Related papers: A Connected Component Labelling algorithm for mult…

The Insertable B-layer (IBL) is a fourth pixel layer that will be added inside the existing ATLAS pixel detector during the long LHC shutdown of 2013 and 2014. The new four layer pixel system will ensure excellent tracking, vertexing and…

We present SemiOccam, an image recognition network that leverages semi-supervised learning in a highly efficient manner. Existing works often rely on complex training techniques and architectures, requiring hundreds of GPU hours for…

This paper proposes a method of transferring physical continuous and switching/converter circuits working in continuous conduction mode (CCM) and discontinuous conduction mode (DCM) to graph representation, independent of the connection or…

Contrastive learning and self-supervised techniques have gained prevalence in computer vision for the past few years. It is essential for medical image analysis, which is often notorious for its lack of annotations. Most existing…

Thin planar pixel modules are promising candidates to instrument the inner layers of the new ATLAS pixel detector for HL-LHC, thanks to the reduced contribution to the material budget and their high charge collection efficiency after…

With the development of high-definition display devices, the practical scenario of Super-Resolution (SR) usually needs to super-resolve large input like 2K to higher resolution (4K/8K). To reduce the computational and memory cost, current…

Semantic Segmentation is an important module for autonomous robots such as self-driving cars. The advantage of video segmentation approaches compared to single image segmentation is that temporal image information is considered, and their…

Integrated optical transceivers, utilizing wavelength-division-multiplexing, offer a path forward for implementation of compact, high-bandwidth and energy-efficient interconnects for future data centers. Here we report the demonstration of…

Semantic segmentation, like other fields of computer vision, has seen a remarkable performance advance by the use of deep convolution neural networks. However, considering that neighboring pixels are heavily dependent on each other, both…

It has been a longstanding goal within image captioning to move beyond a dependence on object detection. We investigate using superpixels coupled with Vision Language Models (VLMs) to bridge the gap between detector-based captioning…

Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling…

The recent upgrade of the LHCb experiment pushes data processing rates up to 40 Tbit/s. Out of the whole reconstruction sequence, one of the most time consuming algorithms is the calorimeter reconstruction. It aims at performing a…

We present a scalable in-pixel processing architecture that can reduce the data throughput by 10X and consume less than 30 mW per megapixel at the imager frontend. Unlike the state-of-the-art (SOA) analog process-in-pixel (PIP) that…

Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…

High-speed signal processing is essential for maximizing data throughput in emerging communication applications, like multiple-input multiple-output (MIMO) systems and radio-frequency (RF) interference cancellation. However, as these…

Continual Learning (CL) is the process of learning ceaselessly a sequence of tasks. Most existing CL methods deal with independent data (e.g., images and text) for which many benchmark frameworks and results under standard experimental…

The ATLAS collaboration will replace its tracking detector with new all silicon pixel and strip systems. This will allow to cope with the higher radiation and occupancy levels expected after the 5-fold increase in the luminosity of the LHC…

After the Large Hadron Collider (LHC) upgrade into High Luminosity LHC (HL-LHC), the instantaneous luminosity is expected to reach values up to 7.5x10^34cm^2/s, causing a harsher radiation environment as well as a significant increase in…

Millimeter-scale embedded sensing systems have unique advantages over larger devices as they are able to capture, analyze, store, and transmit data at the source while being unobtrusive and covert. However, area-constrained systems pose…

High-throughput synthesis of solution-processable structurally variable small-molecule semiconductors is both an opportunity and a challenge. A large number of diverse molecules provide a possibility for quick material discovery and machine…