Junsik Kim

Arda Senocak, Hyeonggon Ryu, Junsik Kim et al.

Humans can easily perceive the direction of sound sources in a visual scene, termed sound source localization. Recent studies on learning-based sound source localization have mainly explored the problem from a localization perspective. However, prior arts and existing benchmarks do not account for a more important aspect of the problem, cross-modal semantic understanding, which is essential for genuine sound source localization. Cross-modal semantic understanding is important in understanding semantically mismatched audio-visual events, e.g., silent objects, or off-screen sounds. To account for this, we propose a cross-modal alignment task as a joint task with sound source localization to better learn the interaction between audio and visual modalities. Thereby, we achieve high localization performance with strong cross-modal semantic understanding. Our method outperforms the state-of-the-art approaches in both sound source localization and cross-modal retrieval. Our work suggests that jointly tackling both tasks is necessary to conquer genuine sound source localization.

Minkyung Kim, Jongmin Yu, Junsik Kim et al.

Most deep anomaly detection models are based on learning normality from datasets due to the difficulty of defining abnormality by its diverse and inconsistent nature. Therefore, it has been a common practice to learn normality under the assumption that anomalous data are absent in a training dataset, which we call normality assumption. However, in practice, the normality assumption is often violated due to the nature of real data distributions that includes anomalous tails, i.e., a contaminated dataset. Thereby, the gap between the assumption and actual training data affects detrimentally in learning of an anomaly detection model. In this work, we propose a learning framework to reduce this gap and achieve better normality representation. Our key idea is to identify sample-wise normality and utilize it as an importance weight, which is updated iteratively during the training. Our framework is designed to be model-agnostic and hyperparameter insensitive so that it applies to a wide range of existing methods without careful parameter tuning. We apply our framework to three different representative approaches of deep anomaly detection that are classified into one-class classification-, probabilistic model-, and reconstruction-based approaches. In addition, we address the importance of a termination condition for iterative methods and propose a termination criterion inspired by the anomaly detection objective. We validate that our framework improves the robustness of the anomaly detection models under different levels of contamination ratios on five anomaly detection benchmark datasets and two image datasets. On various contaminated datasets, our framework improves the performance of three representative anomaly detection methods, measured by area under the ROC curve.

Fei Pan, Francois Rameau, Junsik Kim et al.

Training models dedicated to semantic segmentation requires a large amount of pixel-wise annotated data. Due to their costly nature, these annotations might not be available for the task at hand. To alleviate this problem, unsupervised domain adaptation approaches aim at aligning the feature distributions between the labeled source and the unlabeled target data. While these strategies lead to noticeable improvements, their effectiveness remains limited. To guide the domain adaptation task more efficiently, previous works attempted to include human interactions in this process under the form of sparse single-pixel annotations in the target data. In this work, we propose a new domain adaptation framework for semantic segmentation with annotated points via active selection. First, we conduct an unsupervised domain adaptation of the model; from this adaptation, we use an entropy-based uncertainty measurement for target points selection. Finally, to minimize the domain gap, we propose a domain adaptation framework utilizing these target points annotated by human annotators. Experimental results on benchmark datasets show the effectiveness of our methods against existing unsupervised domain adaptation approaches. The propose pipeline is generic and can be included as an extra module to existing domain adaptation strategies.

Moon Ye-Bin, Dongmin Choi, Yongjin Kwon et al.

We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Since it is an under-explored problem, we first investigate the difficulty of the problem and identify the performance bottleneck by conducting systematic analyses of model components and individual sub-tasks with a simple baseline model. Based on the analyses, we propose ENInst with sub-task enhancement methods: instance-wise mask refinement for enhancing pixel localization quality and novel classifier composition for improving classification accuracy. Our proposed method lifts the overall performance by enhancing the performance of each sub-task. We demonstrate that our ENInst is 7.5 times more efficient in achieving comparable performance to the existing fully-supervised few-shot models and even outperforms them at times.

Fei Pan, Sungsu Hur, Seokju Lee et al.

Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous subdomains. The goal of OCDA is to minimize the domain gap between the labeled source domain and the unlabeled compound target domain, which benefits the model generalization to the unseen domains. Current OCDA for semantic segmentation methods adopt manual domain separation and employ a single model to simultaneously adapt to all the target subdomains. However, adapting to a target subdomain might hinder the model from adapting to other dissimilar target subdomains, which leads to limited performance. In this work, we introduce a multi-teacher framework with bidirectional photometric mixing to separately adapt to every target subdomain. First, we present an automatic domain separation to find the optimal number of subdomains. On this basis, we propose a multi-teacher framework in which each teacher model uses bidirectional photometric mixing to adapt to one target subdomain. Furthermore, we conduct an adaptive distillation to learn a student model and apply consistency regularization to improve the student generalization. Experimental results on benchmark datasets show the efficacy of the proposed approach for both the compound domain and the open domains against existing state-of-the-art approaches.

Yongjin Jeon, Youngtack Oh, Doyoung Jeong et al.

In recent years, monitoring the world wide area with satellite images has been emerged as an important issue. Site monitoring task can be divided into two independent tasks; 1) Change Detection and 2) Anomaly Event Detection. Unlike to change detection research is actively conducted based on the numerous datasets(\eg LEVIR-CD, WHU-CD, S2Looking, xView2 and etc...) to meet up the expectations of industries or governments, research on AI models for detecting anomaly events is passively and rarely conducted. In this paper, we introduce a novel satellite imagery dataset(AED-RS) for detecting anomaly events on the open public places. AED-RS Dataset contains satellite images of normal and abnormal situations of 8 open public places from all over the world. Each places are labeled with different criteria based on the difference of characteristics of each places. With this dataset, we introduce a baseline model for our dataset TB-FLOW, which can be trained in weakly-supervised manner and shows reasonable performance on the AED-RS Dataset compared with the other NF(Normalizing-Flow) based anomaly detection models. Our dataset and code will be publicly open in \url{https://github.com/SIAnalytics/RS_AnomalyDetection.git}.

Dawit Mureja Argaw, Junsik Kim, In So Kweon

Existing video compression (VC) methods primarily aim to reduce the spatial and temporal redundancies between consecutive frames in a video while preserving its quality. In this regard, previous works have achieved remarkable results on videos acquired under specific settings such as instant (known) exposure time and shutter speed which often result in sharp videos. However, when these methods are evaluated on videos captured under different temporal priors, which lead to degradations like motion blur and low frame rate, they fail to maintain the quality of the contents. In this work, we tackle the VC problem in a general scenario where a given video can be blurry due to predefined camera settings or dynamics in the scene. By exploiting the natural trade-off between visual enhancement and data compression, we formulate VC as a min-max optimization problem and propose an effective framework and training strategy to tackle the problem. Extensive experimental results on several benchmark datasets confirm the effectiveness of our method compared to several state-of-the-art VC approaches.

Minkyung Kim, Junsik Kim, Jongmin Yu et al.

Active learning has been utilized as an efficient tool in building anomaly detection models by leveraging expert feedback. In an active learning framework, a model queries samples to be labeled by experts and re-trains the model with the labeled data samples. It unburdens in obtaining annotated datasets while improving anomaly detection performance. However, most of the existing studies focus on helping experts identify as many abnormal data samples as possible, which is a sub-optimal approach for one-class classification-based deep anomaly detection. In this paper, we tackle two essential problems of active learning for Deep SVDD: query strategy and semi-supervised learning method. First, rather than solely identifying anomalies, our query strategy selects uncertain samples according to an adaptive boundary. Second, we apply noise contrastive estimation in training a one-class classification model to incorporate both labeled normal and abnormal data effectively. We analyze that the proposed query strategy and semi-supervised loss individually improve an active learning process of anomaly detection and further improve when combined together on seven anomaly detection datasets.

Arda Senocak, Hyeonggon Ryu, Junsik Kim et al.

Recent studies on learning-based sound source localization have mainly focused on the localization performance perspective. However, prior work and existing benchmarks overlook a crucial aspect: cross-modal interaction, which is essential for interactive sound source localization. Cross-modal interaction is vital for understanding semantically matched or mismatched audio-visual events, such as silent objects or off-screen sounds. In this paper, we first comprehensively examine the cross-modal interaction of existing methods, benchmarks, evaluation metrics, and cross-modal understanding tasks. Then, we identify the limitations of previous studies and make several contributions to overcome the limitations. First, we introduce a new synthetic benchmark for interactive sound source localization. Second, we introduce new evaluation metrics to rigorously assess sound source localization methods, focusing on accurately evaluating both localization performance and cross-modal interaction ability. Third, we propose a learning framework with a cross-modal alignment strategy to enhance cross-modal interaction. Lastly, we evaluate both interactive sound source localization and auxiliary cross-modal retrieval tasks together to thoroughly assess cross-modal interaction capabilities and benchmark competing methods. Our new benchmarks and evaluation metrics reveal previously overlooked issues in sound source localization studies. Our proposed novel method, with enhanced cross-modal alignment, shows superior sound source localization performance. This work provides the most comprehensive analysis of sound source localization to date, with extensive validation of competing methods on both existing and new benchmarks using new and standard evaluation metrics.

Zhiyi Shi, Junsik Kim, Wanhua Li et al.

Multi-modal pre-trained models efficiently extract and fuse features from different modalities with low memory requirements for fine-tuning. Despite this efficiency, their application in disease diagnosis is under-explored. A significant challenge is the frequent occurrence of missing modalities, which impairs performance. Additionally, fine-tuning the entire pre-trained model demands substantial computational resources. To address these issues, we introduce Modality-aware Low-Rank Adaptation (MoRA), a computationally efficient method. MoRA projects each input to a low intrinsic dimension but uses different modality-aware up-projections for modality-specific adaptation in cases of missing modalities. Practically, MoRA integrates into the first block of the model, significantly improving performance when a modality is missing. It requires minimal computational resources, with less than 1.6% of the trainable parameters needed compared to training the entire model. Experimental results show that MoRA outperforms existing techniques in disease diagnosis, demonstrating superior performance, robustness, and training efficiency.

Ye Liu, Jixuan He, Wanhua Li et al.

Video temporal grounding (VTG) is a fine-grained video understanding problem that aims to ground relevant clips in untrimmed videos given natural language queries. Most existing VTG models are built upon frame-wise final-layer CLIP features, aided by additional temporal backbones (e.g., SlowFast) with sophisticated temporal reasoning mechanisms. In this work, we claim that CLIP itself already shows great potential for fine-grained spatial-temporal modeling, as each layer offers distinct yet useful information under different granularity levels. Motivated by this, we propose Reversed Recurrent Tuning ($R^2$-Tuning), a parameter- and memory-efficient transfer learning framework for video temporal grounding. Our method learns a lightweight $R^2$ Block containing only 1.5% of the total parameters to perform progressive spatial-temporal modeling. Starting from the last layer of CLIP, $R^2$ Block recurrently aggregates spatial features from earlier layers, then refines temporal correlation conditioning on the given query, resulting in a coarse-to-fine scheme. $R^2$-Tuning achieves state-of-the-art performance across three VTG tasks (i.e., moment retrieval, highlight detection, and video summarization) on six public benchmarks (i.e., QVHighlights, Charades-STA, Ego4D-NLQ, TACoS, YouTube Highlights, and TVSum) even without the additional backbone, demonstrating the significance and effectiveness of the proposed scheme. Our code is available at https://github.com/yeliudev/R2-Tuning.

Minkyung Kim, Junsik Kim, Jongmin Yu et al.

One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available. In practice, however, abnormal samples are often mixed in a training dataset, and they detrimentally affect the training of deep models, which limits their applicability. For robust normality learning of deep practical models, we propose an unsupervised deep one-class classification that learns normality from pseudo-labeled normal samples, i.e., outlier detection in single cluster scenarios. To this end, we propose a pseudo-labeling method by an adaptive threshold selected by ranking-based training dynamics. The experiments on 10 anomaly detection benchmarks show that our method effectively improves performance on anomaly detection by sizable margins.

Jixuan He, Wanhua Li, Ye Liu et al.

As a common image editing operation, image composition involves integrating foreground objects into background scenes. In this paper, we expand the application of the concept of Affordance from human-centered image composition tasks to a more general object-scene composition framework, addressing the complex interplay between foreground objects and background scenes. Following the principle of Affordance, we define the affordance-aware object insertion task, which aims to seamlessly insert any object into any scene with various position prompts. To address the limited data issue and incorporate this task, we constructed the SAM-FB dataset, which contains over 3 million examples across more than 3,000 object categories. Furthermore, we propose the Mask-Aware Dual Diffusion (MADD) model, which utilizes a dual-stream architecture to simultaneously denoise the RGB image and the insertion mask. By explicitly modeling the insertion mask in the diffusion process, MADD effectively facilitates the notion of affordance. Extensive experimental results show that our method outperforms the state-of-the-art methods and exhibits strong generalization performance on in-the-wild images. Please refer to our code on https://github.com/KaKituken/affordance-aware-any.

Miao Zhang, Junsik Kim, Siyuan Xiang et al.

Multi-agent large language model (LLM) and vision-language model (VLM) debate systems employ specialized roles for complex problem-solving, yet model specializations are not leveraged to decide which model should fill which role. We propose dynamic role assignment, a framework that runs a Meta-Debate to select suitable agents before the actual debate. The meta-debate has two stages: (1) proposal, where candidates provide role-tailored arguments, and (2) peer review, where proposals are scored with data and role-specific criteria to choose the best agent for each position. We evaluate our method on LLM problem solving benchmarks. Applied on top of existing debate systems, our approach consistently outperforms uniform assignments (filling all roles with the same model) by up to 74.8% and random assignments (assigning models to roles without considering their suitability) by up to 29.7%, depending on the task and the specific assignment. This work establishes a new paradigm for multi-agent system design, shifting from static agent deployment to dynamic and capability-aware selection.

Zhiyi Shi, Binjie Wang, Chongjie Si et al.

Model editing aims to efficiently update a pre-trained model's knowledge without the need for time-consuming full retraining. While existing pioneering editing methods achieve promising results, they primarily focus on editing single-modal language models (LLMs). However, for vision-language models (VLMs), which involve multiple modalities, the role and impact of each modality on editing performance remain largely unexplored. To address this gap, we explore the impact of textual and visual modalities on model editing and find that: (1) textual and visual representations reach peak sensitivity at different layers, reflecting their varying importance; and (2) editing both modalities can efficiently update knowledge, but this comes at the cost of compromising the model's original capabilities. Based on our findings, we propose DualEdit, an editor that modifies both textual and visual modalities at their respective key layers. Additionally, we introduce a gating module within the more sensitive textual modality, allowing DualEdit to efficiently update new knowledge while preserving the model's original information. We evaluate DualEdit across multiple VLM backbones and benchmark datasets, demonstrating its superiority over state-of-the-art VLM editing baselines as well as adapted LLM editing methods on different evaluation metrics. Codes are available at https://github.com/zhiyiscs/DualEdit

Jongmin Yu, Hyeontaek Oh, Minkyung Kim et al.

In this paper, we propose Normality-Calibrated Autoencoder (NCAE), which can boost anomaly detection performance on the contaminated datasets without any prior information or explicit abnormal samples in the training phase. The NCAE adversarially generates high confident normal samples from a latent space having low entropy and leverages them to predict abnormal samples in a training dataset. NCAE is trained to minimise reconstruction errors in uncontaminated samples and maximise reconstruction errors in contaminated samples. The experimental results demonstrate that our method outperforms shallow, hybrid, and deep methods for unsupervised anomaly detection and achieves comparable performance compared with semi-supervised methods using labelled anomaly samples in the training phase. The source code is publicly available on `https://github.com/andreYoo/NCAE_UAD.git'.

Jongmin Yu, Junsik Kim, Minkyung Kim et al.

Recently, vehicle re-identification methods based on deep learning constitute remarkable achievement. However, this achievement requires large-scale and well-annotated datasets. In constructing the dataset, assigning globally available identities (Ids) to vehicles captured from a great number of cameras is labour-intensive, because it needs to consider their subtle appearance differences or viewpoint variations. In this paper, we propose camera-tracklet-aware contrastive learning (CTACL) using the multi-camera tracklet information without vehicle identity labels. The proposed CTACL divides an unlabelled domain, i.e., entire vehicle images, into multiple camera-level subdomains and conducts contrastive learning within and beyond the subdomains. The positive and negative samples for contrastive learning are defined using tracklet Ids of each camera. Additionally, the domain adaptation across camera networks is introduced to improve the generalisation performance of learnt representations and alleviate the performance degradation resulted from the domain gap between the subdomains. We demonstrate the effectiveness of our approach on video-based and image-based vehicle Re-ID datasets. Experimental results show that the proposed method outperforms the recent state-of-the-art unsupervised vehicle Re-ID methods. The source code for this paper is publicly available on `https://github.com/andreYoo/CTAM-CTACL-VVReID.git'.

Kento Nishi, Junsik Kim, Wanhua Li et al.

Multi-task learning has become increasingly popular in the machine learning field, but its practicality is hindered by the need for large, labeled datasets. Most multi-task learning methods depend on fully labeled datasets wherein each input example is accompanied by ground-truth labels for all target tasks. Unfortunately, curating such datasets can be prohibitively expensive and impractical, especially for dense prediction tasks which require per-pixel labels for each image. With this in mind, we propose Joint-Task Regularization (JTR), an intuitive technique which leverages cross-task relations to simultaneously regularize all tasks in a single joint-task latent space to improve learning when data is not fully labeled for all tasks. JTR stands out from existing approaches in that it regularizes all tasks jointly rather than separately in pairs -- therefore, it achieves linear complexity relative to the number of tasks while previous methods scale quadratically. To demonstrate the validity of our approach, we extensively benchmark our method across a wide variety of partially labeled scenarios based on NYU-v2, Cityscapes, and Taskonomy.

Junsik Kim, Zhiyi Shi, Davin Jeong et al.

In clinical In-Vitro Fertilization (IVF), identifying the most viable embryo for transfer is important to increasing the likelihood of a successful pregnancy. Traditionally, this process involves embryologists manually assessing embryos' static morphological features at specific intervals using light microscopy. This manual evaluation is not only time-intensive and costly, due to the need for expert analysis, but also inherently subjective, leading to variability in the selection process. To address these challenges, we develop a multimodal model that leverages both time-lapse video data and Electronic Health Records (EHRs) to predict embryo viability. One of the primary challenges of our research is to effectively combine time-lapse video and EHR data, owing to their inherent differences in modality. We comprehensively analyze our multimodal model with various modality inputs and integration approaches. Our approach will enable fast and automated embryo viability predictions in scale for clinical IVF.

Taesoo Kim, HyungSeok Han, Soyeon Park et al.

We present ATLANTIS, the cyber reasoning system developed by Team Atlanta that won 1st place in the Final Competition of DARPA's AI Cyber Challenge (AIxCC) at DEF CON 33 (August 2025). AIxCC (2023-2025) challenged teams to build autonomous cyber reasoning systems capable of discovering and patching vulnerabilities at the speed and scale of modern software. ATLANTIS integrates large language models (LLMs) with program analysis -- combining symbolic execution, directed fuzzing, and static analysis -- to address limitations in automated vulnerability discovery and program repair. Developed by researchers at Georgia Institute of Technology, Samsung Research, KAIST, and POSTECH, the system addresses core challenges: scaling across diverse codebases from C to Java, achieving high precision while maintaining broad coverage, and producing semantically correct patches that preserve intended behavior. We detail the design philosophy, architectural decisions, and implementation strategies behind ATLANTIS, share lessons learned from pushing the boundaries of automated security when program analysis meets modern AI, and release artifacts to support reproducibility and future research.

Zhiyi Shi, Junsik Kim, Helen Y. Yang et al.

Automating embryo viability prediction for in vitro fertilization (IVF) is important but challenging due to the limited availability of labeled pregnancy outcome data, as only a small fraction of embryos are labeled after transfer. Self-supervised learning (SSL) can leverage both labeled and unlabeled data to improve prediction. However, existing SSL methods for videos are not directly applicable to embryo development videos due to two challenges: (1) embryo time-lapse videos contain hundreds of frames, requiring significant GPU memory for conventional SSL; (2) the dataset contains videos with varying lengths and many outlier frames, causing traditional video alignment methods to struggle with semantic misalignment. We propose Spatial-Temporal Pre-Training (STPT) to address these challenges. STPT includes two stages: spatial and temporal. In each stage, only one encoder is trained while the other is frozen, reducing memory demands. To handle temporal misalignment, STPT avoids frame-by-frame alignment across videos. The spatial stage learns from alignments within each video and its temporally consistent augmentations. The temporal stage then models relationships between video embeddings. Our method efficiently handles long videos and temporal variability. On 23,027 time-lapse videos (3,286 labeled), STPT achieves the highest AUC of 0.635 (95% CI: 0.632-0.638) compared to baselines, with limited computational resources.

Junsik Kim, Gun Bang, Soowoong Kim

Hierarchical LiDAR geometry compression encodes voxel occupancies from low to high bit-depths, yet prior methods treat each depth independently and re-estimate local context from coordinates at every level, limiting compression efficiency. We present ELiC, a real-time framework that combines cross-bit-depth feature propagation, a Bag-of-Encoders (BoE) selection scheme, and a Morton-order-preserving hierarchy. Cross-bit-depth propagation reuses features extracted at denser, lower depths to support prediction at sparser, higher depths. BoE selects, per depth, the most suitable coding network from a small pool, adapting capacity to observed occupancy statistics without training a separate model for each level. The Morton hierarchy maintains global Z-order across depth transitions, eliminating per-level sorting and reducing latency. Together these components improve entropy modeling and computation efficiency, yielding state-of-the-art compression at real-time throughput on Ford and SemanticKITTI. Code and models will be released upon publication.

Minkyung Kim, Junsik Kim, Woongcheol Yang et al.

Large Language Models (LLMs) enable dynamic game interactions but fail to follow essential procedural flows in rule-governed trading systems, eroding player trust. This work resolves the core tension between the creative flexibility of LLMs and the procedural demands of in-game trading (browse-offer-review-confirm). To this end, Autoregressive State-Tracking Prompting (ASTP) is introduced, a methodology centered on a strategically orchestrated prompt that compels an LLM to make its state-tracking process explicit and verifiable. Instead of relying on implicit contextual understanding, ASTP tasks the LLM with identifying and reporting a predefined state label from the previous turn. To ensure transactional integrity, this is complemented by a state-specific placeholder post-processing method for accurate price calculations. Evaluation across 300 trading dialogues demonstrates >99% state compliance and 99.3% calculation precision. Notably, ASTP with placeholder post-processing on smaller models (Gemini-2.5-Flash) matches larger models' (Gemini-2.5-Pro) performance while reducing response time from 21.2s to 2.4s, establishing a practical foundation that satisfies both real-time requirements and resource constraints of commercial games.

Hyun-Jic Oh, Junsik Kim, Zhiyi Shi et al.

Multiplex imaging is revolutionizing pathology by enabling the simultaneous visualization of multiple biomarkers within tissue samples, providing molecular-level insights that traditional hematoxylin and eosin (H&E) staining cannot provide. However, the complexity and cost of multiplex data acquisition have hindered its widespread adoption. Additionally, most existing large repositories of H&E images lack corresponding multiplex images, limiting opportunities for multimodal analysis. To address these challenges, we leverage recent advances in latent diffusion models (LDMs), which excel at modeling complex data distributions by utilizing their powerful priors for fine-tuning to a target domain. In this paper, we introduce a novel framework for virtual multiplex staining that utilizes pretrained LDM parameters to generate multiplex images from H&E images using a conditional diffusion model. Our approach enables marker-by-marker generation by conditioning the diffusion model on each marker, while sharing the same architecture across all markers. To tackle the challenge of varying pixel value distributions across different marker stains and to improve inference speed, we fine-tune the model for single-step sampling, enhancing both color contrast fidelity and inference efficiency through pixel-level loss functions. We validate our framework on two publicly available datasets, notably demonstrating its effectiveness in generating up to 18 different marker types with improved accuracy, a substantial increase over the 2-3 marker types achieved in previous approaches. This validation highlights the potential of our framework, pioneering virtual multiplex staining. Finally, this paper bridges the gap between H&E and multiplex imaging, potentially enabling retrospective studies and large-scale analyses of existing H&E image repositories.

Minkyung Kim, Junsik Kim, Hwidong Bae et al.

Large Language Models enable dynamic game interactions but struggle with rule-governed trading systems. Current implementations suffer from rule violations, such as item hallucinations and calculation errors, that erode player trust. Here, State-Inference-Based Prompting (SIBP) enables reliable trading through autonomous dialogue state inference and context-specific rule adherence. The approach decomposes trading into six states within a unified prompt framework, implementing context-aware item referencing and placeholder-based price calculations. Evaluation across 100 trading dialogues demonstrates >97% state compliance, >95% referencing accuracy, and 99.7% calculation precision. SIBP maintains computational efficiency while outperforming baseline approaches, establishing a practical foundation for trustworthy NPC interactions in commercial games.

Junsik Kim, Jinwook Park, Kangil Kim

In knowledge graph embedding, leveraging relation specific entity transformation has markedly enhanced performance. However, the consistency of embedding differences before and after transformation remains unaddressed, risking the loss of valuable inductive bias inherent in the embeddings. This inconsistency stems from two problems. First, transformation representations are specified for relations in a disconnected manner, allowing dissimilar transformations and corresponding entity embeddings for similar relations. Second, a generalized plug-in approach as a SFBR (Semantic Filter Based on Relations) disrupts this consistency through excessive concentration of entity embeddings under entity-based regularization, generating indistinguishable score distributions among relations. In this paper, we introduce a plug-in KGE method, Relation-Semantics Consistent Filter (RSCF). Its entity transformation has three features for enhancing semantic consistency: 1) shared affine transformation of relation embeddings across all relations, 2) rooted entity transformation that adds an entity embedding to its change represented by the transformed vector, and 3) normalization of the change to prevent scale reduction. To amplify the advantages of consistency that preserve semantics on embeddings, RSCF adds relation transformation and prediction modules for enhancing the semantics. In knowledge graph completion tasks with distance-based and tensor decomposition models, RSCF significantly outperforms state-of-the-art KGE methods, showing robustness across all relations and their frequencies.

Arda Senocak, Junsik Kim, Tae-Hyun Oh et al.

Human brain is continuously inundated with the multisensory information and their complex interactions coming from the outside world at any given moment. Such information is automatically analyzed by binding or segregating in our brain. While this task might seem effortless for human brains, it is extremely challenging to build a machine that can perform similar tasks since complex interactions cannot be dealt with single type of integration but requires more sophisticated approaches. In this paper, we propose a new model to address the multisensory integration problem with individual event-specific layers in a multi-task learning scheme. Unlike previous works where single type of fusion is used, we design event-specific layers to deal with different audio-visual relationship tasks, enabling different ways of audio-visual formation. Experimental results show that our event-specific layers can discover unique properties of the audio-visual relationships in the videos. Moreover, although our network is formulated with single labels, it can output additional true multi-labels to represent the given videos. We demonstrate that our proposed framework also exposes the modality bias of the video data category-wise and dataset-wise manner in popular benchmark datasets.

Arda Senocak, Hyeonggon Ryu, Junsik Kim et al.

The objective of this work is to localize the sound sources in visual scenes. Existing audio-visual works employ contrastive learning by assigning corresponding audio-visual pairs from the same source as positives while randomly mismatched pairs as negatives. However, these negative pairs may contain semantically matched audio-visual information. Thus, these semantically correlated pairs, "hard positives", are mistakenly grouped as negatives. Our key contribution is showing that hard positives can give similar response maps to the corresponding pairs. Our approach incorporates these hard positives by adding their response maps into a contrastive learning objective directly. We demonstrate the effectiveness of our approach on VGG-SS and SoundNet-Flickr test sets, showing favorable performance to the state-of-the-art methods.

Dawit Mureja Argaw, Junsik Kim, Francois Rameau et al.

We propose a novel framework to generate clean video frames from a single motion-blurred image. While a broad range of literature focuses on recovering a single image from a blurred image, in this work, we tackle a more challenging task i.e. video restoration from a blurred image. We formulate video restoration from a single blurred image as an inverse problem by setting clean image sequence and their respective motion as latent factors, and the blurred image as an observation. Our framework is based on an encoder-decoder structure with spatial transformer network modules to restore a video sequence and its underlying motion in an end-to-end manner. We design a loss function and regularizers with complementary properties to stabilize the training and analyze variant models of the proposed network. The effectiveness and transferability of our network are highlighted through a large set of experiments on two different types of datasets: camera rotation blurs generated from panorama scenes and dynamic motion blurs in high speed videos.

Dawit Mureja Argaw, Junsik Kim, Francois Rameau et al.

In most of computer vision applications, motion blur is regarded as an undesirable artifact. However, it has been shown that motion blur in an image may have practical interests in fundamental computer vision problems. In this work, we propose a novel framework to estimate optical flow from a single motion-blurred image in an end-to-end manner. We design our network with transformer networks to learn globally and locally varying motions from encoded features of a motion-blurred input, and decode left and right frame features without explicit frame supervision. A flow estimator network is then used to estimate optical flow from the decoded features in a coarse-to-fine manner. We qualitatively and quantitatively evaluate our model through a large set of experiments on synthetic and real motion-blur datasets. We also provide in-depth analysis of our model in connection with related approaches to highlight the effectiveness and favorability of our approach. Furthermore, we showcase the applicability of the flow estimated by our method on deblurring and moving object segmentation tasks.

Dawit Mureja Argaw, Junsik Kim, Francois Rameau et al.

Abrupt motion of camera or objects in a scene result in a blurry video, and therefore recovering high quality video requires two types of enhancements: visual enhancement and temporal upsampling. A broad range of research attempted to recover clean frames from blurred image sequences or temporally upsample frames by interpolation, yet there are very limited studies handling both problems jointly. In this work, we present a novel framework for deblurring, interpolating and extrapolating sharp frames from a motion-blurred video in an end-to-end manner. We design our framework by first learning the pixel-level motion that caused the blur from the given inputs via optical flow estimation and then predict multiple clean frames by warping the decoded features with the estimated flows. To ensure temporal coherence across predicted frames and address potential temporal ambiguity, we propose a simple, yet effective flow-based rule. The effectiveness and favorability of our approach are highlighted through extensive qualitative and quantitative evaluations on motion-blurred datasets from high speed videos.

Chaoning Zhang, Philipp Benz, Dawit Mureja Argaw et al.

ResNet or DenseNet? Nowadays, most deep learning based approaches are implemented with seminal backbone networks, among them the two arguably most famous ones are ResNet and DenseNet. Despite their competitive performance and overwhelming popularity, inherent drawbacks exist for both of them. For ResNet, the identity shortcut that stabilizes training also limits its representation capacity, while DenseNet has a higher capacity with multi-layer feature concatenation. However, the dense concatenation causes a new problem of requiring high GPU memory and more training time. Partially due to this, it is not a trivial choice between ResNet and DenseNet. This paper provides a unified perspective of dense summation to analyze them, which facilitates a better understanding of their core difference. We further propose dense weighted normalized shortcuts as a solution to the dilemma between them. Our proposed dense shortcut inherits the design philosophy of simple design in ResNet and DenseNet. On several benchmark datasets, the experimental results show that the proposed DSNet achieves significantly better results than ResNet, and achieves comparable performance as DenseNet but requiring fewer computation resources.

Arda Senocak, Tae-Hyun Oh, Junsik Kim et al.

Visual events are usually accompanied by sounds in our daily lives. However, can the machines learn to correlate the visual scene and sound, as well as localize the sound source only by observing them like humans? To investigate its empirical learnability, in this work we first present a novel unsupervised algorithm to address the problem of localizing sound sources in visual scenes. In order to achieve this goal, a two-stream network structure which handles each modality with attention mechanism is developed for sound source localization. The network naturally reveals the localized response in the scene without human annotation. In addition, a new sound source dataset is developed for performance evaluation. Nevertheless, our empirical evaluation shows that the unsupervised method generates false conclusions in some cases. Thereby, we show that this false conclusion cannot be fixed without human prior knowledge due to the well-known correlation and causality mismatch misconception. To fix this issue, we extend our network to the supervised and semi-supervised network settings via a simple modification due to the general architecture of our two-stream network. We show that the false conclusions can be effectively corrected even with a small amount of supervision, i.e., semi-supervised setup. Furthermore, we present the versatility of the learned audio and visual embeddings on the cross-modal content alignment and we extend this proposed algorithm to a new application, sound saliency based automatic camera view panning in 360-degree° videos.

Seokju Lee, Junsik Kim, Tae-Hyun Oh et al.

Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for free. In this work, we leverage the large-scale unlabeled yet naturally paired data for visual representation learning in the driving scenario. A representation is learned in an end-to-end self-supervised framework for predicting dense optical flow from a single frame with paired sensing data. We postulate that success on this task requires the network to learn semantic and geometric knowledge in the ego-centric view. For example, forecasting a future view to be seen from a moving vehicle requires an understanding of scene depth, scale, and movement of objects. We demonstrate that our learned representation can benefit other tasks that require detailed scene understanding and outperforms competing unsupervised representations on semantic segmentation.

Junsik Kim, Tae-Hyun Oh, Seokju Lee et al.

In daily life, graphic symbols, such as traffic signs and brand logos, are ubiquitously utilized around us due to its intuitive expression beyond language boundary. We tackle an open-set graphic symbol recognition problem by one-shot classification with prototypical images as a single training example for each novel class. We take an approach to learn a generalizable embedding space for novel tasks. We propose a new approach called variational prototyping-encoder (VPE) that learns the image translation task from real-world input images to their corresponding prototypical images as a meta-task. As a result, VPE learns image similarity as well as prototypical concepts which differs from widely used metric learning based approaches. Our experiments with diverse datasets demonstrate that the proposed VPE performs favorably against competing metric learning based one-shot methods. Also, our qualitative analyses show that our meta-task induces an effective embedding space suitable for unseen data representation.

Arda Senocak, Tae-Hyun Oh, Junsik Kim et al.

Visual events are usually accompanied by sounds in our daily lives. We pose the question: Can the machine learn the correspondence between visual scene and the sound, and localize the sound source only by observing sound and visual scene pairs like human? In this paper, we propose a novel unsupervised algorithm to address the problem of localizing the sound source in visual scenes. A two-stream network structure which handles each modality, with attention mechanism is developed for sound source localization. Moreover, although our network is formulated within the unsupervised learning framework, it can be extended to a unified architecture with a simple modification for the supervised and semi-supervised learning settings as well. Meanwhile, a new sound source dataset is developed for performance evaluation. Our empirical evaluation shows that the unsupervised method eventually go through false conclusion in some cases. We show that even with a few supervision, false conclusion is able to be corrected and the source of sound in a visual scene can be localized effectively.

Junsik Kim, Seokju Lee, Tae-Hyun Oh et al.

Recent advances in visual recognition show overarching success by virtue of large amounts of supervised data. However,the acquisition of a large supervised dataset is often challenging. This is also true for intelligent transportation applications, i.e., traffic sign recognition. For example, a model trained with data of one country may not be easily generalized to another country without much data. We propose a novel feature embedding scheme for unseen class classification when the representative class template is given. Traffic signs, unlike other objects, have official images. We perform co-domain embedding using a quadruple relationship from real and synthetic domains. Our quadruplet network fully utilizes the explicit pairwise similarity relationships among samples from different domains. We validate our method on three datasets with two experiments involving one-shot classification and feature generalization. The results show that the proposed method outperforms competing approaches on both seen and unseen classes.

Seokju Lee, Junsik Kim, Jae Shin Yoon et al.

In this paper, we propose a unified end-to-end trainable multi-task network that jointly handles lane and road marking detection and recognition that is guided by a vanishing point under adverse weather conditions. We tackle rainy and low illumination conditions, which have not been extensively studied until now due to clear challenges. For example, images taken under rainy days are subject to low illumination, while wet roads cause light reflection and distort the appearance of lane and road markings. At night, color distortion occurs under limited illumination. As a result, no benchmark dataset exists and only a few developed algorithms work under poor weather conditions. To address this shortcoming, we build up a lane and road marking benchmark which consists of about 20,000 images with 17 lane and road marking classes under four different scenarios: no rain, rain, heavy rain, and night. We train and evaluate several versions of the proposed multi-task network and validate the importance of each task. The resulting approach, VPGNet, can detect and classify lanes and road markings, and predict a vanishing point with a single forward pass. Experimental results show that our approach achieves high accuracy and robustness under various conditions in real-time (20 fps). The benchmark and the VPGNet model will be publicly available.

Jae Shin Yoon, Francois Rameau, Junsik Kim et al.

We propose a novel video object segmentation algorithm based on pixel-level matching using Convolutional Neural Networks (CNN). Our network aims to distinguish the target area from the background on the basis of the pixel-level similarity between two object units. The proposed network represents a target object using features from different depth layers in order to take advantage of both the spatial details and the category-level semantic information. Furthermore, we propose a feature compression technique that drastically reduces the memory requirements while maintaining the capability of feature representation. Two-stage training (pre-training and fine-tuning) allows our network to handle any target object regardless of its category (even if the object's type does not belong to the pre-training data) or of variations in its appearance through a video sequence. Experiments on large datasets demonstrate the effectiveness of our model - against related methods - in terms of accuracy, speed, and stability. Finally, we introduce the transferability of our network to different domains, such as the infrared data domain.

Kyungdon Joo, Tae-Hyun Oh, Junsik Kim et al.

Most man-made environments, such as urban and indoor scenes, consist of a set of parallel and orthogonal planar structures. These structures are approximated by the Manhattan world assumption, in which notion can be represented as a Manhattan frame (MF). Given a set of inputs such as surface normals or vanishing points, we pose an MF estimation problem as a consensus set maximization that maximizes the number of inliers over the rotation search space. Conventionally, this problem can be solved by a branch-and-bound framework, which mathematically guarantees global optimality. However, the computational time of the conventional branch-and-bound algorithms is rather far from real-time. In this paper, we propose a novel bound computation method on an efficient measurement domain for MF estimation, i.e., the extended Gaussian image (EGI). By relaxing the original problem, we can compute the bound with a constant complexity, while preserving global optimality. Furthermore, we quantitatively and qualitatively demonstrate the performance of the proposed method for various synthetic and real-world data. We also show the versatility of our approach through three different applications: extension to multiple MF estimation, 3D rotation based video stabilization, and vanishing point estimation (line clustering).