517 citations · 880 across the 52 of their papers we have counts for
54 papers
Tempered Self-Similarity Alignment for Physically Plausible Video Generation
Manjin Kim, Suha Kwak, Minsu Cho
Despite remarkable advances in video generative models, they still struggle to generate physically realistic videos, frequently exhibiting appearance drift, implausible motion, and…
Robust Promptable Video Object Segmentation
Sohyun Lee, Yeho Gwon, Lukas Hoyer +3
The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in safety-critical domains. Thi…
RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation
Donghyeon Kwon, Taegyu Park, Suha Kwak
Semi-supervised learning for LiDAR semantic segmentation often suffers from error propagation and confirmation bias caused by noisy pseudo-labels. To tackle this chronic issue, we…
Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
Dongwon Kim, Gawon Seo, Jinsung Lee +2
World models provide a powerful framework for simulating environment dynamics conditioned on actions or instructions, enabling downstream tasks such as action planning or policy le…
Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection
Dongkeun Kim, Minsu Cho, Suha Kwak
Social interactions often emerge from subtle, fine-grained cues such as facial expressions, gaze, and gestures. However, existing methods for social interaction detection overlook…
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Dayoung Gong, Suha Kwak, Minsu Cho
Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos. Despite apparent relevance and potential…
Efficient and Versatile Robust Fine-Tuning of Zero-shot Models
Sungyeon Kim, Boseung Jeong, Donghyun Kim +1
Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in…
Online Temporal Action Localization with Memory-Augmented Transformer
Youngkil Song, Dongkeun Kim, Minsu Cho +1
Online temporal action localization (On-TAL) is the task of identifying multiple action instances given a streaming video. Since existing methods take as input only a video segment…
FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions
Sohyun Lee, Namyup Kim, Sungyeon Kim +1
Robust semantic segmentation under adverse conditions is crucial in real-world applications. To address this challenging task in practical scenarios where labeled normal condition…
Classification Matters: Improving Video Action Detection with Class-Specific Attention
Jinsung Lee, Taeoh Kim, Inwoong Lee +4
Video action detection (VAD) aims to detect actors and classify their actions in a video. We figure that VAD suffers more from classification rather than localization of actors. He…
Extreme Point Supervised Instance Segmentation
Hyeonjun Lee, Sehyun Hwang, Suha Kwak
This paper introduces a novel approach to learning instance segmentation using extreme points, i.e., the topmost, leftmost, bottommost, and rightmost points, of each object. These…
Active Label Correction for Semantic Segmentation with Foundation Models
Hoyoung Kim, Sehyun Hwang, Suha Kwak +1
Training and validating models for semantic segmentation require datasets with pixel-wise annotations, which are notoriously labor-intensive. Although useful priors such as foundat…
Activity Grammars for Temporal Action Segmentation
Dayoung Gong, Joonseok Lee, Deunsol Jung +2
Sequence prediction on temporal data requires the ability to understand compositional structures of multi-level semantics beyond individual and contextual properties. The task of t…
Towards More Practical Group Activity Detection: A New Benchmark and Model
Dongkeun Kim, Youngkil Song, Minsu Cho +1
Group activity detection (GAD) is the task of identifying members of each group and classifying the activity of the group at the same time in a video. While GAD has been studied re…
Active Learning for Semantic Segmentation with Multi-class Label Query
Sehyun Hwang, Sohyun Lee, Hoyoung Kim +3
This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions…
Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning
Sungyeon Kim, Donghyun Kim, Suha Kwak
A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve mu…
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
Junhyeong Cho, Gilhyun Nam, Sungyeon Kim +2
In a joint vision-language space, a text feature (e.g., from "a photo of a dog") could effectively represent its relevant image features (e.g., from dog photos). Also, a recent stu…
Shatter and Gather: Learning Referring Image Segmentation with Text Supervision
Dongwon Kim, Namyup Kim, Cuiling Lan +1
Referring image segmentation, the task of segmenting any arbitrary entities described in free-form texts, opens up a variety of vision applications. However, manual labeling of tra…
Human Pose Estimation in Extremely Low-Light Conditions
Sohyun Lee, Jaesung Rim, Boseung Jeong +5
We study human pose estimation in extremely low-light images. This task is challenging due to the difficulty of collecting real low-light images with accurate labels, and severely…
Adaptive Superpixel for Active Learning in Semantic Segmentation
Hoyoung Kim, Minhyeon Oh, Sehyun Hwang +2
Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learn…
Learning to Detect Semantic Boundaries with Image-level Class Labels
Namyup Kim, Sehyun Hwang, Suha Kwak
This paper presents the first attempt to learn semantic boundary detection using image-level class labels as supervision. Our method starts by estimating coarse areas of object cla…
HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization
Sungyeon Kim, Boseung Jeong, Suha Kwak
Supervision for metric learning has long been given in the form of equivalence between human-labeled classes. Although this type of supervision has been a basis of metric learning…
Cross-Domain Ensemble Distillation for Domain Generalization
Kyungmoon Lee, Sungyeon Kim, Suha Kwak
Domain generalization is the task of learning models that generalize to unseen target domains. We propose a simple yet effective method for domain generalization, named cross-domai…
Few-shot Metric Learning: Online Adaptation of Embedding for Retrieval
Deunsol Jung, Dahyun Kang, Suha Kwak +1
Metric learning aims to build a distance metric typically by learning an effective embedding function that maps similar objects into nearby points in its embedding space. Despite r…