Related papers: The new object oriented analysis framework for H1
Vision Transformers (ViTs) have been widely adopted in vision tasks due to their strong transferability. In Federated Learning (FL), where full fine-tuning is communication heavy, Low-Rank Adaptation (LoRA) provides an efficient and…
Performance analysis in process mining aims to provide insights on the performance of a business process by using a process model as a formal representation of the process. Such insights are reliably interpreted by process analysts in the…
High statistics measurements of the diffractive reduced cross section $\sigma_r^D$ from the H1 collaboration are presented which make use of two different experimental methods to achieve the largest possible coverage of the kinematic phase…
Given the rapid improvement of the detectors at high-energy physics experiments, the need for real-time data monitoring systems has become imperative. The significance of these systems lies in their ability to display experiment status,…
A selection of results from the H1 and ZEUS experiments at HERA are reviewed, particularly in the area of deep inelastic scattering and diffraction. Quantum chromodynamics gives a good explanation of these data down to surprisingly low…
When multiple objects are involved in a process, there is an opportunity for processes to be discovered from different angles with new information that previously might not have been analyzed from a single object point of view. This does…
The objective of this research is to optimize the eleventh iteration of You Only Look Once (YOLOv11) by developing size-specific modified versions of the architecture. These modifications involve pruning unnecessary layers and reconfiguring…
Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets. Despite the challenges posed by…
Despite large neural networks demonstrating remarkable abilities to complete different tasks, they require excessive memory usage to store the optimization states for training. To alleviate this, the low-rank adaptation (LoRA) is proposed…
More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…
Federated learning systems have been identified as an efficient approach to scaling distributed model training with a large amount of participants or data owners while guaranteeing data privacy. To apply the current most popular pre-trained…
Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tuning (PEFT) method, offers an efficient solution by optimizing…
Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples. The mechanism of the human visual system is to interpret spatial relationships…
As particle physics experiments push their limits on both the energy and the intensity frontiers, the amount and complexity of the produced data are also expected to increase accordingly. With such large data volumes, next-generation…
The HORACE suite of programs has been developed to work with large multiple-measurement data sets collected from time-of-flight neutron spectrometers equipped with arrays of position-sensitive detectors. The software allows exploratory…
In most modern object detection pipelines, the detection proposals are processed independently given the feature map. Therefore, they overlook the underlying relationships between objects and the surrounding background, which could have…
Recent data obtained in ep collisions at HERA by the H1 collaboration are presented: searches for new phenomena beyond the Standard Model, measurement of the inclusive neutral and charged current cross sections and of the proton structure…
This paper presents a dataset, called Reeds, for research on robot perception algorithms. The dataset aims to provide demanding benchmark opportunities for algorithms, rather than providing an environment for testing application-specific…
In the context of the tremendous progress achieved at HERA in diffraction and the need for a new level of statistical and systematic precision, the new very large acceptance forward spectrometer planned by H1 (VFPS) is presented and the…
Existing transformer-based image backbones typically propagate feature information in one direction from lower to higher-levels. This may not be ideal since the localization ability to delineate accurate object boundaries, is most prominent…