Related papers: Ray-Patch: An Efficient Querying for Light Field T…
Solving multiple visual tasks using individual models can be resource-intensive, while multi-task learning can conserve resources by sharing knowledge across different tasks. Despite the benefits of multi-task learning, such techniques can…
We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression…
While general object detection with deep learning has achieved great success in the past few years, the performance and efficiency of detecting small objects are far from satisfactory. The most common and effective way to promote small…
Current approaches for segmenting ultra high resolution images either slide a window, thereby discarding global context, or downsample and lose fine detail. We propose a simple yet effective method that brings explicit multi scale reasoning…
In this thesis, we propose a pioneering work on sparse keypoints tracking across images using transformer networks. While deep learning-based keypoints matching have been widely investigated using graph neural networks - and more recently…
Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having…
As RDF becomes more widely established and the amount of linked data is rapidly increasing, the efficient querying of large amount of data becomes a significant challenge. In this paper, we propose a family of algorithms for querying large…
Transformers have demonstrated tremendous success not only in the natural language processing (NLP) domain but also the field of computer vision, igniting various creative approaches and applications. Yet, the superior performance and…
To enhance precision and comprehensiveness in identifying targets in electric power construction monitoring video, a novel target recognition algorithm utilizing infrared imaging is explored. This algorithm employs a color processing…
Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…
Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction…
Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…
A point-spread function describes the optics of an imaging system and can be used to correct collected images for instrumental effects. The state of the art for deconvolving images with the point-spread function is the Richardson-Lucy…
The high computational expense of simulating light through ray-tracing in large, sparsely instrumented particle detectors such as IceCube and Antares is a critical outstanding problem in particle physics. When the detector is sparsely…
Vision Transformers are at the heart of the current surge of interest in foundation models for histopathology. They process images by breaking them into smaller patches following a regular grid, regardless of their content. Yet, not all…
We present PARQ - a multi-view 3D object detector with transformer and pixel-aligned recurrent queries. Unlike previous works that use learnable features or only encode 3D point positions as queries in the decoder, PARQ leverages…
We present a novel method for efficiently producing semi-dense matches across images. Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios but suffers…
We present a new effective way for performance capture of deforming meshes with fine-scale time-varying surface detail from multi-view video. Our method builds up on coarse 4D surface reconstructions, as obtained with commonly used…
The recent advances in query-based multi-camera 3D object detection are featured by initializing object queries in the 3D space, and then sampling features from perspective-view images to perform multi-round query refinement. In such a…
Given a query graph that represents a pattern of interest, the emerging pattern detection problem can be viewed as a continuous query problem on a dynamic graph. We present an incremental algorithm for continuous query processing on dynamic…