Ming-Hsuan Yang

research

∙ 04/13/2020

Regularizing Meta-Learning via Gradient Dropout

With the growing attention on learning-to-learn new tasks using only a f...

Hung-Yu Tseng, et al. ∙

research

∙ 04/02/2020

Learning to See Through Obstructions

We present a learning-based approach for removing unwanted obstructions,...

Yu-Lun Liu, et al. ∙

research

∙ 04/02/2020

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Recovering a high dynamic range (HDR) image from a single low dynamic ra...

Yu-Lun Liu, et al. ∙

research

∙ 03/31/2020

Deep Semantic Matching with Foreground Detection and Cycle-Consistency

Establishing dense semantic correspondences between object instances rem...

Yun-Chun Chen, et al. ∙

research

∙ 03/30/2020

TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge

Real-time semantic video segmentation is a challenging task due to the s...

Junyi Feng, et al. ∙

research

∙ 03/24/2020

Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

Object frequency in the real world often follows a power law, leading to...

Muhammad Abdullah Jamal, et al. ∙

research

∙ 03/18/2020

Collaborative Distillation for Ultra-Resolution Universal Style Transfer

Universal style transfer methods typically leverage rich representations...

Huan Wang, et al. ∙

research

∙ 03/17/2020

CycleISP: Real Image Restoration via Improved Data Synthesis

The availability of large-scale datasets has helped unleash the true pot...

Syed Waqas Zamir, et al. ∙

research

∙ 03/15/2020

Learning Enriched Features for Real Image Restoration and Enhancement

With the goal of recovering high-quality image content from its degraded...

Syed Waqas Zamir, et al. ∙

research

∙ 03/13/2020

Self-supervised Single-view 3D Reconstruction via Semantic Consistency

We learn a self-supervised, single-view 3D reconstruction model that pre...

Xueting Li, et al. ∙

research

∙ 03/02/2020

Gated Fusion Network for Degraded Image Super Resolution

Single image super resolution aims to enhance image quality with respect...

Xinyi Zhang, et al. ∙

research

∙ 02/19/2020

Model-Agnostic Structured Sparsification with Learnable Channel Shuffle

Recent advances in convolutional neural networks (CNNs) usually come wit...

Xin-Yu Zhang, et al. ∙

research

∙ 02/19/2020

Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning

Weakly-supervised semantic segmentation is a challenging task as no pixe...

Xiang Wang, et al. ∙

research

∙ 01/23/2020

Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation

Few-shot classification aims to recognize novel categories with only few...

Hung-Yu Tseng, et al. ∙

research

∙ 01/10/2020

Visual Question Answering on 360° Images

In this work, we introduce VQA 360, a novel task of visual question answ...

Shih-Han Chou, et al. ∙

research

∙ 01/09/2020

CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency

Unsupervised domain adaptation algorithms aim to transfer the knowledge ...

Yun-Chun Chen, et al. ∙

research

∙ 12/30/2019

RC-DARTS: Resource Constrained Differentiable Architecture Search

Recent advances show that Neural Architectural Search (NAS) method is ab...

Xiaojie Jin, et al. ∙

research

∙ 12/25/2019

Controllable and Progressive Image Extrapolation

Image extrapolation aims at expanding the narrow field of view of a give...

Yijun Li, et al. ∙

research

∙ 12/19/2019

Neural Design Network: Graphic Layout Generation with Constraints

Graphic design is essential for visual communication with layouts being ...

Hsin-Ying Lee, et al. ∙

research

∙ 11/22/2019

Adversarial Learning of Privacy-Preserving and Task-Oriented Representations

Data privacy has emerged as an important issue as data-driven deep learn...

Taihong Xiao, et al. ∙

research

∙ 11/20/2019

Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications

Visual events are usually accompanied by sounds in our daily lives. Howe...

Arda Senocak, et al. ∙

research

∙ 11/05/2019

Dancing to Music

Dancing to music is an instinctive move by humans. Learning to model the...

Hsin-Ying Lee, et al. ∙

research

∙ 11/02/2019

Quadratic video interpolation

Video interpolation is an important problem in computer vision, which he...

Xiangyu Xu, et al. ∙

research

∙ 10/24/2019

Progressive Domain Adaptation for Object Detection

Recent deep learning methods for object detection rely on a large amount...

Han-Kai Hsu, et al. ∙

research

∙ 10/10/2019

Referring Expression Object Segmentation with Caption-Aware Consistency

Referring expressions are natural language descriptions that identify a ...

Yi-Wen Chen, et al. ∙

research

∙ 09/26/2019

Joint-task Self-supervised Learning for Temporal Correspondence

This paper proposes to learn reliable dense correspondence from videos i...

Xueting Li, et al. ∙

research

∙ 07/31/2019

Video Stitching for Linear Camera Arrays

Despite the long history of image and video stitching research, existing...

Wei-Sheng Lai, et al. ∙

research

∙ 06/13/2019

Show, Match and Segment: Joint Learning of Semantic Matching and Object Co-segmentation

We present an approach for jointly matching and segmenting object instan...

Yun-Chun Chen, et al. ∙

research

∙ 06/06/2019

Detection and Tracking of Multiple Mice Using Part Proposal Networks

The study of mouse social behaviours has been increasingly undertaken in...

Zheheng Jiang, et al. ∙

research

∙ 05/14/2019

Self-supervised Audio Spatialization with Correspondence Classifier

Spatial audio is an essential medium to audiences for 3D visual and audi...

Yu-Ding Lu, et al. ∙

research

∙ 05/13/2019

Weakly-supervised Caricature Face Parsing through Domain Adaptation

A caricature is an artistic form of a person's picture in which certain ...

Wenqing Chu, et al. ∙

research

∙ 05/13/2019

Few-Shot Viewpoint Estimation

Viewpoint estimation for known categories of objects has been improved s...

Hung-Yu Tseng, et al. ∙

research

∙ 05/03/2019

SCOPS: Self-Supervised Co-Part Segmentation

Parts provide a good intermediate representation of objects that is robu...

Wei-Chih Hung, et al. ∙

research

∙ 05/02/2019

DRIT++: Diverse Image-to-Image Translation via Disentangled Representations

Image-to-image translation aims to learn the mapping between two visual ...

Hsin-Ying Lee, et al. ∙

research

∙ 04/03/2019

Target-Aware Deep Tracking

Existing deep trackers mainly use convolutional neural networks pre-trai...

Xin Li, et al. ∙

research

∙ 04/02/2019

Res2Net: A New Multi-scale Backbone Architecture

Representing features at multiple scales is of great importance for nume...

Shang-Hua Gao, et al. ∙

research

∙ 04/01/2019

Depth-Aware Video Frame Interpolation

Video frame interpolation aims to synthesize nonexistent frames in-betwe...

Wenbo Bao, et al. ∙

research

∙ 03/20/2019

Im2Pencil: Controllable Pencil Illustration from Photographs

We propose a high-quality photo-to-pencil translation method with fine-g...

Yijun Li, et al. ∙

research

∙ 03/15/2019

Inserting Videos into Videos

In this paper, we introduce a new problem of manipulating a given video ...

Donghoon Lee, et al. ∙

research

∙ 03/13/2019

Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments

Affordance modeling plays an important role in visual understanding. In ...

Xueting Li, et al. ∙

research

∙ 03/13/2019

Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis

Most conditional generation tasks expect diverse outputs given a single ...

Qi Mao, et al. ∙

research

∙ 02/02/2019

Online Multi-Object Tracking with Dual Matching Attention Networks

In this paper, we propose an online Multi-Object Tracking (MOT) approach...

Ji Zhu, et al. ∙

research

∙ 01/08/2019

Unseen Object Segmentation in Videos via Transferable Representations

In order to learn object segmentation models in videos, conventional met...

Yi-Wen Chen, et al. ∙

research

∙ 12/15/2018

PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection

In saliency detection, every pixel needs contextual information to make ...

Nian Liu, et al. ∙

research

∙ 12/06/2018

Context-Aware Synthesis and Placement ofObject Instances

Learning to insert an object instance into an image in a semantically co...

Donghoon Lee, et al. ∙

research

∙ 12/06/2018

Context-Aware Synthesis and Placement of Object Instances

Learning to insert an object instance into an image in a semantically co...

Donghoon Lee, et al. ∙

research

∙ 11/22/2018

Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement

We address the problem of restoring a high-resolution face image from a ...

Yibing Song, et al. ∙

research

∙ 10/23/2018

A Fusion Approach for Multi-Frame Optical Flow Estimation

To date, top-performing optical flow estimation methods only take pairs ...

Zhile Ren, et al. ∙

research

∙ 10/20/2018

MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement

Motion estimation (ME) and motion compensation (MC) have been widely use...

Wenbo Bao, et al. ∙

research

∙ 10/09/2018

Deep Attentive Tracking via Reciprocative Learning

Visual attention, derived from cognitive neuroscience, facilitates human...

Shi Pu, et al. ∙

Ming-Hsuan Yang

Featured Co-authors