arXiv subjects

Soo-Hyung Kim

Publications and source records attributed to Soo-Hyung Kim.

At least 19 recordsLinked to original sources

arXiv2026

A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognition

Facial affect in the wild is naturally multi-task: valence-arousal, discrete expressions, and facial action units describe the same face. Yet real corpora annotate these tasks only partially and unevenly, so most systems mask the missing labels or impute pseudo-labels and forgo the cross-task signal. We instead cast partially-labeled multi-task learning as marginalization over a shared affect latent: one variational bottleneck mediates all three task decoders, so a frame annotated for one task shapes the representation the others use, and the masked objective reappears as the reconstruction term of an evidence lower bound. On s-Aff-Wild2, where only 37% of frames carry all three labels, the classes are severely imbalanced, and pretraining on the source data is disallowed, we isolate where this coupling acts. On a single backbone it lifts expression macro-F1 from 0.403 for a dedicated specialist to 0.446, which the masked-loss model does not reach; a second, near-peer backbone with decorrelated errors then breaks an action-unit ceiling that external action-unit data could not, while valence-arousal stays within noise. Every gain is disciplined by a matched-control negative; together these controls indicate that the rare-class failure is representational, not a matter of loss shaping. As each task's source is chosen on the evaluation split, we report the assembled result, a combined multi-task score of 1.679 on validation, as an in-sample endpoint and rest our conclusions on the controlled comparisons; a small, regime-dependent transfer of the expression advantage to AffectNet and RAF-DB is presented as exploratory rather than conclusive.

cs.CV↗

arXiv2026

The Circumplex Degeneracy Behind the Rare-Class Limit in Affect Recognition

In-the-wild expression recognition persistently fails on a few rare emotions, and the standard explanation is class imbalance. Through a controlled multi-task study on two benchmarks, we show the failure is instead a property of affect geometry: the rare classes are degenerate on Russell's circumplex, and that degeneracy bounds what any loss or cost can achieve. Our instrument is a circumplex-cost optimal-transport term that prices expression confusions by their valence-arousal distance. The term improves the official score and expression macro-F1, but a control most studies omit shows the gain is not geometric: a uniform cost, equivalent to a generic confidence penalty, matches it on Aff-Wild2 (p=0.625) and significantly exceeds it on AffectNet (+0.057 over base, larger than the circumplex). What the geometry reshapes is the structure of the errors, making them affectively nearer the truth on Aff-Wild2 (p=0.031 against the uniform control), an effect that does not survive on AffectNet, where a visual confound at the far corner of the circumplex overwhelms it. The rare-class failure, by contrast, is stable across both datasets we examine: the degenerate pairs (anger-fear on Aff-Wild2, anger-contempt on AffectNet) resist frequency-based interventions, the transport term, and an action-unit-augmented cost built specifically to separate them. We conclude that progress on rare expressions requires representations that distinguish the classes, not supervision that reprices their confusions, and we provide the controls and metrics needed to tell the two apart.

cs.CV↗

arXiv2026

Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations

Multimodal models can name the action units (AUs) behind a facial emotion, but their AU->emotion rationales are typically plausible rather than faithful: nothing forces the AUs a model invokes to be the AUs that actually drive its prediction. We cast AU->emotion reasoning as a counterfactual-consistency problem between the rationale, the label, and a structural AU->emotion causal graph G, and propose FACR, which grounds the reasoner in an independently induced, polarity-aware G and trains a counterfactual-faithfulness objective: a do-intervention on an AU that G marks causal for a class must move the prediction, while one it marks irrelevant must leave it unchanged. Faithfulness is thereby both trainable and measurable through a matching interventional metric, which we evaluate against a known causal structure, the PSPI pain-AU composition, as no existing affective-reasoning benchmark allows. We are explicit that this metric tests fidelity to the supplied structure rather than its rediscovery: it asks whether the trained reasoner invokes the AUs the structure marks causal, on held-out subjects and a second dataset. Under subject-independent evaluation on UNBC-PAIN, the objective raises the agreement between the invoked AUs and the PSPI composition from a no-objective baseline of 0.08 to 0.57, at a small detection cost; an unfaithfulness control attributes the gain to the objective. On a cross-dataset emotion transfer, the objective likewise raises fidelity to G on a seven-class task (0.50 to 0.84). Finally, we attach a language verbalizer and extend the audit to the generated text: biasing each action unit's emission by its latent activation makes the rationale faithful by construction, so that ablating an AU removes it from the explanation, a property that transfers to a second language-model backbone, whereas a freely generated rationale is unfaithful.

cs.CV↗

arXiv2026

Coarse-to-fine Hierarchical Architecture with Sequential Mamba for Brain Reconstruction

Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience. While modern vision models achieve strong performance in image recognition, their correspondence with the hierarchical organization of the human visual cortex remains an open question. In this study, we propose CHASMBrain, a novel hierarchical two-stage framework for image-to-fMRI encoding. Our architecture leverages a dual-stream Mamba design to explicitly separate and process global semantic tokens and local spatial patches, motivated by the functional organization of the visual cortex. A coarse-to-fine strategy is employed: Stage 1 predicts denoised ROI-level activations, while Stage 2 refines these coarse responses into full voxel-level predictions using a Mamba-VAE. Experiments on the Natural Scenes Dataset (NSD) demonstrate that our method achieves a Pearson correlation of 0.429 and an MSE of 0.261, outperforming all evaluated baselines including ridge regression and DINOv2 linear probes. Beyond predictive performance, causal branch-ablation experiments reveal an asymmetric specialization: the patch stream is specifically locked to early visual cortex (retinotopic regions), while the CLS stream contributes broader semantic context to higher-order areas -- a correspondence that holds causally, not merely correlationally. Cross-subject transfer experiments further show that the learned backbone generalizes across individuals with minimal per-subject adaptation, suggesting the model captures a shared, subject-agnostic visual representation.

cs.CV↗

arXiv2025

GlobalizeEd: A Multimodal Translation System that Preserves Speaker Identity in Academic Lectures

A large amount of valuable academic content is only available in its original language, creating a significant access barrier for the global student community. This is a challenge for translating in several subjects, such as history, culture, and the arts, where current automated subtitle tools fail to convey the appropriate pedagogical tone and specialized meaning. In addition, reading traditional automated subtitles increases cognitive load and leads to a disconnected learning experience. Through a mixed-methods study involving 36 participants, we found that GlobalizeEds dubbed formats significantly reduce cognitive load and offer a more immersive learning experience compared to traditional subtitles. Although learning effectiveness was comparable between high-quality subtitles and dubbed formats, both groups valued GlobalizeEds ability to preserve the speakers voice, which enhanced perceived authenticity. Instructors rated translation accuracy and vocal naturalness, whereas students reported that synchronized, identity-preserving outputs fostered engagement and trust. This work contributes a novel human-centered AI framework for cross-lingual education, demonstrating how multimodal translation systems can balance linguistic fidelity, cultural adaptability, and user control to create more inclusive global learning experiences.

cs.HC↗

arXiv2025

ATL-Diff: Audio-Driven Talking Head Generation with Early Landmarks-Guide Noise Diffusion

Audio-driven talking head generation requires precise synchronization between facial animations and audio signals. This paper introduces ATL-Diff, a novel approach addressing synchronization limitations while reducing noise and computational costs. Our framework features three key components: a Landmark Generation Module converting audio to facial landmarks, a Landmarks-Guide Noise approach that decouples audio by distributing noise according to landmarks, and a 3D Identity Diffusion network preserving identity characteristics. Experiments on MEAD and CREMA-D datasets demonstrate that ATL-Diff outperforms state-of-the-art methods across all metrics. Our approach achieves near real-time processing with high-quality animations, computational efficiency, and exceptional preservation of facial nuances. This advancement offers promising applications for virtual assistants, education, medical communication, and digital platforms. The source code is available at: \href{https://github.com/sonvth/ATL-Diff}{https://github.com/sonvth/ATL-Diff}

cs.CV↗

arXiv2025

Anatomical Attention Alignment representation for Radiology Report Generation

Automated Radiology report generation (RRG) aims at producing detailed descriptions of medical images, reducing radiologists' workload and improving access to high-quality diagnostic services. Existing encoder-decoder models only rely on visual features extracted from raw input images, which can limit the understanding of spatial structures and semantic relationships, often resulting in suboptimal text generation. To address this, we propose Anatomical Attention Alignment Network (A3Net), a framework that enhance visual-textual understanding by constructing hyper-visual representations. Our approach integrates a knowledge dictionary of anatomical structures with patch-level visual features, enabling the model to effectively associate image regions with their corresponding anatomical entities. This structured representation improves semantic reasoning, interpretability, and cross-modal alignment, ultimately enhancing the accuracy and clinical relevance of generated reports. Experimental results on IU X-Ray and MIMIC-CXR datasets demonstrate that A3Net significantly improves both visual perception and text generation quality. Our code is available at \href{https://github.com/Vinh-AI/A3Net}{GitHub}.

cs.CV↗

arXiv2025

Latent Behavior Diffusion for Sequential Reaction Generation in Dyadic Setting

The dyadic reaction generation task involves synthesizing responsive facial reactions that align closely with the behaviors of a conversational partner, enhancing the naturalness and effectiveness of human-like interaction simulations. This paper introduces a novel approach, the Latent Behavior Diffusion Model, comprising a context-aware autoencoder and a diffusion-based conditional generator that addresses the challenge of generating diverse and contextually relevant facial reactions from input speaker behaviors. The autoencoder compresses high-dimensional input features, capturing dynamic patterns in listener reactions while condensing complex input data into a concise latent representation, facilitating more expressive and contextually appropriate reaction synthesis. The diffusion-based conditional generator operates on the latent space generated by the autoencoder to predict realistic facial reactions in a non-autoregressive manner. This approach allows for generating diverse facial reactions that reflect subtle variations in conversational cues and emotional states. Experimental results demonstrate the effectiveness of our approach in achieving superior performance in dyadic reaction synthesis tasks compared to existing methods.

cs.LG↗

arXiv2024

Rethinking Top Probability from Multi-view for Distracted Driver Behaviour Localization

Naturalistic driving action localization task aims to recognize and comprehend human behaviors and actions from video data captured during real-world driving scenarios. Previous studies have shown great action localization performance by applying a recognition model followed by probability-based post-processing. Nevertheless, the probabilities provided by the recognition model frequently contain confused information causing challenge for post-processing. In this work, we adopt an action recognition model based on self-supervise learning to detect distracted activities and give potential action probabilities. Subsequently, a constraint ensemble strategy takes advantages of multi-camera views to provide robust predictions. Finally, we introduce a conditional post-processing operation to locate distracted behaviours and action temporal boundaries precisely. Experimenting on test set A2, our method obtains the sixth position on the public leaderboard of track 3 of the 2024 AI City Challenge.

cs.CV↗

arXiv2024

Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Model

Automatic polyp segmentation is crucial for effective diagnosis and treatment in colonoscopy images. Traditional methods encounter significant challenges in accurately delineating polyps due to limitations in feature representation and the handling of variability in polyp appearance. Deep learning techniques, including CNN and Transformer-based methods, have been explored to improve polyp segmentation accuracy. However, existing approaches often neglect additional semantics, restricting their ability to acquire adequate contexts of polyps in colonoscopy images. In this paper, we propose an innovative method named ``Automatic Polyp Segmentation with Self-Enriched Semantic Model'' to address these limitations. First, we extract a sequence of features from an input image and decode high-level features to generate an initial segmentation mask. Using the proposed self-enriched semantic module, we query potential semantics and augment deep features with additional semantics, thereby aiding the model in understanding context more effectively. Extensive experiments show superior segmentation performance of the proposed method against state-of-the-art polyp segmentation baselines across five polyp benchmarks in both superior learning and generalization capabilities.

cs.CV↗

arXiv2024

Transformer with Leveraged Masked Autoencoder for video-based Pain Assessment

Accurate pain assessment is crucial in healthcare for effective diagnosis and treatment; however, traditional methods relying on self-reporting are inadequate for populations unable to communicate their pain. Cutting-edge AI is promising for supporting clinicians in pain recognition using facial video data. In this paper, we enhance pain recognition by employing facial video analysis within a Transformer-based deep learning model. By combining a powerful Masked Autoencoder with a Transformers-based classifier, our model effectively captures pain level indicators through both expressions and micro-expressions. We conducted our experiment on the AI4Pain dataset, which produced promising results that pave the way for innovative healthcare solutions that are both comprehensive and objective.

cs.CV↗

arXiv2024

KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation

Audio-driven talking face generation is a widely researched topic due to its high applicability. Reconstructing a talking face using audio significantly contributes to fields such as education, healthcare, online conversations, virtual assistants, and virtual reality. Early studies often focused solely on changing the mouth movements, which resulted in outcomes with limited practical applications. Recently, researchers have proposed a new approach of constructing the entire face, including face pose, neck, and shoulders. To achieve this, they need to generate through landmarks. However, creating stable landmarks that align well with the audio is a challenge. In this paper, we propose the KFusion of Dual-Domain model, a robust model that generates landmarks from audio. We separate the audio into two distinct domains to learn emotional information and facial context, then use a fusion mechanism based on the KAN model. Our model demonstrates high efficiency compared to recent models. This will lay the groundwork for the development of the audio-driven talking face generation problem in the future.

cs.CV↗

arXiv2024

Leveraging WaveNet for Dynamic Listening Head Modeling from Speech

The creation of listener facial responses aims to simulate interactive communication feedback from a listener during a face-to-face conversation. Our goal is to generate believable videos of listeners' heads that respond authentically to a single speaker by a sequence-to-sequence model with an combination of WaveNet and Long short-term memory network. Our approach focuses on capturing the subtle nuances of listener feedback, ensuring the preservation of individual listener identity while expressing appropriate attitudes and viewpoints. Experiment results show that our method surpasses the baseline models on ViCo benchmark Dataset.

cs.CV↗

arXiv2024

Adaptation of Distinct Semantics for Uncertain Areas in Polyp Segmentation

Colonoscopy is a common and practical method for detecting and treating polyps. Segmenting polyps from colonoscopy image is useful for diagnosis and surgery progress. Nevertheless, achieving excellent segmentation performance is still difficult because of polyp characteristics like shape, color, condition, and obvious non-distinction from the surrounding context. This work presents a new novel architecture namely Adaptation of Distinct Semantics for Uncertain Areas in Polyp Segmentation (ADSNet), which modifies misclassified details and recovers weak features having the ability to vanish and not be detected at the final stage. The architecture consists of a complementary trilateral decoder to produce an early global map. A continuous attention module modifies semantics of high-level features to analyze two separate semantics of the early global map. The suggested method is experienced on polyp benchmarks in learning ability and generalization ability, experimental results demonstrate the great correction and recovery ability leading to better segmentation performance compared to the other state of the art in the polyp image segmentation task. Especially, the proposed architecture could be experimented flexibly for other CNN-based encoders, Transformer-based encoders, and decoder backbones.

cs.CV↗

arXiv2024

Mental Workload Estimation with Electroencephalogram Signals by Combining Multi-Space Deep Models

The human brain remains continuously active, whether an individual is working or at rest. Mental activity is a daily process, and if the brain becomes excessively active, known as overload, it can adversely affect human health. Recently, advancements in early prediction of mental health conditions have emerged, aiming to prevent serious consequences and enhance the overall quality of life. Consequently, the estimation of mental status has garnered significant attention from diverse researchers due to its potential benefits. While various signals are employed to assess mental state, the electroencephalogram, containing extensive information about the brain, is widely utilized by researchers. In this paper, we categorize mental workload into three states (low, middle, and high) and estimate a continuum of mental workload levels. Our method leverages information from multiple spatial dimensions to achieve optimal results in mental estimation. For the time domain approach, we employ Temporal Convolutional Networks. In the frequency domain, we introduce a novel architecture based on combining residual blocks, termed the Multi-Dimensional Residual Block. The integration of these two domains yields significant results compared to individual estimates in each domain. Our approach achieved a 74.98% accuracy in the three-class classification, surpassing the provided data results at 69.00%. Specially, our method demonstrates efficacy in estimating continuous levels, evidenced by a corresponding Concordance Correlation Coefficient (CCC) result of 0.629. The combination of time and frequency domain analysis in our approach highlights the exciting potential to improve healthcare applications in the future.

eess.SP↗

arXiv2023

DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation

Conversational engagement estimation is posed as a regression problem, entailing the identification of the favorable attention and involvement of the participants in the conversation. This task arises as a crucial pursuit to gain insights into human's interaction dynamics and behavior patterns within a conversation. In this research, we introduce a dilated convolutional Transformer for modeling and estimating human engagement in the MULTIMEDIATE 2023 competition. Our proposed system surpasses the baseline models, exhibiting a noteworthy $7$\% improvement on test set and $4$\% on validation set. Moreover, we employ different modality fusion mechanism and show that for this type of data, a simple concatenated method with self-attention fusion gains the best performance.

cs.MM↗

arXiv2023

Multi-scale Transformer-based Network for Emotion Recognition from Multi Physiological Signals

This paper presents an efficient Multi-scale Transformer-based approach for the task of Emotion recognition from Physiological data, which has gained widespread attention in the research community due to the vast amount of information that can be extracted from these signals using modern sensors and machine learning techniques. Our approach involves applying a Multi-modal technique combined with scaling data to establish the relationship between internal body signals and human emotions. Additionally, we utilize Transformer and Gaussian Transformation techniques to improve signal encoding effectiveness and overall performance. Our model achieves decent results on the CASE dataset of the EPiC competition, with an RMSE score of 1.45.

eess.SP↗

arXiv2023

CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge's improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.

cs.CV↗