Junyeong Kim

Thang Vu, Kookhoi Kim, Tung M. Luu et al.

This paper considers a network referred to as SoftGroup for accurate and scalable 3D instance segmentation. Existing state-of-the-art methods produce hard semantic predictions followed by grouping instance segmentation results. Unfortunately, errors stemming from hard decisions propagate into the grouping, resulting in poor overlap between predicted instances and ground truth and substantial false positives. To address the abovementioned problems, SoftGroup allows each point to be associated with multiple classes to mitigate the uncertainty stemming from semantic prediction. It also suppresses false positive instances by learning to categorize them as background. Regarding scalability, the existing fast methods require computational time on the order of tens of seconds on large-scale scenes, which is unsatisfactory and far from applicable for real-time. Our finding is that the $k$-Nearest Neighbor ($k$-NN) module, which serves as the prerequisite of grouping, introduces a computational bottleneck. SoftGroup is extended to resolve this computational bottleneck, referred to as SoftGroup++. The proposed SoftGroup++ reduces time complexity with octree $k$-NN and reduces search space with class-aware pyramid scaling and late devoxelization. Experimental results on various indoor and outdoor datasets demonstrate the efficacy and generality of the proposed SoftGroup and SoftGroup++. Their performances surpass the best-performing baseline by a large margin (6\% $\sim$ 16\%) in terms of AP$_{50}$. On datasets with large-scale scenes, SoftGroup++ achieves a 6$\times$ speed boost on average compared to SoftGroup. Furthermore, SoftGroup can be extended to perform object detection and panoptic segmentation with nontrivial improvements over existing methods. The source code and trained models are available at \url{https://github.com/thangvubk/SoftGroup}.

Sangyeon Cho, Jangyeong Jeon, Dongjoon Lee et al.

The use of pre-trained language models fine-tuned to address specific downstream tasks is a common approach in natural language processing (NLP). However, acquiring domain-specific knowledge via fine-tuning is challenging. Traditional methods involve pretraining language models using vast amounts of domain-specific data before fine-tuning for particular tasks. This study investigates emergency/non-emergency classification tasks based on electronic medical record (EMR) data obtained from pediatric emergency departments (PEDs) in Korea. Our findings reveal that existing domain-specific pre-trained language models underperform compared to general language models in handling N-lingual free-text data characteristics of non-English-speaking regions. To address these limitations, we propose a domain knowledge transfer methodology that leverages knowledge distillation to infuse general language models with domain-specific knowledge via fine-tuning. This study demonstrates the effective transfer of specialized knowledge between models by defining a general language model as the student model and a domain-specific pre-trained model as the teacher model. In particular, we address the complexities of EMR data obtained from PEDs in non-English-speaking regions, such as Korea, and demonstrate that the proposed method enhances classification performance in such contexts. The proposed methodology not only outperforms baseline models on Korean PED EMR data, but also promises broader applicability in various professional and technical domains. In future works, we intend to extend this methodology to include diverse non-English-speaking regions and address additional downstream tasks, with the aim of developing advanced model architectures using state-of-the-art KD techniques. The code is available in https://github.com/JoSangYeon/DSG-KD.

Sunjae Yoon, Ji Woo Hong, Eunseop Yoon et al.

Video moment retrieval (VMR) aims to localize target moments in untrimmed videos pertinent to a given textual query. Existing retrieval systems tend to rely on retrieval bias as a shortcut and thus, fail to sufficiently learn multi-modal interactions between query and video. This retrieval bias stems from learning frequent co-occurrence patterns between query and moments, which spuriously correlate objects (e.g., a pencil) referred in the query with moments (e.g., scene of writing with a pencil) where the objects frequently appear in the video, such that they converge into biased moment predictions. Although recent debiasing methods have focused on removing this retrieval bias, we argue that these biased predictions sometimes should be preserved because there are many queries where biased predictions are rather helpful. To conjugate this retrieval bias, we propose a Selective Query-guided Debiasing network (SQuiDNet), which incorporates the following two main properties: (1) Biased Moment Retrieval that intentionally uncovers the biased moments inherent in objects of the query and (2) Selective Query-guided Debiasing that performs selective debiasing guided by the meaning of the query. Our experimental results on three moment retrieval benchmarks (i.e., TVR, ActivityNet, DiDeMo) show the effectiveness of SQuiDNet and qualitative analysis shows improved interpretability.

Sunjae Yoon, Eunseop Yoon, Hee Suk Yoon et al.

Video-grounded Dialogue (VGD) aims to decode an answer sentence to a question regarding a given video and dialogue context. Despite the recent success of multi-modal reasoning to generate answer sentences, existing dialogue systems still suffer from a text hallucination problem, which denotes indiscriminate text-copying from input texts without an understanding of the question. This is due to learning spurious correlations from the fact that answer sentences in the dataset usually include the words of input texts, thus the VGD system excessively relies on copying words from input texts by hoping those words to overlap with ground-truth texts. Hence, we design Text Hallucination Mitigating (THAM) framework, which incorporates Text Hallucination Regularization (THR) loss derived from the proposed information-theoretic text hallucination measurement approach. Applying THAM with current dialogue systems validates the effectiveness on VGD benchmarks (i.e., AVSD@DSTC7 and AVSD@DSTC8) and shows enhanced interpretability.

Jisoo Yang, Jongwon Ryu, Minuk Ma et al.

Large Language Models (LLMs) reveal inherent and distinctive personas through dialogue. However, most existing persona discovery approaches rely on surface-level lexical or stylistic cues, treating dialogue as a flat sequence of tokens and failing to capture the deeper discourse-level structures that sustain persona consistency. To address this limitation, we propose a novel analytical framework that interprets LLM dialogue through bridging inference -- implicit conceptual relations that connect utterances via shared world knowledge and discourse coherence. By modeling these relations as structured knowledge graphs, our approach captures latent semantic links that govern how LLMs organize meaning across turns, enabling persona discovery at the level of discourse coherence rather than surface realizations. Experimental results across multiple reasoning backbones and target LLMs, ranging from small-scale models to 80B-parameter systems, demonstrate that bridging-inference graphs yield significantly stronger semantic coherence and more stable persona identification than frequency or style-based baselines. These results show that persona traits are consistently encoded in the structural organization of discourse rather than isolated lexical patterns. This work presents a systematic framework for probing, extracting, and visualizing latent LLM personas through the lens of Cognitive Discourse Theory, bridging computational linguistics, cognitive semantics, and persona reasoning in large language models. Codes are available at https://github.com/JiSoo-Yang/Persona_Bridging.git

Tri Ton, Ji Woo Hong, SooHwan Eom et al.

Open-vocabulary 3D instance segmentation transcends traditional closed-vocabulary methods by enabling the identification of both previously seen and unseen objects in real-world scenarios. It leverages a dual-modality approach, utilizing both 3D point clouds and 2D multi-view images to generate class-agnostic object mask proposals. Previous efforts predominantly focused on enhancing 3D mask proposal models; consequently, the information that could come from 2D association to 3D was not fully exploited. This bias towards 3D data, while effective for familiar indoor objects, limits the system's adaptability to new and varied object types, where 2D models offer greater utility. Addressing this gap, we introduce Zero-Shot Dual-Path Integration Framework that equally values the contributions of both 3D and 2D modalities. Our framework comprises three components: 3D pathway, 2D pathway, and Dual-Path Integration. 3D pathway generates spatially accurate class-agnostic mask proposals of common indoor objects from 3D point cloud data using a pre-trained 3D model, while 2D pathway utilizes pre-trained open-vocabulary instance segmentation model to identify a diverse array of object proposals from multi-view RGB-D images. In Dual-Path Integration, our Conditional Integration process, which operates in two stages, filters and merges the proposals from both pathways adaptively. This process harmonizes output proposals to enhance segmentation capabilities. Our framework, utilizing pre-trained models in a zero-shot manner, is model-agnostic and demonstrates superior performance on both seen and unseen data, as evidenced by comprehensive evaluations on the ScanNet200 and qualitative results on ARKitScenes datasets.

Jongwon Ryu, Joonhyung Park, Jaeho Han et al.

Multi-domain image-to-image translation re quires grounding semantic differences ex pressed in natural language prompts into corresponding visual transformations, while preserving unrelated structural and seman tic content. Existing methods struggle to maintain structural integrity and provide fine grained, attribute-specific control, especially when multiple domains are involved. We propose LACE (Language-grounded Attribute Controllable Translation), built on two compo nents: (1) a GLIP-Adapter that fuses global semantics with local structural features to pre serve consistency, and (2) a Multi-Domain Control Guidance mechanism that explicitly grounds the semantic delta between source and target prompts into per-attribute translation vec tors, aligning linguistic semantics with domain level visual changes. Together, these modules enable compositional multi-domain control with independent strength modulation for each attribute. Experiments on CelebA(Dialog) and BDD100K demonstrate that LACE achieves high visual fidelity, structural preservation, and interpretable domain-specific control, surpass ing prior baselines. This positions LACE as a cross-modal content generation framework bridging language semantics and controllable visual translation.

Sunjae Yoon, Dahyun Kim, Eunseop Yoon et al.

Video-grounded Dialogue (VGD) aims to answer questions regarding a given multi-modal input comprising video, audio, and dialogue history. Although there have been numerous efforts in developing VGD systems to improve the quality of their responses, existing systems are competent only to incorporate the information in the video and text and tend to struggle in extracting the necessary information from the audio when generating appropriate responses to the question. The VGD system seems to be deaf, and thus, we coin this symptom of current systems' ignoring audio data as a deaf response. To overcome the deaf response problem, Hearing Enhanced Audio Response (HEAR) framework is proposed to perform sensible listening by selectively attending to audio whenever the question requires it. The HEAR framework enhances the accuracy and audibility of VGD systems in a model-agnostic manner. HEAR is validated on VGD datasets (i.e., AVSD@DSTC7 and AVSD@DSTC8) and shows effectiveness with various VGD systems.

Woojun Jung, Junyeong Kim

Video-to-text summarization remains underexplored in terms of comprehensive evaluation methods. Traditional n-gram overlap-based metrics and recent large language model (LLM)-based approaches depend heavily on human-written reference summaries, limiting their practicality and sensitivity to nuanced semantic aspects. In this paper, we propose QEVA, a reference-free metric evaluating candidate summaries directly against source videos through multimodal question answering. QEVA assesses summaries along three clear dimensions: Coverage, Factuality, and Chronology. We also introduce MLVU(VS)-Eval, a new annotated benchmark derived from the MLVU dataset, comprising 800 summaries generated from 200 videos using state-of-the-art video-language multimodal models. This dataset establishes a transparent and consistent framework for evaluation. Experimental results demonstrate that QEVA shows higher correlation with human judgments compared to existing approaches, as measured by Kendall's $τ_b$, $τ_c$, and Spearman's $ρ$. We hope that our benchmark and metric will facilitate meaningful progress in video-to-text summarization research and provide valuable insights for the development of future evaluation methods.

Woojun Jung, Jaehoon Go, Mingyu Jeon et al.

Multimodal Large Language Models (MLLMs) demonstrate impressive reasoning capabilities, but often fail to perceive fine-grained visual details, limiting their applicability in precision-demanding tasks. While methods that crop salient regions of an image offer a partial solution, we identify a critical limitation they introduce: "Contextual Blindness". This failure occurs due to structural disconnect between high-fidelity details (from the crop) and the broader global context (from the original image), even when all necessary visual information is present. We argue that this limitation stems not from a lack of information 'Quantity', but from a lack of 'Structural Diversity' in the model's input. To resolve this, we propose Visual Funnel, a training-free, two-step approach. Visual Funnel first performs Contextual Anchoring to identify the region of interest in a single forward pass. It then constructs an Entropy-Scaled Portfolio that preserves the hierarchical context - ranging from focal detail to broader surroundings - by dynamically determining crop sizes based on attention entropy and refining crop centers. Through extensive experiments, we demonstrate that Visual Funnel significantly outperforms naive single-crop and unstructured multi-crop baselines. Our results further validate that simply adding more unstructured crops provides limited or even detrimental benefits, confirming that the hierarchical structure of our portfolio is key to resolving Contextual Blindness.

Mingyu Jeon, Sungjin Han, Jinkwon Hwang et al.

Recent advances in Multimodal Large Language Models (MLLMs) have improved image recognition and reasoning, but video-related tasks remain challenging due to memory constraints from dense frame processing. Existing Video Moment Retrieval (VMR) methodologies rely on sparse frame sampling, risking potential information loss, especially in lengthy videos. We propose SMORE (See MORE, store less), a framework that enhances memory efficiency while maintaining high information resolution. SMORE (1) uses query-guided captions to encode semantics aligned with user intent, (2) applies query-aware importance modulation to highlight relevant segments, and (3) adaptively compresses frames to preserve key content while reducing redundancy. This enables efficient video understanding without exceeding memory budgets. Experimental validation reveals that SMORE achieves state-of-the-art performance on QVHighlights, Charades-STA, and ActivityNet-Captions benchmarks.

Sangyeon Cho, Jangyeong Jeon, Mingi Kim et al.

Multi-modal representation learning has become a pivotal area in artificial intelligence, enabling the integration of diverse modalities such as vision, text, and audio to solve complex problems. However, existing approaches predominantly focus on bimodal interactions, such as image-text pairs, which limits their ability to fully exploit the richness of multi-modal data. Furthermore, the integration of modalities in equal-scale environments remains underexplored due to the challenges of constructing large-scale, balanced datasets. In this study, we propose Synergy-CLIP, a novel framework that extends the contrastive language-image pre-training (CLIP) architecture to enhance multi-modal representation learning by integrating visual, textual, and audio modalities. Unlike existing methods that focus on adapting individual modalities to vanilla-CLIP, Synergy-CLIP aligns and captures latent information across three modalities equally. To address the high cost of constructing large-scale multi-modal datasets, we introduce VGG-sound+, a triple-modal dataset designed to provide equal-scale representation of visual, textual, and audio data. Synergy-CLIP is validated on various downstream tasks, including zero-shot classification, where it outperforms existing baselines. Additionally, we introduce a missing modality reconstruction task, demonstrating Synergy-CLIP's ability to extract synergy among modalities in realistic application scenarios. These contributions provide a robust foundation for advancing multi-modal representation learning and exploring new research directions.

Jangyeong Jeon, Sangyeon Cho, Dongjoon Lee et al.

Pediatric Emergency Department (PED) overcrowding presents a significant global challenge, prompting the need for efficient solutions. This paper introduces the BioBridge framework, a novel approach that applies Natural Language Processing (NLP) to Electronic Medical Records (EMRs) in written free-text form to enhance decision-making in PED. In non-English speaking countries, such as South Korea, EMR data is often written in a Code-Switching (CS) format that mixes the native language with English, with most code-switched English words having clinical significance. The BioBridge framework consists of two core modules: "bridging modality in context" and "unified bio-embedding." The "bridging modality in context" module improves the contextual understanding of bilingual and code-switched EMRs. In the "unified bio-embedding" module, the knowledge of the model trained in the medical domain is injected into the encoder-based model to bridge the gap between the medical and general domains. Experimental results demonstrate that the proposed BioBridge significantly performance traditional machine learning and pre-trained encoder-based models on several metrics, including F1 score, area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and Brier score. Specifically, BioBridge-XLM achieved enhancements of 0.85% in F1 score, 0.75% in AUROC, and 0.76% in AUPRC, along with a notable 3.04% decrease in the Brier score, demonstrating marked improvements in accuracy, reliability, and prediction calibration over the baseline XLM model. The source code will be made publicly available.

Junyeong Kim, Sunjae Yoon, Dahyun Kim et al.

A video-grounded dialogue system referred to as the Structured Co-reference Graph Attention (SCGA) is presented for decoding the answer sequence to a question regarding a given video while keeping track of the dialogue context. Although recent efforts have made great strides in improving the quality of the response, performance is still far from satisfactory. The two main challenging issues are as follows: (1) how to deduce co-reference among multiple modalities and (2) how to reason on the rich underlying semantic structure of video with complex spatial and temporal dynamics. To this end, SCGA is based on (1) Structured Co-reference Resolver that performs dereferencing via building a structured graph over multiple modalities, (2) Spatio-temporal Video Reasoner that captures local-to-global dynamics of video via gradually neighboring graph attention. SCGA makes use of pointer network to dynamically replicate parts of the question for decoding the answer sequence. The validity of the proposed SCGA is demonstrated on AVSD@DSTC7 and AVSD@DSTC8 datasets, a challenging video-grounded dialogue benchmarks, and TVQA dataset, a large-scale videoQA benchmark. Our empirical results show that SCGA outperforms other state-of-the-art dialogue systems on both benchmarks, while extensive ablation study and qualitative analysis reveal performance gain and improved interpretability.

Minuk Ma, Sunjae Yoon, Junyeong Kim et al.

Video Moment Retrieval (VMR) is a task to localize the temporal moment in untrimmed video specified by natural language query. For VMR, several methods that require full supervision for training have been proposed. Unfortunately, acquiring a large number of training videos with labeled temporal boundaries for each query is a labor-intensive process. This paper explores methods for performing VMR in a weakly-supervised manner (wVMR): training is performed without temporal moment labels but only with the text query that describes a segment of the video. Existing methods on wVMR generate multi-scale proposals and apply query-guided attention mechanisms to highlight the most relevant proposal. To leverage the weak supervision, contrastive learning is used which predicts higher scores for the correct video-query pairs than for the incorrect pairs. It has been observed that a large number of candidate proposals, coarse query representation, and one-way attention mechanism lead to blurry attention maps which limit the localization performance. To handle this issue, Video-Language Alignment Network (VLANet) is proposed that learns sharper attention by pruning out spurious candidate proposals and applying a multi-directional attention mechanism with fine-grained query representation. The Surrogate Proposal Selection module selects a proposal based on the proximity to the query in the joint embedding space, and thus substantially reduces candidate proposals which leads to lower computation load and sharper attention. Next, the Cascaded Cross-modal Attention module considers dense feature interactions and multi-directional attention flow to learn the multi-modal alignment. VLANet is trained end-to-end using contrastive loss which enforces semantically similar videos and queries to gather. The experiments show that the method achieves state-of-the-art performance on Charades-STA and DiDeMo datasets.

Junyeong Kim, Minuk Ma, Trung Pham et al.

This paper considers a network referred to as Modality Shifting Attention Network (MSAN) for Multimodal Video Question Answering (MVQA) task. MSAN decomposes the task into two sub-tasks: (1) localization of temporal moment relevant to the question, and (2) accurate prediction of the answer based on the localized moment. The modality required for temporal localization may be different from that for answer prediction, and this ability to shift modality is essential for performing the task. To this end, MSAN is based on (1) the moment proposal network (MPN) that attempts to locate the most appropriate temporal moment from each of the modalities, and also on (2) the heterogeneous reasoning network (HRN) that predicts the answer using an attention mechanism on both modalities. MSAN is able to place importance weight on the two modalities for each sub-task using a component referred to as Modality Importance Modulation (MIM). Experimental results show that MSAN outperforms previous state-of-the-art by achieving 71.13\% test accuracy on TVQA benchmark dataset. Extensive ablation studies and qualitative analysis are conducted to validate various components of the network.

Junyeong Kim, Minuk Ma, Kyungsu Kim et al.

This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of vision and language. However, establishing large scale dataset for multi-modal video question answering is expensive and the existing benchmarks are relatively small to provide sufficient supervision. To overcome this challenge, this paper proposes a multi-task learning method which is composed of three main components: (1) multi-modal video question answering network that answers the question based on the both video and subtitle feature, (2) temporal retrieval network that predicts the time in the video clip where the question was generated from and (3) modality alignment network that solves metric learning problem to find correct association of video and subtitle modalities. By simultaneously solving related auxiliary tasks with hierarchically shared intermediate layers, the extra synergistic supervisions are provided. Motivated by curriculum learning, multi task ratio scheduling is proposed to learn easier task earlier to set inductive bias at the beginning of the training. The experiments on publicly available dataset TVQA shows state-of-the-art results, and ablation studies are conducted to prove the statistical validity.

Junyeong Kim, Minuk Ma, Kyungsu Kim et al.

This paper proposes the progressive attention memory network (PAMN) for movie story question answering (QA). Movie story QA is challenging compared to VQA in two aspects: (1) pinpointing the temporal parts relevant to answer the question is difficult as the movies are typically longer than an hour, (2) it has both video and subtitle where different questions require different modality to infer the answer. To overcome these challenges, PAMN involves three main features: (1) progressive attention mechanism that utilizes cues from both question and answer to progressively prune out irrelevant temporal parts in memory, (2) dynamic modality fusion that adaptively determines the contribution of each modality for answering the current question, and (3) belief correction answering scheme that successively corrects the prediction score on each candidate answer. Experiments on publicly available benchmark datasets, MovieQA and TVQA, demonstrate that each feature contributes to our movie story QA architecture, PAMN, and improves performance to achieve the state-of-the-art result. Qualitative analysis by visualizing the inference mechanism of PAMN is also provided.