This high-speed and power-efficient content addressable memory employs parallel lookups to expedite matching without compromising power consumption. It introduces three significant innovations: i. pre-computation based operation, which enhances search speed by eliminating mismatch conditions only in 4-bit comparisons; ii. a hybrid match line structure that strategically balances power and delay, amalgamating the high-speed attributes of NOR with the low-power characteristics of NAND; and iii. a control technique that processes segments to the final match line. Performance metrics exhibit significant enhancements when these methodologies are seamlessly integrated. Employing 45 nm CMOS technology, the design accommodates diverse process voltages, temperatures, and frequencies for a$64\times 32$memory array. Monte Carlo simulations validate design stability. The proposed architecture surpasses the leading benchmark in speed and power-delay-product by 62.85% and 99.78%, respectively. The proposed architecture supports repeated data searches at frequencies up to 2 GHz, which has the potential to revolutionize search in high-performance computing, mobile devices, and IoT applications.

We conducted a large-scale subjective study of the perceptual quality of User-Generated Mobile Video Content on a set of mobile-originated videos obtained from the Indian social media platform ShareChat. The content viewed by volunteer human subjects under controlled laboratory conditions has the benefit of culturally diversifying the existing corpus of User-Generated Content (UGC) video quality datasets. There is a great need for large and diverse UGC-VQA datasets, given the explosive global growth of the visual internet and social media platforms. This is particularly true in regard to videos obtained by smartphones, especially in rapidly emerging economies like India. ShareChat provides a safe and cultural community oriented space for users to generate and share content in their preferred Indian languages and dialects. Our subjective quality study, which is based on this data, supplies much needed cultural, visual, and language diversification to the overall shareable corpus of video quality data. We expect that this new data resource will also allow for the development of systems that can predict the perceived visual quality of Indian social media videos, and in this context, control scaling and compression protocols for streaming, provide better user recommendations, and guide content analysis and processing. We demonstrate the value of the new data resource by conducting a study of leading blind video quality models on it, including a simple new model, called MoEVA, which deploys a mixture of experts to predict video quality. Both the new LIVE-ShareChat Database and sample source code for MoEVA are being made freely available to the research community at https://github.com/sandeep-sm/LIVE-SC.

3D generation guided by text-to-image diffusion models enables the creation of visually compelling assets. However previous methods explore generation based on image or text. The boundaries of creativity are limited by what can be expressed through words or the images that can be sourced. We present YouDream, a method to generate high-quality anatomically controllable animals. YouDream is guided using a text-to-image diffusion model controlled by 2D views of a 3D pose prior. Our method is capable of generating novel imaginary animals that previous text-to-3D generative methods are unable to create. Additionally, our method can preserve anatomic consistency in the generated animals, an area where prior approaches often struggle. Moreover, we design a fully automated pipeline for generating commonly observed animals. To circumvent the need for human intervention to create a 3D pose, we propose a multi-agent LLM that adapts poses from a limited library of animal 3D poses to represent the desired animal. A user study conducted on the outcomes of YouDream demonstrates the preference of the animal models generated by our method over others. Visualizations and code are available at https://youdream3d.github.io/.

Automatic Perceptual Image Quality Assessment is a challenging problem that impacts billions of internet, and social media users daily. To advance research in this field, we propose a Mixture of Experts approach to train two separate encoders to learn high-level content and low-level image quality features in an unsupervised setting. The unique novelty of our approach is its ability to generate low-level representations of image quality that are complementary to high-level features representing image content. We refer to the framework used to train the two encoders as Re-IQA. For Image Quality Assessment in the Wild, we deploy the complementary low and high-level image representations obtained from the Re-IQA framework to train a linear regression model, which is used to map the image representations to the ground truth quality scores, refer Figure 1. Our method achieves state-of-the-art performance on multiple large-scale image quality assessment databases containing both real and synthetic distortions, demonstrating how deep neural networks can be trained in an unsupervised setting to produce perceptually relevant representations. We conclude from our experiments that the low and high-level features obtained are indeed complementary and positively impact the performance of the linear regressor. A public release of all the codes associated with this work will be made available on GitHub.

Detecting moving targets in synthetic aperture radar (SAR) imagery has recently gained a lot of interest as a way to augment optical moving target detection and classification in adverse (e.g., cloudy) weather conditions. In this paper, we primarily focus on the problem of detecting and imaging moving targets in single-channel (or summed multichannel) SAR data. Single-channel-based methods provide the ability to do detection well below the normal minimum detectable velocity (MDV) of multichannel-based GMTI. This can be particularly important for small radar antennas, which tend to have high conventional GMTI MDV. We also show results for multiple channel geolocation after single-channel detection and imaging. The algorithms consist of the following steps. We first suppress the stationary scene by comparing noncoherent time-subimages. We then detect the movers by applying a set of possible motion corrections to the image and use a novel matched filter to detect the movers in this space. We can then image the moving targets using standard SAR focusing techniques and geolocate the movers using multichannel (if available) along-track interferometry. We demonstrate and evaluate our algorithms using data collected from the Lincoln Multimission ISR Testbed airborne radar system.

Content-addressable memory (CAM) is a hardware searchengine used for parallel lookup that assures high-speed match but at the cost of higher power consumption. Both low power NAND-type and highspeed NOR-type match-line (ML) schemes suffer from requirement of the precharge prior to the search. Recently, a precharge-free ML structure has been proposed but with inadequate search performance. In this brief, a self-controlled precharge-free CAM (SCPF-CAM) structure is proposed for high-speed applications. The proposed architecture is useful in applications where search time is very crucial to design larger word lengths. The proposed 128×32-bit SCPF-CAM structure has been implemented using predictive 45-nm CMOS process and simulated in SPECTRE at the supply voltage of 1 V. The ML delay using the proposed SCPF-CAM architecture has been reduced by 88% and 73% compared to the precharge-free and traditional NAND-type ML structure.

A ternary content addressable memory (TCAM) speeds up the search process in the memory by searching through prestored contents rather than addresses. The additional don't care (X) state makes the TCAM suitable for many network applications but the large amount of cell requirement for storage consumes high power and takes a large design area. This paper presents a novel architecture of TCAM, which prestores 2 bits of data in an up-down manner and provides multiple masking operations through a single control multimasking circuit. The proposed dual bit associative memory with match error and mask control (EMDBAM) consumes low power and selects the valid value on matchline through match error controller. The proposed design has been implemented using a standard 45-nm CMOS technology, and the extracted layout has been simulated using SPECTRE with the supply voltage at 1 V. The proposed EMDBAM can reduce the cell area by 39% compared with a basic TCAM design with a reduction of 9.6% in the energy-delay product.