Related papers: Chip-level CMP Modeling and Smart Dummy for HDP an…
In this work, we investigate Vacuum-Packed Particle (VPP) dampers -- granular-core dampers offering tunable damping performance -- as a more sustainable alternative to conventional systems such as magnetorheological fluid dampers. A…
Deep learning algorithms have recently gained significant attention due to their impressive performance. However, their high complexity and un-interpretable mode of operation hinders their confident deployment in real-world safety-critical…
Differentiating signals from the background in micrographs is a critical initial step for cryogenic electron microscopy (cryo-EM), yet it remains laborious due to low signal-to-noise ratio (SNR), the presence of contaminants and densely…
Image compression is one of the most fundamental techniques and commonly used applications in the image and video processing field. Earlier methods built a well-designed pipeline, and efforts were made to improve all modules of the pipeline…
We present a novel method to track 3D models in color and depth data. To this end, we introduce approximations that accelerate the state-of-the-art in region-based tracking by an order of magnitude while retaining similar accuracy.…
We introduce CUPS, a novel method for learning sequence-to-sequence 3D human shapes and poses from RGB videos with uncertainty quantification. To improve on top of prior work, we develop a method to generate and score multiple hypotheses…
This paper proposes probabilistic conformal prediction (PCP), a predictive inference algorithm that estimates a target variable by a discontinuous predictive set. Given inputs, PCP construct the predictive set based on random samples from…
Crack-templated networks, metallic frameworks fabricated from crack patterns in sacrificial thin films, can exhibit high optical transmittance, high electric conductivity, and a host of other properties attractive for applications. Despite…
Motivated by the desire to exploit patterns shared across classes, we present a simple yet effective class-specific memory module for fine-grained feature learning. The memory module stores the prototypical feature representation for each…
To fully exploit the increased luminosity of the HL-LHC, the CMS Inner Tracker is undergoing a major upgrade to withstand extreme radiation levels and data rates, while improving granularity and reducing material budget. The upgraded…
Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes. Existing deep learning systems focus on optimizing and executing static neural networks which assume a…
The modeling of superconducting magnetic bearing (SMB) is of great significance for predicting and optimizing its levitation performance before construction. Although lots of efforts have been made in this area, it still remains some space…
The Digital Correlated Double Sampling (DCDS) is a technique based on multiple analog-to-digital conversions of every pixel when reading a CCD out. This technique allows to remove analog integrators, simplifying the readout electronics…
We propose an experimental approach, by which thin films of copper polyphthalocyanine (CuPPC) can be directly synthesized in a chemical vapor deposition (CVD) set-up at mild temperature (420 {\deg}C). High polymerization degree and high…
Deep Neural Networks (DNNs) have shown excellent performance in a wide range of machine learning applications. Knowing the latency of running a DNN model or tensor program on a specific device is useful in various tasks, such as DNN graph-…
Continual learning aims to update a model so that it can sequentially learn new tasks without forgetting previously acquired knowledge. Recent continual learning approaches often leverage the vision-language model CLIP for its…
Dense image alignment from RGB-D images remains a critical issue for real-world applications, especially under challenging lighting conditions and in a wide baseline setting. In this paper, we propose a new framework to learn a pixel-wise…
Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. The most popular CNN-based methods are optimised using pixel wise loss…
Contrastive Language-Image Pre-training (CLIP) has attracted a surge of attention for its superior zero-shot performance and excellent transferability to downstream tasks. However, training such large-scale models usually requires…
This paper investigates the application of unsupervised learning methods for computed tomography (CT) reconstruction. To motivate our work, we review several existing priors, namely the truncated Gaussian prior, the $l_1$ prior, the total…