Browsing Electronic Engineering and Computer Science by Author "Oh, C"
Now showing items 1-20 of 24
-
Boosting Video Object Segmentation Based on Scale Inconsistency
Wang, H; Oh, C (IEEE, 2022-01-01)We present a refinement framework to boost the performance of pre-trained semi-supervised video object segmentation (VOS) models. Our work is based on scale inconsistency, which is motivated by the observation that existing ... -
CLUSTER-BASED 3D KEYPOINT DETECTION FOR CATEGORY-AGNOSTIC 6D POSE TRACKING
Tian, L; Cavallaro, A; Oh, C (IEEE, 2022)We present a model for category-agnostic 6D pose tracking. We tackle object pose tracking as a 3D keypoint detection and matching task that does not require ground-truth annotation of the keypoints. Using RGB-D data and ... -
Deep network for simultaneous stereo matching and dehazing
Song, T; Kim, Y; Oh, C; Sohn, K (2019-01-01)© 2018. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. Unveiling the image structure and dense correspondence under the haze layer remains a ... -
Depth Analogy: Data-Driven Approach for Single Image Depth Estimation Using Gradient Samples
Choi, S; Min, D; Ham, B; Kim, Y; Oh, C; Sohn, K (Institute of Electrical and Electronics Engineers (IEEE), 2015-10-27) -
Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation
Kim, J; Oh, C; Do, H; Kim, S; Sohn, K; IEEE/CVF International Conference on Computer Vision and Pattern Recognition 2024We present a new multi-modal face image generation method that converts a text prompt and a visual input, such as a semantic mask or scribble map, into a photo-realistic face image. To do this, we combine the strengths ... -
EdgeFool: An Adversarial Image Enhancement Filter
Shahin, A; Oh, C; Cavallaro, A; International Conference on Acoustics, Speech, and Signal Processing (International Conference on Acoustics, Speech, and Signal Processing, 2020)Adversarial examples are intentionally perturbed images that mislead classifiers. These images can, however, be easily detected using denoising algorithms, when high-frequency spatial perturbations are used, or can be ... -
IMPROVING GENERALIZATION OF DEEP NETWORKS FOR ESTIMATING PHYSICAL PROPERTIES OF CONTAINERS AND FILLINGS
Wang, H; Zhu, C; Ma, Z; Oh, C (IEEE, 2022)We present methods to estimate the physical properties of house-hold containers and their fillings manipulated by humans. We use a lightweight, pre-trained convolutional neural network with coordinate attention as a backbone ... -
Improving image de-raining using reference-guided transformers
Ye, Z; Cho, J; Oh, C; IEEE International Conference on Image Processing -
Investigating Adversarial Policy Learning for Robust Agents in Automated Driving Highway Simulations
Pighetti, A; Bellotti, F; Oh, C; Lazzaroni, L; Forneris, L; Fresta, M; Berta, R; International Conference on Applications in Electronics Pervading Industry, Environment and Society -
Learning Action Representations for Self-supervised Visual Exploration
Oh, C; Cavallaro, A; IEEE (2019) -
Learning by Erasing: Conditional Entropy Based Transferable Out-of-Distribution Detection
Xing, M; Feng, Z; Su, Y; Oh, C; AAAI Conference on Artificial Intelligence 2024Detecting OOD inputs is crucial to deploy machine learning models to the real world safely. However, existing OOD detection methods require an in-distribution (ID) dataset to retrain the models. In this paper, we propose ... -
Multi-modal robotic visual-tactile localisation and detection of surface cracks
Palermo, F; Rincon-Ardila, L; Oh, C; Althoefer, K; Poslad, S; Venture, G; Farkhatdinov, I; 2021 IEEE 17th International Conference on Automation Science and Engineering (IEEE, 2021)We present and validate a method to detect surface cracks with visual and tactile sensing. The proposed algorithm localises cracks in remote environments through videos/photos taken by an on-board robot camera. The identified ... -
Neuromorphic Tactile Sensing System for Textural Features Classification
Ali, HAH; Abbass, Y; Gianoglio, C; Ibrahim, A; Oh, C; Valle, M (IEEE, 2024-04-04)Artificial tactile sensing systems have gained significant attention in recent years due to their potential to enhance human-machine interaction. Numerous initiatives have been introduced to shift the computational paradigms ... -
Non-parametric human segmentation using support vector machine
Kim, K; Oh, C; Sohn, K (Institute of Electrical and Electronics Engineers (IEEE), 2016-07-29) -
OHPL: One-shot Hand-eye Policy Learner
Oh, C; Pang, YL; Cavallaro, A (2021) -
Open-vocabulary object 6D pose estimation
Corsetti, J; Boscaini, D; Oh, C; Cavallaro, A; Poiesi, F; IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 (2024)We introduce the new setting of open-vocabulary object 6D pose estimation, in which a textual prompt is used to specify the object of interest. In contrast to existing approaches, in our setting (i) the object of interest ... -
Robust interactive image segmentation using structure-aware labeling
Oh, C; Ham, B; Sohn, K (Elsevier BV, 2017-02-27) -
Semantically Adversarial Learnable Filters
Shahin Shamsabadi, A; Oh, C; Cavallaro, A (Institute of Electrical and Electronics Engineers, 2021-09)We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and the semantics of the labels. The proposed framework combines a structure loss and a semantic ... -
Simultaneous Deep Stereo Matching and Dehazing with Feature Attention
Song, T; Kim, Y; Oh, C; Jang, H; Ha, N; Sohn, K (2020-04) -
Structure Selective Depth Superresolution for RGB-D Cameras
Kim, Y; Ham, B; Oh, C; Sohn, K (Institute of Electrical and Electronics Engineers (IEEE), 2016-08-18)