Search Results for author:
Found 39 papers, 23 papers with code
Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery
Despite its broad application and interest, it remains a challenging problem in part due to the vast range of conditions under which it must be robust.
A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court
To address this, we developed a document processing pipeline that produces an anonymized dataset optimized for topic modeling.
ComicsPAP: understanding comic strips by picking the correct panel
Large multimodal models (LMMs) have made impressive strides in image captioning, VQA, and video comprehension, yet they still struggle with the intricate temporal and spatial cues found in comics.
HoloMine: A Synthetic Dataset for Buried Landmines Recognition using Microwave Holographic Imaging
The detection and removal of landmines is a complex and risky task that requires advanced remote sensing techniques to reduce the risk for the professionals involved in this task.
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
In this paper, we show that the common practice of individually exploiting the text or image encoders of these powerful multi-modal models is highly suboptimal for intra-modal tasks like image-to-image retrieval.
ComiCap: A VLMs pipeline for dense captioning of Comic Panels
The comic domain is rapidly advancing with the development of single- and multi-page analysis and synthesis models.
Garment Attribute Manipulation with Multi-level Attention
In the rapidly evolving field of online fashion shopping, the need for more personalized and interactive image retrieval systems has become paramount.
One missing piece in Vision and Language: A Survey on Comics Understanding
Our contributions are fivefold: (1) We analyze the structure of the comics medium, detailing its distinctive compositional elements; (2) We survey the widely used datasets and tasks in comics research, emphasizing their role in advancing the field; (3) We introduce the Layer of Comics Understanding (LoCU) framework, a novel taxonomy that redefines vision-language tasks within comics and lays the foundation for future work; (4) We provide a detailed review and categorization of existing methods following the LoCU framework; (5) Finally, we highlight current research challenges and propose directions for future exploration, particularly in the context of vision-language models applied to comics.
Prompt and Prejudice
This paper investigates the impact of using first names in Large Language Models (LLMs) and Vision Language Models (VLMs), particularly when prompted with ethical decision-making tasks.
CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
We introduce a novel benchmark, CoMix, designed to evaluate the multi-task capabilities of models in comic analysis.
Comics Datasets Framework: Mix of Comics datasets for detection benchmarking
We have benchmarked a variety of detection architectures using the Comics Datasets Framework.
Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation
Our approach, which we call Knowledge Distillation Prompt Learning (KDPL), can be integrated into existing prompt learning techniques and eliminates the need for labeled examples during adaptation.
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
Given a query consisting of a reference image and a relative caption, Composed Image Retrieval (CIR) aims to retrieve target images visually similar to the reference one while incorporating the changes specified in the relative caption.
Multimodal-Conditioned Latent Diffusion Models for Fashion Image Editing
Fashion illustration is a crucial medium for designers to convey their creative vision and transform design concepts into tangible representations that showcase the interplay between clothing and the human body.
Quality-Aware Image-Text Alignment for Real-World Image Quality Assessment
At the same time, we force CLIP to generate consistent representations for images with similar content and the same level of degradation.
Ranked #2 on
No-Reference Image Quality Assessment
on UHD-IQA
Restoration of Analog Videos Using Swin-UNet
In this paper, we present a system to restore analog videos of historical archives.
Ranked #2 on
Analog Video Restoration
on TAPE
Perceptual Quality Improvement in Videoconferencing using Keyframes-based GAN
Given that, in this context, the speaker is typically in front of the camera and remains the same for the entire duration of the transmission, we can maintain a set of reference keyframes of the person from the higher-quality I-frames that are transmitted within the video stream and exploit them to guide the visual quality improvement; a novel aspect of this approach is the update policy that maintains and updates a compact and effective set of reference keyframes.
Reference-based Restoration of Digitized Analog Videotapes
We design a transformer-based Swin-UNet network that exploits both neighboring and reference frames via our Multi-Reference Spatial Feature Fusion (MRSFF) blocks.
Ranked #1 on
Analog Video Restoration
on TAPE
ARNIQA: Learning Distortion Manifold for Image Quality Assessment
In this work, we propose a self-supervised approach named ARNIQA (leArning distoRtion maNifold for Image Quality Assessment) for modeling the image distortion manifold to obtain quality representations in an intrinsic manner.
Ranked #2 on
No-Reference Image Quality Assessment
on CSIQ
Mapping Memes to Words for Multimodal Hateful Meme Classification
Multimodal image-text memes are prevalent on the internet, serving as a unique form of communication that combines visual and textual elements to convey humor, ideas, or emotions.
Ranked #3 on
Hateful Meme Classification
on HarMeme
Exploiting CLIP-based Multi-modal Approach for Artwork Classification and Retrieval
Given the recent advances in multimodal image pretraining where visual models trained with semantically dense textual supervision tend to have better generalization capabilities than those trained using categorical attributes or through unsupervised techniques, in this work we investigate how recent CLIP model can be applied in several tasks in artwork domain.
OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data
The inexorable growth of online shopping and e-commerce demands scalable and robust machine learning-based solutions to accommodate customer requirements.
Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption.
Ranked #9 on
Image Retrieval
on Fashion IQ
ECO: Ensembling Context Optimization for Vision-Language Models
Among these, the CLIP model has shown remarkable capabilities for zero-shot transfer by matching an image and a custom textual prompt in its latent space.
4DSR-GCN: 4D Video Point Cloud Upsampling using Graph Convolutional Networks
Time varying sequences of 3D point clouds, or 4D point clouds, are now being acquired at an increasing pace in several applications (e. g., LiDAR in autonomous or assisted driving).
LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On
In this context, image-based virtual try-on, which consists in generating a novel image of a target model wearing a given in-shop garment, has yet to capitalize on the potential of these powerful generative solutions.
Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing
Given the lack of existing datasets suitable for the task, we also extend two existing fashion datasets, namely Dress Code and VITON-HD, with multimodal annotations collected in a semi-automatic manner.
Zero-Shot Composed Image Retrieval with Textual Inversion
Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption that describes the difference between the two images.
Error assessment of microwave holography inversion for shallow buried objects
Holographic imaging is a technique that uses microwave energy to create a three-dimensional image of an object or scene.
Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features
The proposed method is based on an initial training stage where a simple combination of visual and textual features is used, to fine-tune the CLIP text encoder.
Ranked #3 on
Image Retrieval
on LaSCo
Composed Image Retrieval (CoIR)
Content-Based Image Retrieval
+2
Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features
the visual content of the query image.
Ranked #15 on
Image Retrieval
on CIRR
Partially fake it till you make it: mixing real and fake thermal images for improved object detection
In this paper we propose a novel data augmentation approach for visual content domains that have scarce training datasets, compositing synthetic 3D objects within real scenes.
Robust pedestrian detection in thermal imagery using synthesized images
Experimental results demonstrate the effectiveness of our approach: using less than 50\% of available real thermal training data, and relying on synthesized data generated by our model in the domain adaptation phase, our detector achieves state-of-the-art results on the KAIST Multispectral Pedestrian Detection Benchmark; even if more real thermal data is available adding GAN generated images to the training data results in improved performance, thus showing that these images act as an effective form of data augmentation.
Inner Eye Canthus Localization for Human Body Temperature Screening
As additional contribution, we enrich the original dataset by using the annotated landmarks to deform and project the 3DMM onto the images.
Image Retrieval using Multi-scale CNN Features Pooling
In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network.
Deep Generative Adversarial Compression Artifact Removal
Moreover we show that our approach can be used as a pre-processing step for object detection in case images are degraded by compression to a point that state-of-the art detectors fail.
Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases
In this paper we present an efficient method for visual descriptors retrieval based on compact hash codes computed using a multiple k-means assignment.
Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval
Where previous reviews on content-based image retrieval emphasize on what can be seen in an image to bridge the semantic gap, this survey considers what people tag about an image.
A Data-Driven Approach for Tag Refinement and Localization in Web Videos
Our approach exploits collective knowledge embedded in user-generated tags and web sources, and visual similarity of keyframes and images uploaded to social sites like YouTube and Flickr, as well as web sources like Google and Bing.
