-
Article
CMSNet: Deep Color and Monochrome Stereo
In this paper, we propose an end-to-end convolutional neural network for stereo matching with color and monochrome cameras, called CMSNet (Color and Monochrome Stereo Network). Both cameras have the same structur...
-
Chapter and Conference Paper
One-Trimap Video Matting
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 practical setting and propose One-...
-
Chapter and Conference Paper
The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing
Machine learning is transforming the video editing industry. Recent advances in computer vision have leveled-up video editing tasks such as intelligent reframing, rotosco**, color grading, or applying digita...
-
Chapter and Conference Paper
Tracking by Associating Clips
The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its s...
-
Chapter and Conference Paper
Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection
Scaling object taxonomies is one of the important steps toward a robust real-world deployment of recognition systems. We have faced remarkable progress in images since the introduction of the LVIS benchmark. T...
-
Article
Open AccessMechanism of Heat-Induced Fusion of Silver Nanowires
Physical changes in arranged silver nanowires were monitored during progressive heating inside a transmission electron microscope. Using the in-situ experimental method, overall variation of silver nanowires and ...
-
Article
A Simple and Light-Weight Attention Module for Convolutional Neural Networks
Many aspects of deep neural networks, such as depth, width, or cardinality, have been studied to strengthen the representational power. In this work, we study the effect of attention in convolutional neural netwo...
-
Chapter and Conference Paper
URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark
We propose a unified referring video object segmentation network (URVOS). URVOS takes a video and a referring expression as inputs, and estimates the object masks referred by the given language expression in t...
-
Article
Correction to: One-Day Outdoor Photometric Stereo Using Skylight Estimation
The original version of this article unfortunately contained mistakes in the figure captions.
-
Article
One-Day Outdoor Photometric Stereo Using Skylight Estimation
We present an outdoor photometric stereo method using images captured in a single day. We simulate a sky hemisphere for each image according to its GPS and timestamp and parameterize the obtained sky hemispher...
-
Article
Three-Partition Hydrogel Apparatus to Gauge Viability of Gelatin-Pluronic® F127 Hybrid Hydrogels as Cell Barrier Membranes for Guided Bone Regeneration Following Periodontitis
Periodontitis, or conventionally “Gum Disease,” is the infection and inflammation of gingival tissue, and is currently the leading cause of tooth loss in the United States. One of the most effective treatments...
-
Article
Estrogenic effects of phytoestrogens derived from Flemingia strobilifera in MCF-7 cells and immature rats
Phytoestrogen (PE) has received considerable attention due to the physiological significance of its estrogenicity. Flemingia strobilifera (FS) has been used as a folk medicine in Asia for the treatment of inflamm...
-
Chapter and Conference Paper
CBAM: Convolutional Block Attention Module
We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers...
-
Chapter and Conference Paper
Learning to Blend Photos
Photo blending is a common technique to create aesthetically pleasing artworks by combining multiple photos. However, the process of photo blending is usually time-consuming, and care must be taken in the proc...
-
Chapter and Conference Paper
What Do I Annotate Next? An Empirical Study of Active Learning for Action Localization
Despite tremendous progress achieved in temporal action localization, state-of-the-art methods still struggle to train accurate models when annotated data is scarce. In this paper, we introduce a novel active ...
-
Chapter and Conference Paper
Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias
While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts. Our a...
-
Article
Generating Fluttering Patterns with Low Autocorrelation for Coded Exposure Imaging
The performance of coded exposure imaging critically depends on finding good binary sequences. Previous coded exposure imaging methods have mostly relied on random searching to find the binary codes, but that ...
-
Article
Robust upright adjustment of 360 spherical panoramas
With the recent advent of 360 cameras, spherical panorama images are becoming more popular and widely available. In a spherical panorama, alignment of the scene orientation to the image axes is important for p...
-
Chapter and Conference Paper
Fine-Scale Surface Normal Estimation Using a Single NIR Image
We present surface normal estimation using a single near infrared (NIR) image. We are focusing on reconstructing fine-scale surface geometry using an image captured with an uncalibrated light source. To tackle...
-
Article
Open AccessSynchronous mucosal Schwann-cell hamartomas in a young adult suggestive of mucosal Schwann-cell harmatomatosis: a case report
Mucosal Schwann-cell hamartoma is a rare mesenchymal polyp that presents in the intestine. Despite lacking ganglion cells, it resembles a gastrointestinal ganglioneuroma.