most citedUniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification

1 citations · 2 across the 3 of their papers we have counts for

collaborators

5 papers

eess.IV2024

Machine Perceptual Quality: Evaluating the Impact of Severe Lossy Compression on Audio and Image Models

Dan Jacobellis, Daniel Cummings, Neeraja J. Yadwadkar

In the field of neural data compression, the prevailing focus has been on optimizing algorithms for either classical distortion metrics, such as PSNR or SSIM, or human perceptual q…

cs.LG2023

Neural Architecture Codesign for Fast Bragg Peak Analysis

Luke McDermott, Jason Weitz, Dmitri Demler +3

We develop an automated pipeline to streamline neural architecture codesign for fast, real-time Bragg peak analysis in high-energy diffraction microscopy. Traditional approaches, n…

cs.CV20231 cited

UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification

Jennifer Crawford, Haoli Yin, Luke McDermott +1

Multimodal Re-Identification (ReID) is a popular retrieval task that aims to re-identify objects across diverse data streams, prompting many researchers to integrate multiple modal…

cs.LG2023

Linear Mode Connectivity in Sparse Neural Networks

Luke McDermott, Daniel Cummings

With the rise in interest of sparse neural networks, we study how neural network pruning with synthetic data leads to sparse networks with unique training properties. We find that…

cs.CV20231 cited

GraFT: Gradual Fusion Transformer for Multimodal Re-Identification

Haoli Yin, Jiayao Li, Eva Schiller +2

Object Re-Identification (ReID) is pivotal in computer vision, witnessing an escalating demand for adept multimodal representation learning. Current models, although promising, rev…