Related papers: SPOLRE: Semantic Preserving Object Layout Reconstr…

In this paper, a modification to the training process of the popular SPLICE algorithm has been proposed for noise robust speech recognition. The modification is based on feature correlations, and enables this stereo-based algorithm to…

Interactive simulation of ultrasound imaging greatly facilitates sonography training. Although ray-tracing based methods have shown promising results, obtaining realistic images requires substantial modeling effort and manual parameter…

This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment with user prompts and consistency with input images. We…

Modern sensing systems generate large volumes of unlabeled multivariate time-series data. This abundance of unlabeled data makes self-supervised learning (SSL) a natural approach for learning transferable representations. However, most…

Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for training self-correction typically depend on either multiple…

Image captioning aims to describe visual content in natural language. As 'a picture is worth a thousand words', there could be various correct descriptions for an image. However, with maximum likelihood estimation as the training objective,…

Zero-shot Image Captioning (ZIC) increasingly utilizes synthetic datasets generated by text-to-image (T2I) models to mitigate the need for costly manual annotation. However, these T2I models often produce images that exhibit semantic…

While advanced image captioning systems are increasingly describing images coherently and exactly, recent progress in continual learning allows deep learning models to avoid catastrophic forgetting. However, the domain where image…

The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity or semantic…

As Vision-Language Models (VLMs) are increasingly deployed in split-DNN configurations--with visual encoders (e.g., ResNet, ViT) operating on user devices and sending intermediate features to the cloud--there is a growing privacy risk from…

Automatically evaluating the quality of image captions can be very challenging since human language is quite flexible that there can be various expressions for the same meaning. Most of the current captioning metrics rely on token level…

Zero-Shot Composed Image Retrieval (ZS-CIR) supports diverse tasks with a broad range of visual content manipulation intentions that can be related to domain, scene, object, and attribute. A key challenge for ZS-CIR is to accurately map…

Effectively aligning with human judgment when evaluating machine-generated image captions represents a complex yet intriguing challenge. Existing evaluation metrics like CIDEr or CLIP-Score fall short in this regard as they do not take into…

Remote sensing image change captioning (RSICC) aims to articulate the changes in objects of interest within bi-temporal remote sensing images using natural language. Given the limitations of current RSICC methods in expressing general…

In the domain of vision-language integration, generating detailed image captions poses a significant challenge due to the lack of curated and rich datasets. This study introduces PixLore, a novel method that leverages Querying Transformers…

We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. Depth-based reconstructions tend to focus on small-scale objects or large-scale SLAM reconstructions that treat moving objects as outliers. We…

Composed Image Retrieval (CIR) is the task of retrieving a target image from a gallery using a composed query consisting of a reference image and a modification text. Among various CIR approaches, training-free zero-shot methods based on…

In the era of evolving artificial intelligence, machines are increasingly emulating human-like capabilities, including visual perception and linguistic expression. Image captioning stands at the intersection of these domains, enabling…

OCR-based image captioning is an important but under-explored task, aiming to generate descriptions containing visual objects and scene text. Recent studies have made encouraging progress, but they are still suffering from a lack of overall…

One key bottleneck of employing state-of-the-art semantic segmentation networks in the real world is the availability of training labels. Conventional semantic segmentation networks require massive pixel-wise annotated labels to reach…