Author name cluster

Jinjoo Song

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

EAAI Journal 2026 Journal Article

Scalable feed-forward and backward quantum image representation

Sunmin Kim
Gangjoon Yoon
Jinjoo Song
Sang Min Yoon

Quantum image processing, leveraging quantum coherence, entanglement, and superposition, enables computational tasks beyond classical approaches. However, current quantum image processing methods face challenges, including limited scalable positional encoding, poor bi-directional fidelity between classical and quantum domains, and difficulties in verification and reconstruction. In this work, we present a novel framework for quantum image representation based on stereographic projection and back-projection, which encodes positional information into quantum states while preserving the digital image’s geometric structure. Our method ensures precise and reversible mapping between digital and quantum representations and reduces circuit depth and time complexity compared to existing quantum image processing algorithms. Extensive evaluations using quantum simulators and quantum hardware validate the robustness, scalability, and computational efficiency of the proposed approach, marking a significant advancement toward practical quantum image processing.

Details DOI

EAAI Journal 2026 Journal Article

Self-representative multi-view deep subspace clustering with feature optimization and fusion

Jinjoo Song
Gang-Joon Yoon
Sangwon Baek
Sang Min Yoon

Subspace clustering approaches, including both single- and multi-view, aim to partition high-dimensional data into multiple low-dimensional subspaces. While deep learning-based subspace clustering methods have shown significant advantages over traditional ones, most existing approaches still rely on single-view architectures, which fail to fully utilize the heterogeneous and complementary nature of real-world data. To address this, we propose a self-representative multi-view subspace clustering framework that integrates a feature extraction encoder with feature boosting, view-specific constraints, and multi-view feature optimization. Our method extracts discriminative representations from all directional views of a tensor and fuses them to suppress redundancy while enhancing meaningful features for self-representation. Experimental results demonstrate the effectiveness of our approach, achieving clustering accuracies of up to 99. 72% across four standard benchmark datasets. On average, our method outperforms state-of-the-art single-view and multi-view subspace clustering methods by a margin of 2%–5%, validating its ability to capture both discriminative and complementary features for robust clustering performance.

Details DOI

EAAI Journal 2025 Journal Article

Visual object tracking using learnable target-aware token emphasis

Minho Park
Jinjoo Song
Sang Min Yoon

Visual object tracking, which involves tracking the spatial location of a target object either within a single viewpoint or across various camera perspectives, is an important task in computer vision. Deep neural networks, especially vision transformers, typically outperform traditional methods and have thus become the preferred choice for visual object tasks. However, existing visual object tracking frameworks still struggle to adapt to targets with continuously changing appearances within the current frame, as they rely heavily on the static initial target template rather than continuously emphasizing the evolving target features. In this paper, we introduce a visual object tracking network with a learnable target-aware token emphasis, which is composed of vision transformer backbone embedded in the token emphasizer, localization head and target template update decision module. The learnable target-aware token emphasizer and target template update decision modules in the proposed model contribute to stabilizing visual object tracking across various scenarios. This is achieved not only by emphasizing features that have a relationship between the target template and the search region but also by reducing irrelevant features and consistently updating the high-quality target template online during the process. Qualitative and quantitative analyses, including ablation analysis across a diverse set of tracking benchmark datasets, validate the robustness of the proposed tracking framework. The code and trained models are available at https: //github. com/qkdkralsgh/TETrack.

Details DOI

EAAI Journal 2024 Journal Article

Fusing bi-directional global–local features for single image super-resolution

Kyomin Hwang
Gangjoon Yoon
Jinjoo Song
Sang Min Yoon

Image super resolution, which obtains high resolution output from a corresponding low resolution image, has been challenging due to inefficiencies in establishing complex high dimensional mapping for massive raw data. Single image super resolution can dramatically improve performance compared with current algorithms due to the proliferation of deep learning systems. However, convolutional kernels in deep neural networks are locally connected to the input feature maps, whereas features only interact with their local neighbors. Mutual interference between local features without considering global features causes blurring and staircase effects. This paper proposes an end-to-end single image super resolution model by simultaneously separating high and low frequency features and learning adaptive local and global features to effectively reconstruct the high resolution image by minimizing the loss of edges and texture information. The image frequency decomposition module with an attention block emphasizes self-representative low frequency features to separate high and low frequency features. The bidirectional global and local feature exchange module extracts global and local features from the separated network and fuses each feature to improve performance. Quantitative and qualitative analyses for the proposed frequency adaptive network validated that the proposed method is stable and robust against blurring and staircase effects by separating texture and the structure into adaptive and shared networks.

Details DOI

EAAI Journal 2024 Journal Article

Unified spatio-temporal attention mixformer for visual object tracking

Minho Park
Gang-Joon Yoon
Jinjoo Song
Sang Min Yoon

In this paper, we present a unified spatio-temporal attention MixFormer framework for visual object tracking. Within the vision transformer framework, we design a cohesive network consisting of target template and search region feature extraction, cross-attention utilizing spatial and temporal information, and task-specific heads, all operating in an end-to-end manner. Incorporating spatial and temporal attention modules within the network enables simultaneous feature extraction and emphasis, allowing the model to concentrate on target-specific discriminative features despite changes in illumination, occlusion, scale, camera pose, and background clutter. Stacking multiple non-hierarchical blocks allows meaningful features to be extracted while irrelevant features are discarded from the provided target template and search region. The simultaneous spatio-temporal attention module is employed to accentuate target appearance features and alleviate variation in the object state across frame sequences. Qualitative and quantitative analysis, including ablation tests based on various tracking benchmarks, validates the robustness of the proposed tracking methodology.

Details DOI

EAAI Journal 2024 Journal Article

View synthesis with multiplane images from computationally generated RGB-D light fields

Gang-Joon Yoon
Geunho Jung
Jinjoo Song
Sang Min Yoon

Image based view synthesis using deep neural networks provide novel scene views from a set of captured single or multiple images. Multiplane images (MPI) represent scene content as set of RGB α planes within a reference view frustum and render novel views by projecting the content into the target viewpoints. Image based view synthesis with multiple images is very popularly deployed in various areas because it effectively represents geometric uncertainty in ambiguous regions and can convincingly simulate non-Lambertian effects. However, previous image based view synthesis approaches suffer from interpolating and extrapolating information in pixels or ray spaces to generate seamless novel views without occlusion. To effectively improve visual performance for view interpolation and extrapolation, this paper proposes a novel view synthesis with MPI images. From a monocular RGB image, light field images are computationally generated, the proposed depth map guided deep network produces robust MPI using the light field images and their corresponding depth images, and the MPI network embedded with depth attention blocks forces semantic and geometric information to be uniformly distributed and divided among layers. The proposed approach achieves 3. 5% and 4. 02% improvements in SSIM and PSNR values, comparing to the SOTA approaches. Qualitative analysis on benchmark dataset also verifies the robustness of the proposed approach.

Details DOI