68 citations · 148 across the 12 of their papers we have counts for
15 papers
Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models
Juhong Min, Lazar Valkov, Vitali Petsiuk +2
Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this tension via foveation: a coarse…
GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining
Deen Dayal Mohan, Hossein Souri, Vitali Petsiuk +4
Until recently, the success of large-scale vision-language models (VLMs) has primarily relied on billion-sample datasets, posing a significant barrier to progress. Latest works hav…
Combinative Matching for Geometric Shape Assembly
Nahyuk Lee, Juhong Min, Junhong Lee +2
This paper introduces a new shape-matching methodology, combinative matching, to combine interlocking parts for geometric shape assembly. Previous methods for geometric assembly ty…
3D Geometric Shape Assembly via Efficient Point Cloud Matching
Nahyuk Lee, Juhong Min, Junha Lee +4
Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local…
MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
Juhong Min, Shyamal Buch, Arsha Nagrani +2
This paper addresses the task of video question answering (videoQA) via a decomposed multi-stage, modular reasoning framework. Previous modular methods have shown promise with a si…
Efficient Semantic Matching with Hypercolumn Correlation
Seungwook Kim, Juhong Min, Minsu Cho
Recent studies show that leveraging the match-wise relationships within the 4D correlation map yields significant improvements in establishing semantic correspondences - but at the…
Peripheral Vision Transformer
Juhong Min, Yucheng Zhao, Chong Luo +1
Human vision possesses a special type of visual processing systems called peripheral vision. Partitioning the entire visual field into multiple contour regions based on the distanc…
TransforMatcher: Match-to-Match Attention for Semantic Correspondence
Seungwook Kim, Juhong Min, Minsu Cho
Establishing correspondences between images remains a challenging task, especially under large appearance changes due to different viewpoints or intra-class variations. In this wor…
Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
Juhong Min, Seungwook Kim, Minsu Cho
Despite advances in feature representation, leveraging geometric relations is crucial for establishing reliable visual correspondences under large variations of images. In this wor…
Relational Embedding for Few-Shot Classification
Dahyun Kang, Heeseung Kwon, Juhong Min +1
We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective. Our method leverages relational p…
Hypercorrelation Squeeze for Few-Shot Segmentation
Juhong Min, Dahyun Kang, Minsu Cho
Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenging task r…
Convolutional Hough Matching Networks
Juhong Min, Minsu Cho
Despite advances in feature representation, leveraging geometric relations is crucial for establishing reliable visual correspondences under large variations of images. In this wor…
Learning to Compose Hypercolumns for Visual Correspondence
Juhong Min, Jongmin Lee, Jean Ponce +1
Feature representation plays a crucial role in visual correspondence, and recent methods for image matching resort to deeply stacked convolutional layers. These models, however, ar…
SPair-71k: A Large-scale Benchmark for Semantic Correspondence
Juhong Min, Jongmin Lee, Jean Ponce +1
Establishing visual correspondences under large intra-class variations, which is often referred to as semantic correspondence or semantic matching, remains a challenging problem in…
Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features
Juhong Min, Jongmin Lee, Jean Ponce +1
Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local pattern…