Related papers: PYVALE: A Fast, Scalable, Open-Source 2D Digital I…
The dynamic mode decomposition (DMD) is a simple and powerful data-driven modeling technique that is capable of revealing coherent spatiotemporal patterns from data. The method's linear algebra-based formulation additionally allows for a…
Contrastive pre-trained vision-language models, such as CLIP, demonstrate strong generalization abilities in zero-shot classification by leveraging embeddings extracted from image and text encoders. This paper aims to robustly fine-tune…
In application-specific designs, owing to the trade-off between power consumption and speed, optimization of various circuit parameters has become a challenging task. Several of the performance metrics, viz. energy efficiency, gain,…
In modern cloud and heterogeneous distributed infrastructures, container images are widely used as the deployment unit for machine learning applications. An image bundles the application with its entire platform-specific execution…
With the increased attention to memristive-based in-memory analog computing (IMAC) architectures as an alternative for energy-hungry computer systems for data-intensive applications, a tool that enables exploring their device- and…
Image matching aims at identifying corresponding points between a pair of images. Currently, detector-free methods have shown impressive performance in challenging scenarios, thanks to their capability of generating dense matches and global…
Advanced ultrasound computed tomography techniques like full-waveform inversion are mathematically challenging and orders of magnitude more computationally expensive than conventional ultrasound imaging methods. This computational and…
Hyperspectral images taken from aircraft or satellites contain information from hundreds of spectral bands, within which lie latent lower-dimensional structures that can be exploited for classifying vegetation and other materials. A…
The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption.…
Due to the high complexity and occlusion, insufficient perception in the crowded urban intersection can be a serious safety risk for both human drivers and autonomous algorithms, whereas CVIS (Cooperative Vehicle Infrastructure System) is a…
Visual quality inspection in automotive production is essential for ensuring the safety and reliability of vehicles. Computer vision (CV) has become a popular solution for these inspections due to its cost-effectiveness and reliability.…
Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and…
Given two images, we can estimate the relative camera pose between them by establishing image-to-image correspondences. Usually, correspondences are 2D-to-2D and the pose we estimate is defined only up to scale. Some applications, aiming at…
We present PyWiFeS, a new Python-based data reduction pipeline for the Wide Field Spectrograph (WiFeS). PyWiFeS consists of a series of core data processing routines built on standard scientific Python packages commonly used in astronomical…
The growth of large, programatically accessible bibliometrics databases presents new opportunities for complex analyses of publication metadata. In addition to providing a wealth of information about authors and institutions, databases such…
Existing unsupervised image alignment methods exhibit limited accuracy and high computational complexity. To address these challenges, we propose a dense cross-scale image alignment model. It takes into account the correlations between…
Bin picking in real industrial environments remains challenging due to severe clutter, occlusions, and the high cost of traditional 3D sensing setups. We present Pickalo, a modular 6D pose-based bin-picking pipeline built entirely on…
Analog compute-in-memory (CIM) in static random-access memory (SRAM) is promising for accelerating deep learning inference by circumventing the memory wall and exploiting ultra-efficient analog low-precision arithmetic. Latest analog CIM…
We introduce PyPulse, a Python package for imputation of biosignals in both clinical and wearable sensor settings. Missingness is commonplace in these settings and can arise from multiple causes, such as insecure sensor attachment or data…
Today, video cameras are deployed in dense for monitoring physical places e.g., city, industrial, or agricultural sites. In the current systems, each camera node sends its feed to a cloud server individually. However, this approach suffers…