49 citations · 111 across the 28 of their papers we have counts for
30 papers
Identity-preserving Distillation Sampling by Fixed-Point Iterator
SeonHwa Kim, Jiwon Kim, Soobin Park +5
Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions…
PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification
Minsu Kim, Seungryong Kim, JungIn Park +2
Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data…
Few-shot Neural Radiance Fields Under Unconstrained Illumination
SeokYeong Lee, JunYong Choi, Seungryong Kim +2
In this paper, we introduce a new challenge for synthesizing novel view images in practical environments with limited input multi-view images and varying lighting conditions. Neura…
Deep Translation Prior: Test-time Training for Photorealistic Style Transfer
Sunwoo Kim, Soohyun Kim, Seungryong Kim
Recent techniques to solve photorealistic style transfer within deep convolutional neural networks (CNNs) generally require intensive training from large-scale datasets, thus havin…
Memory-guided Image De-raining Using Time-Lapse Data
Jaehoon Cho, Seungryong Kim, Kwanghoon Sohn
This paper addresses the problem of single image de-raining, that is, the task of recovering clean and rain-free background scenes from a single image obscured by a rainy artifact.…
Cost Aggregation Is All You Need for Few-Shot Segmentation
Sunghwan Hong, Seokju Cho, Jisu Nam +1
We introduce a novel cost aggregation network, dubbed Volumetric Aggregation with Transformers (VAT), to tackle the few-shot segmentation task by using both convolutions and transf…
Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge
Yoonna Jang, Jungwoo Lim, Yuna Hur +6
Humans usually have conversations by making use of prior knowledge about a topic and background information of the people whom they are talking to. However, existing conversational…
HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning
Yunsung Lee, Teakgyu Hong, Han-Cheol Cho +2
Recently, self-supervised methods show remarkable achievements in image-level representation learning. Nevertheless, their image-level self-supervisions lead the learned representa…
MOI-Mixer: Improving MLP-Mixer with Multi Order Interactions in Sequential Recommendation
Hojoon Lee, Dongyoon Hwang, Sunghwan Hong +3
Successful sequential recommendation systems rely on accurately capturing the user's short-term and long-term interest. Although Transformer-based models achieved state-of-the-art…
Learning Canonical 3D Object Representation for Fine-Grained Recognition
Sunghun Joung, Seungryong Kim, Minsu Kim +2
We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image, trained on an image collection without usi…
Deep Matching Prior: Test-Time Optimization for Dense Correspondence
Sunghwan Hong, Seungryong Kim
Conventional techniques to establish dense correspondences across visually or semantically similar images focused on designing a task-specific matching prior, which is difficult to…
CATs: Cost Aggregation Transformers for Visual Correspondence
Seokju Cho, Sunghwan Hong, Sangryul Jeon +3
We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images with additional challeng…
Modeling Object Dissimilarity for Deep Saliency Prediction
Bahar Aydemir, Deblina Bhattacharjee, Tong Zhang +3
Saliency prediction has made great strides over the past two decades, with current techniques modeling low-level information, such as color, intensity and size contrasts, and high-…
RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
Sungha Choi, Sanghun Jung, Huiwon Yun +3
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To addre…
On the confidence of stereo matching in a deep-learning era: a quantitative evaluation
Matteo Poggi, Seungryong Kim, Fabio Tosi +5
Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, synchronized and rectified images. Along…
Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation
Minsu Kim, Sunghun Joung, Seungryong Kim +3
Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the…
Online Exemplar Fine-Tuning for Image-to-Image Translation
Taewon Kang, Soohyun Kim, Sunwoo Kim +1
Existing techniques to solve exemplar-based image-to-image translation within deep convolutional neural networks (CNNs) generally require a training phase to optimize the network p…
Adaptive confidence thresholding for monocular depth estimation
Hyesong Choi, Hunsang Lee, Sunkyung Kim +4
Self-supervised monocular depth estimation has become an appealing solution to the lack of ground truth labels, but its reconstruction loss often produces over-smoothed results acr…
Volumetric Transformer Networks
Seungryong Kim, Sabine Süsstrunk, Mathieu Salzmann
Existing techniques to encode spatial invariance within deep convolutional neural networks (CNNs) apply the same warping field to all the feature channels. This does not account fo…
Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation
Sunghun Joung, Seungryong Kim, Hanjae Kim +4
Existing techniques to encode spatial invariance within deep convolutional neural networks only model 2D transformation fields. This does not account for the fact that objects in a…
Joint Learning of Semantic Alignment and Object Landmark Detection
Sangryul Jeon, Dongbo Min, Seungryong Kim +1
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark detection have improved their performance significantly. Current efforts for the tw…
Context-Aware Emotion Recognition Networks
Jiyoung Lee, Seungryong Kim, Sunok Kim +2
Traditional techniques for emotion recognition have focused on the facial expression analysis only, thus providing limited ability to encode context that comprehensively represents…
Semantic Attribute Matching Networks
Seungryong Kim, Dongbo Min, Somi Jeong +3
We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligent…
Recurrent Transformer Networks for Semantic Correspondence
Seungryong Kim, Stephen Lin, Sangryul Jeon +2
We present recurrent transformer networks (RTNs) for obtaining dense correspondences between semantically similar images. Our networks accomplish this through an iterative process…