant shapes of objects like buildings. Prior works relies on tweaking multiple loss functions to convert segmentation maps into the final scale invariant representation,…

The representation of urban trajectory data plays a critical role in effectively analyzing spatial movement patterns. Despite considerable progress, the challenge of designing trajectory representations that can capture diverse and…

Complex tables with multi-level headers, merged cells and heterogeneous layouts pose persistent challenges for LLMs in both understanding and reasoning. Existing approaches typically rely on table linearization or normalized grid modeling.…

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained…

The remarkable performance of large multimodal models (LMMs) has attracted significant interest from the image segmentation community. To align with the next-token-prediction paradigm, current LMM-driven segmentation methods either use…

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…