Sangryul Jeon
YOU?
Author Swipe
View article: Zero-shot Building Attribute Extraction from Large-Scale Vision and Language Models
Zero-shot Building Attribute Extraction from Large-Scale Vision and Language Models Open
Existing building recognition methods, exemplified by BRAILS, utilize supervised learning to extract information from satellite and street-view images for classification and segmentation. However, each task module requires human-annotated …
View article: Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence Open
Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters. This architecture, however, inevitably results in a low-resol…
View article: Unsupervised Scene Sketch to Photo Synthesis
Unsupervised Scene Sketch to Photo Synthesis Open
Sketches make an intuitive and powerful visual expression as they are fast executed freehand drawings. We present a method for synthesizing realistic photos from scene sketches. Without the need for sketch and photo pairs, our framework di…
View article: Pyramidal Semantic Correspondence Networks
Pyramidal Semantic Correspondence Networks Open
This paper presents a deep architecture, called pyramidal semantic correspondence networks (PSCNet), that estimates locally-varying affine transformation fields across semantically similar images. To deal with large appearance and shape va…
View article: Semantic Correspondence with Transformers.
Semantic Correspondence with Transformers. Open
We propose a novel cost aggregation network, called Cost Aggregation with Transformers (CATs), to find dense correspondences between semantically similar images with additional challenges posed by large intra-class appearance and geometric…
View article: CATs: Cost Aggregation Transformers for Visual Correspondence
CATs: Cost Aggregation Transformers for Visual Correspondence Open
We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images with additional challenges posed by large intra-class appearance and geometric vari…
View article: Joint Learning of Semantic Alignment and Object Landmark Detection
Joint Learning of Semantic Alignment and Object Landmark Detection Open
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark detection have improved their performance significantly. Current efforts for the two tasks focus on addressing the lack of massive training da…
View article: Joint Learning of Semantic Alignment and Object Landmark Detection
Joint Learning of Semantic Alignment and Object Landmark Detection Open
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark detection have improved their performance significantly. Current efforts for the two tasks focus on addressing the lack of massive training da…
View article: Graph Regularization Network with Semantic Affinity for Weakly-Supervised Temporal Action Localization
Graph Regularization Network with Semantic Affinity for Weakly-Supervised Temporal Action Localization Open
This paper presents a novel deep architecture for weakly-supervised temporal action localization that not only generates segment-level action responses but also propagates segment-level responses to the neighborhood in a form of graph Lapl…
View article: Semantic Attribute Matching Networks
Semantic Attribute Matching Networks Open
We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligently weaves the advantages of the two tasks while overcoming …
View article: Semantic Attribute Matching Networks
Semantic Attribute Matching Networks Open
We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligently weaves the advantages of the two tasks while overcoming …
View article: Recurrent Transformer Networks for Semantic Correspondence
Recurrent Transformer Networks for Semantic Correspondence Open
We present recurrent transformer networks (RTNs) for obtaining dense correspondences between semantically similar images. Our networks accomplish this through an iterative process of estimating spatial transformations between the input ima…
View article: PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence Estimation
PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence Estimation Open
This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra-class appearance a…
View article: PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence Open
This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra-class appearance a…
View article: FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence Open
We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic correspondence. To robustly match points among different instances within the same object class, we formulate FCSS using local self-similarity (…