Search Results for author:
Found 29 papers, 10 papers with code
Iterative Feature Transformation for Fast and Versatile Universal Style Transfer
The general framework for fast universal style transfer consists of an autoencoder and a feature transformation at the bottleneck.
Interpreting COVID Lateral Flow Tests' Results with Foundation Models
Accordingly, we explore the abilities of modern foundation vision language models (VLMs) in interpreting such tests.
An Evaluation of GPT-4V and Gemini in Online VQA
While there is much excitement about the potential of large multimodal models (LMM), a comprehensive evaluation is critical to establish their true capabilities and limitations.
Fully Authentic Visual Question Answering Dataset from Online Communities
Visual Question Answering (VQA) entails answering questions about images.
VQA Therapy: Exploring Answer Differences by Visually Grounding Answers
Visual question answering is a task of predicting the answer to a question about an image.
Interactive Segmentation for Diverse Gesture Types Without Context
Interactive segmentation entails a human marking an image to guide how a model either creates or edits a segmentation.
Helping Visually Impaired People Take Better Quality Pictures
The photographs taken by visually impaired users often suffer from one or both of two kinds of quality issues: technical quality (distortions), and semantic quality, such as framing and aesthetic composition.
Salient Object Detection for Images Taken by People With Vision Impairments
Salient object detection is the task of producing a binary mask for an image that deciphers which pixels belong to the foreground object versus background.
A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories
Our goal is to improve upon the status quo for designing image classification models trained in one domain that perform well on images from another domain.
Line Search-Based Feature Transformation for Fast, Stable, and Tunable Content-Style Control in Photorealistic Style Transfer
Photorealistic style transfer is the task of synthesizing a realistic-looking image when adapting the content from one image to appear in the style of another image.
VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments
Compared to existing few-shot object detection and instance segmentation datasets, our dataset is the first to locate holes in objects (e. g., found in 12. 3\% of our segmentations), it shows objects that occupy a much larger range of sizes relative to the images, and text is over five times more common in our objects (e. g., found in 22. 4\% of our segmentations).
PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Models
To our knowledge, this is the first knowledge distillation method for photorealistic style transfer.
Grounding Answers for Visual Questions Asked by Visually Impaired People
Visual question answering is the task of answering questions about images.
Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning
Generalized few-shot semantic segmentation was introduced to move beyond only evaluating few-shot segmentation models on novel classes to include testing their ability to remember base classes.
PhotoWCT$^2$: Compact Autoencoder for Photorealistic Style Transfer Resulting from Blockwise Training and Skip Connections of High-Frequency Residuals
First, we introduce blockwise training to perform coarse-to-fine feature transformations that enable state-of-art stylization strength in a single autoencoder in place of the inefficient cascade of four autoencoders used in PhotoWCT.
CrowdMOT: Crowdsourcing Strategies for Tracking Multiple Objects in Videos
Crowdsourcing is a valuable approach for tracking objects in videos in a more scalable manner than possible with domain experts.
Objectness-Aware Few-Shot Semantic Segmentation
We demonstrate how to increase overall model capacity to achieve improved performance, by introducing objectness, which is class-agnostic and so not prone to overfitting, for complementary use with class-specific features.
Assessing Image Quality Issues for Real-World Problems
We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering.
Captioning Images Taken by People Who Are Blind
While an important problem in the vision community is to design algorithms that can automatically caption images, few publicly-available datasets for algorithm development directly address the interests of real users.
VizWiz Dataset Browser: A Tool for Visualizing Machine Learning Datasets
We present a visualization tool to exhaustively search and browse through a set of large-scale machine learning datasets.
Why Does a Visual Question Have Different Answers?
Visual question answering is the task of returning the answer to a question about an image.
Unconstrained Foreground Object Search
Many people search for foreground objects to use when editing images.
VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People
We introduce the first visual privacy dataset originating from people who are blind in order to better understand their privacy disclosures and to encourage the development of algorithms that can assist in preventing their unintended disclosures.
Predicting How to Distribute Work Between Algorithms and Humans to Segment an Image Batch
We propose a resource allocation framework for predicting how best to allocate a fixed budget of human annotation effort in order to collect higher quality segmentations for a given batch of images and automated methods.
Guided Image Inpainting: Replacing an Image Region by Pulling Content from Another Image
Deep generative models have shown success in automatically synthesizing missing image regions using surrounding context.
VizWiz Grand Challenge: Answering Visual Questions from Blind People
The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial VQA settings.
Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)
We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems.
Visual Question: Predicting If a Crowd Will Agree on the Answer
Visual question answering (VQA) systems are emerging from a desire to empower users to ask any natural language question about visual content and receive a valid answer in response.
Pull the Plug? Predicting If Computers or Humans Should Segment Images
We propose a resource allocation framework for predicting how best to allocate a fixed budget of human annotation effort in order to collect higher quality segmentations for a given batch of images and automated methods.
