336 citations · 523 across the 20 of their papers we have counts for
27 papers
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…
Long-range Multimodal Pretraining for Movie Understanding
Dawit Mureja Argaw, Joon-Young Lee, Markus Woodson +2
Learning computer vision models from (and for) movies has a long-standing history. While great progress has been attained, there is still a need for a pretrained multimodal model t…
Tracking by Associating Clips
Sanghyun Woo, Kwanyong Park, Seoung Wug Oh +2
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…
Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection
Sanghyun Woo, Kwanyong Park, Seoung Wug Oh +2
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 introduc…
Per-Clip Video Object Segmentation
Kwanyong Park, Sanghyun Woo, Seoung Wug Oh +2
Recently, memory-based approaches show promising results on semi-supervised video object segmentation. These methods predict object masks frame-by-frame with the help of frequently…
The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing
Dawit Mureja Argaw, Fabian Caba Heilbron, Joon-Young Lee +2
Machine learning is transforming the video editing industry. Recent advances in computer vision have leveled-up video editing tasks such as intelligent reframing, rotoscoping, colo…
Learning to Associate Every Segment for Video Panoptic Segmentation
Sanghyun Woo, Dahun Kim, Joon-Young Lee +1
Temporal correspondence - linking pixels or objects across frames - is a fundamental supervisory signal for the video models. For the panoptic understanding of dynamic scenes, we f…
Onion-Peel Networks for Deep Video Completion
Seoung Wug Oh, Sungho Lee, Joon-Young Lee +1
We propose the onion-peel networks for video completion. Given a set of reference images and a target image with holes, our network fills the hole by referring the contents in the…
Learning Video Representations from Correspondence Proposals
Xingyu Liu, Joon-Young Lee, Hailin Jin
Correspondences between frames encode rich information about dynamic content in videos. However, it is challenging to effectively capture and learn those due to their irregular str…
Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence
Dahun Kim, Sanghyun Woo, Joon-Young Lee +1
Blind video decaptioning is a problem of automatically removing text overlays and inpainting the occluded parts in videos without any input masks. While recent deep learning based…
Deep Video Inpainting
Dahun Kim, Sanghyun Woo, Joon-Young Lee +1
Video inpainting aims to fill spatio-temporal holes with plausible content in a video. Despite tremendous progress of deep neural networks for image inpainting, it is challenging t…
Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks
Seoung Wug Oh, Joon-Young Lee, Ning Xu +1
We present a deep learning method for the interactive video object segmentation. Our method is built upon two core operations, interaction and propagation, and each operation is co…
Video Object Segmentation using Space-Time Memory Networks
Seoung Wug Oh, Joon-Young Lee, Ning Xu +1
We propose a novel solution for semi-supervised video object segmentation. By the nature of the problem, available cues (e.g. video frame(s) with object masks) become richer with t…
GAPLE: Generalizable Approaching Policy LEarning for Robotic Object Searching in Indoor Environment
Xin Ye, Zhe Lin, Joon-Young Lee +3
We study the problem of learning a generalizable action policy for an intelligent agent to actively approach an object of interest in an indoor environment solely from its visual i…
CBAM: Convolutional Block Attention Module
Sanghyun Woo, Jongchan Park, Joon-Young Lee +1
We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, o…
BAM: Bottleneck Attention Module
Jongchan Park, Sanghyun Woo, Joon-Young Lee +1
Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in genera…
Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning
Jongchan Park, Joon-Young Lee, Donggeun Yoo +1
Learning-based color enhancement approaches typically learn to map from input images to retouched images. Most of existing methods require expensive pairs of input-retouched images…
The AdobeIndoorNav Dataset: Towards Deep Reinforcement Learning based Real-world Indoor Robot Visual Navigation
Kaichun Mo, Haoxiang Li, Zhe Lin +1
Deep reinforcement learning (DRL) demonstrates its potential in learning a model-free navigation policy for robot visual navigation. However, the data-demanding algorithm relies on…
Photometric Stabilization for Fast-forward Videos
Xuaner Cecilia Zhang, Joon-Young Lee, Kalyan Sunkavalli +1
Videos captured by consumer cameras often exhibit temporal variations in color and tone that are caused by camera auto-adjustments like white-balance and exposure. When such videos…
Gradient-based Camera Exposure Control for Outdoor Mobile Platforms
Inwook Shim, Tae-Hyun Oh, Joon-Young Lee +3
We introduce a novel method to automatically adjust camera exposure for image processing and computer vision applications on mobile robot platforms. Because most image processing a…
Action-Driven Object Detection with Top-Down Visual Attentions
Donggeun Yoo, Sunggyun Park, Kyunghyun Paeng +2
A dominant paradigm for deep learning based object detection relies on a "bottom-up" approach using "passive" scoring of class agnostic proposals. These approaches are efficient bu…
Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks
Yinda Zhang, Shuran Song, Ersin Yumer +4
Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperform…
Fine-scale Surface Normal Estimation using a Single NIR Image
Youngjin Yoon, Gyeongmin Choe, Namil Kim +2
We present surface normal estimation using a single near infrared (NIR) image. We are focusing on fine-scale surface geometry captured with an uncalibrated light source. To tackle…
Automatic Content-Aware Color and Tone Stylization
Joon-Young Lee, Kalyan Sunkavalli, Zhe Lin +2
We introduce a new technique that automatically generates diverse, visually compelling stylizations for a photograph in an unsupervised manner. We achieve this by learning style ra…