515 citations · 739 across the 33 of their papers we have counts for
18 papers · 1 filter
UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection
Bumsoo Kim, Taeho Choi, Jaewoo Kang +1
Recent advances in deep neural networks have achieved significant progress in detecting individual objects from an image. However, object detection is not sufficient to fully under…
Semantic-Aware Implicit Template Learning via Part Deformation Consistency
Sihyeon Kim, Minseok Joo, Jaewon Lee +3
Learning implicit templates as neural fields has recently shown impressive performance in unsupervised shape correspondence. Despite the success, we observe current approaches, whi…
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
Dohwan Ko, Joonmyung Choi, Hyeong Kyu Choi +3
Foundation models have shown outstanding performance and generalization capabilities across domains. Since most studies on foundation models mainly focus on the pretraining phase,…
Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wild
Jaewon Lee, Injae Kim, Hwan Heo +1
We present a learning framework for reconstructing neural scene representations from a small number of unconstrained tourist photos. Since each image contains transient occluders,…
VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression
Won Jo, Geuntaek Lim, Gwangjin Lee +3
In content-based video retrieval (CBVR), dealing with large-scale collections, efficiency is as important as accuracy; thus, several video-level feature-based studies have actively…
Domain Generalization Emerges from Dreaming
Hwan Heo, Youngjin Oh, Jaewon Lee +1
Recent studies have proven that DNNs, unlike human vision, tend to exploit texture information rather than shape. Such texture bias is one of the factors for the poor generalizatio…
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers
Hyeong Kyu Choi, Joonmyung Choi, Hyunwoo J. Kim
Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many salien…
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection
Jihwan Park, SeungJun Lee, Hwan Heo +2
Human-Object Interaction detection is a holistic visual recognition task that entails object detection as well as interaction classification. Previous works of HOI detection has be…
Perception Prioritized Training of Diffusion Models
Jooyoung Choi, Jungbeom Lee, Chaehun Shin +3
Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i.e., denoising sco…
Video-Text Representation Learning via Differentiable Weak Temporal Alignment
Dohwan Ko, Joonmyung Choi, Juyeon Ko +4
Learning generic joint representations for video and text by a supervised method requires a prohibitively substantial amount of manually annotated video datasets. As a practical al…
VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
Su Ho Han, Sukjun Hwang, Seoung Wug Oh +4
For online video instance segmentation (VIS), fully utilizing the information from previous frames in an efficient manner is essential for real-time applications. Most previous met…
Point Cloud Augmentation with Weighted Local Transformations
Sihyeon Kim, Sanghyeok Lee, Dasol Hwang +3
Despite the extensive usage of point clouds in 3D vision, relatively limited data are available for training deep neural networks. Although data augmentation is a standard approach…
HOTR: End-to-End Human-Object Interaction Detection with Transformers
Bumsoo Kim, Junhyun Lee, Jaewoo Kang +2
Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (…
Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring
Sam Sattarzadeh, Mahesh Sudhakar, Konstantinos N. Plataniotis +3
Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image…
Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks
Mahesh Sudhakar, Sam Sattarzadeh, Konstantinos N. Plataniotis +3
Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturba…
Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods
Byungjoo Kim, Bryce Chudomelka, Jinyoung Park +3
Deep neural networks have achieved state-of-the-art performance in a variety of fields. Recent works observe that a class of widely used neural networks can be viewed as the Euler…
Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation
Sam Sattarzadeh, Mahesh Sudhakar, Anthony Lem +7
As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs).…
Unpaired Image Translation via Adaptive Convolution-based Normalization
Wonwoong Cho, Kangyeol Kim, Eungyeup Kim +2
Disentangling content and style information of an image has played an important role in recent success in image translation. In this setting, how to inject given style into an inpu…