205 citations · 572 across the 30 of their papers we have counts for
34 papers · 1 filter
Tracking Anything with Decoupled Video Segmentation
Ho Kei Cheng, Seoung Wug Oh, Brian Price +2
Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary set…
Interactive Segmentation for Diverse Gesture Types Without Context
Josh Myers-Dean, Yifei Fan, Brian Price +2
Interactive segmentation entails a human marking an image to guide how a model either creates or edits a segmentation. Our work addresses limitations of existing methods: they eith…
Towards Open-World Segmentation of Parts
Tai-Yu Pan, Qing Liu, Wei-Lun Chao +1
Segmenting object parts such as cup handles and animal bodies is important in many real-world applications but requires more annotation effort. The largest dataset nowadays contain…
GamutMLP: A Lightweight MLP for Color Loss Recovery
Hoang M. Le, Brian Price, Scott Cohen +1
Cameras and image-editing software often process images in the wide-gamut ProPhoto color space, encompassing 90% of all visible colors. However, when images are encoded for sharing…
Improving Diffusion Models for Scene Text Editing with Dual Encoders
Jiabao Ji, Guanhua Zhang, Zhaowen Wang +4
Scene text editing is a challenging task that involves modifying or inserting specified texts in an image while maintaining its natural and realistic appearance. Most previous appr…
ObjectStitch: Generative Object Compositing
Yizhi Song, Zhifei Zhang, Zhe Lin +5
Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow ge…
One-Trimap Video Matting
Hongje Seong, Seoung Wug Oh, Brian Price +2
Recent studies made great progress in video matting by extending the success of trimap-based image matting to the video domain. In this paper, we push this task toward a more pract…
End-to-end Document Recognition and Understanding with Dessurt
Brian Davis, Bryan Morse, Bryan Price +3
We introduce Dessurt, a relatively simple document understanding transformer capable of being fine-tuned on a greater variety of document tasks than prior methods. It receives a do…
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation
Yutong Dai, Brian Price, He Zhang +1
Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps…
Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning
Josh Myers-Dean, Yinan Zhao, Brian Price +2
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…
Visual FUDGE: Form Understanding via Dynamic Graph Editing
Brian Davis, Bryan Morse, Brian Price +2
We address the problem of form understanding: finding text entities and the relationships/links between them in form images. The proposed FUDGE model formulates this problem on a g…
Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
Xingqian Xu, Zhifei Zhang, Zhaowen Wang +3
Text segmentation is a prerequisite in many real-world text-related tasks, e.g., text style transfer, and scene text removal. However, facing the lack of high-quality datasets and…
Text and Style Conditioned GAN for Generation of Offline Handwriting Lines
Brian Davis, Chris Tensmeyer, Brian Price +3
This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors. Unlike prior work, which produce stroke points or singl…
Objectness-Aware Few-Shot Semantic Segmentation
Yinan Zhao, Brian Price, Scott Cohen +1
Few-shot semantic segmentation models aim to segment images after learning from only a few annotated examples. A key challenge for them is how to avoid overfitting because limited…
DeepStrip: High Resolution Boundary Refinement
Peng Zhou, Brian Price, Scott Cohen +2
In this paper, we target refining the boundaries in high resolution images given low resolution masks. For memory and computation efficiency, we propose to convert the regions of i…
Getting to 99% Accuracy in Interactive Segmentation
Marco Forte, Brian Price, Scott Cohen +2
Interactive object cutout tools are the cornerstone of the image editing workflow. Recent deep-learning based interactive segmentation algorithms have made significant progress in…
Deep Visual Template-Free Form Parsing
Brian Davis, Bryan Morse, Scott Cohen +2
Automatic, template-free extraction of information from form images is challenging due to the variety of form layouts. This is even more challenging for historical forms due to noi…
Unconstrained Foreground Object Search
Yinan Zhao, Brian Price, Scott Cohen +1
Many people search for foreground objects to use when editing images. While existing methods can retrieve candidates to aid in this, they are constrained to returning objects that…
Answering Questions about Data Visualizations using Efficient Bimodal Fusion
Kushal Kafle, Robik Shrestha, Brian Price +2
Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e.g. bar charts, pie cha…
Measuring Human Perception to Improve Handwritten Document Transcription
Samuel Grieggs, Bingyu Shen, Greta Rauch +5
The subtleties of human perception, as measured by vision scientists through the use of psychophysics, are important clues to the internal workings of visual recognition. For insta…
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
Ning Xu, Linjie Yang, Yuchen Fan +6
Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentatio…
Guided Image Inpainting: Replacing an Image Region by Pulling Content from Another Image
Yinan Zhao, Brian Price, Scott Cohen +1
Deep generative models have shown success in automatically synthesizing missing image regions using surrounding context. However, users cannot directly decide what content to synth…
Discriminability objective for training descriptive captions
Ruotian Luo, Brian Price, Scott Cohen +1
One property that remains lacking in image captions generated by contemporary methods is discriminability: being able to tell two images apart given the caption for one of them. We…
DVQA: Understanding Data Visualizations via Question Answering
Kushal Kafle, Brian Price, Scott Cohen +1
Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them. Existing methods fail when faced with even minor variations in appearance.…