arXiv subjects

Chia-Ming Lee

Publications and source records attributed to Chia-Ming Lee.

At least 19 recordsLinked to original sources

arXiv2026

Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models

Diffusion language models expose a provisional prediction at every denoising step, and on many tasks the candidate answer inside it stabilizes before the step schedule is exhausted. This creates two acceleration opportunities, leaving a block early and stopping the sequence early, but the two require different criteria because block acceleration is local whereas sequence termination is global and freezes the graded answer. Existing methods usually optimize only one axis, and existing exit gates rely on fixed-region confidence or schedule-dependent rules rather than the candidate answer itself. We present $\textbf{C}^4$, which coordinates the two axes by giving each decision its own gate. $\textbf{C}$onfidence-Verified Early Exit (CVEE) decides when the sequence may stop, requiring confidence and sustained argmax stability over a candidate span re-extracted at every step. $\textbf{C}$ommit-$\textbf{C}$ore-Then-$\textbf{C}$onfirm (CCTC) decides which token positions a step may commit by borrowing an autoregressive freezing order inside each block: it commits a boundary-anchored core and confirms deferred positions one step later, so the answer block can be accelerated without allowing local commits inside the answer span to determine sequence-level termination. On 12 zero-shot tasks with LLaDA and Dream, one frozen configuration removes 64--95% of decoding steps and delivers measured end-to-end speedups of 2.6 to 8.6 over full decoding. Code is available at https://github.com/ming053l/C4-dLLM.

cs.CL↗

arXiv2026

VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection -- after competition results

Capsule endoscopy event detection is challenging because clinically relevant findings are sparse, visually heterogeneous, and evaluated at the event level rather than by frame accuracy. We propose VISTA, a metric-aligned multi-backbone framework for the RAREVISION task. VISTA combines EndoFM-LV for temporal context and DINOv3 ViTL/16 for frame-level visual semantics, followed by a Diverse Head Ensemble (DHE), Validation-Guided Weighted Fusion (VGWF), and Anatomy-Aware Temporal Event Decoding (ATED). The original official submission achieved hidden-test temporal mAP@0.5 of 0.3530 and mAP@0.95 of 0.3235. After the competition, extending local threshold refinement with a global coarse search improved performance to 0.3726 mAP@0.5 and 0.3431 mAP@0.95, ranking Team ACVLab second in the post-competition evaluation.

cs.CV↗

arXiv2026

Cross-modal Affinity-aligned Multimodal Learning Analytics for Predicting Student Collaboration Satisfaction in Game-Based Learning

Collaborative game-based learning environments offer rich opportunities for small-group knowledge construction, yet automatically predicting student collaboration satisfaction remains challenging. A critical barrier is modality degradation: in educational deployments, individual modalities such as eye gaze exhibit inconsistent informativeness across student cohorts, causing implicit attention-based fusion to produce brittle multimodal representations. We propose the Affinity-Aligned Multimodal Learning Analytics (AAMLA) framework, whose core contribution is the Cross-modal Affinity-guided Modality Alignment (CAMA) module, which explicitly models inter-modal relationships via affinity matrices and enforces cross-modal consistency through contrastive learning, enabling adaptive suppression of uninformative modalities without discarding them. AAMLA further applies modality-specific projection layers to map heterogeneous features, including facial action units, head pose, eye gaze, and interaction trace logs, into a unified semantic space prior to alignment. Experiments on 50 middle school students in the EcoJourneys collaborative learning environment demonstrate consistent improvements over unimodal baselines and prior cross-attention approaches under standard and modality degradation conditions, with SHAP and t-SNE analyses confirming that CAMA produces robust, interpretable cross-modal representations for student collaboration modeling.

cs.LG↗

arXiv2026

Robust Deepfake Detection, NTIRE 2026 Challenge: Report

Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight image degradation. In addition to weaker degradations that can accidentally occur in the image processing pipeline, there is another risk of malicious deepfakes that specifically introduce degradations, purposefully exploiting the detector's weaknesses in that regard. Here, we present an overview of the NTIRE 2026 Robust Deepfake Detection Challenge, which specifically addresses that problem. Participants were tasked with building a detector that would later be tested on an unknown test-set, which included both common and uncommon degradations of various strengths. With a total number of 337 participants and 57 submissions to the final leaderboard, the first edition of the challenge was well received. To ensure the reliability of the results, participants were given only 24h to complete the test run with no labels provided, limiting the possibility of training on the test data. Furthermore, the top solutions were scored on a private test-set to detect any such overfitting. This report presents the competition setting, dataset preparation, as well as details and performance of methods. Top methods rely on large foundation models, ensembles, and degradation training to combine generality and robustness.

cs.CV↗

arXiv2026

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers

Existing attention accelerators often trade exact softmax semantics, depend on fused Tensor Core kernels, or incur sequential depth that limits FP32 throughput on long sequences. We present \textbf{ELSA}, an algorithmic reformulation of online softmax attention that (i)~preserves exact softmax semantics in real arithmetic with a \emph{provable} $\mathcal{O}(u\log n)$ FP32 relative error bound; (ii)~casts the online softmax update as a prefix scan over an associative monoid $(m,S,W)$, yielding $O(n)$ extra memory and $O(\log n)$ parallel depth; and (iii)~is Tensor-Core independent, implemented in Triton and CUDA C++, and deployable as a \emph{drop-in replacement} requiring no retraining or weight modification. Unlike FlashAttention-2/3, which rely on HMMA/GMMA Tensor Core instructions and provide no compatible FP32 path, ELSA operates identically on A100s and resource-constrained edge devices such as Jetson TX2 -- making it the only hardware-agnostic exact-attention kernel that reduces parallel depth to $O(\log n)$ at full precision. On A100 FP32 benchmarks (1K--16K tokens), ELSA delivers $1.3$--$3.5\times$ speedup over memory-efficient SDPA and $1.97$--$2.27\times$ on BERT; on Jetson TX2, ELSA achieves $1.5$--$1.6\times$ over Math (64--900 tokens), with $17.8$--$20.2\%$ throughput gains under LLaMA-13B offloading at $\ge$32K. In FP16, ELSA approaches hardware-fused baselines at long sequences while retaining full FP32 capability, offering a unified kernel for high-precision inference across platforms. Our code and implementation are available at https://github.com/ming053l/ELSA.

cs.LG↗

arXiv2026

NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods

In this paper, we review the NTIRE 2026 challenge on single-image reflection removal (SIRR) in the wild. SIRR is a fundamental task in image restoration. Despite progress in academic research, most methods are tested on synthetic images or limited real-world images, creating a gap in real-world applications. In this challenge, we provide participants with the OpenRR-5k dataset. This dataset requires participants to process real-world images covering a range of reflection scenarios and intensities, aiming to generate clean images without reflections. The challenge attracted more than 100 registrations, with eleven of them participating in the final testing phase. The top-ranked methods advanced the state-of-the-art reflection removal performance and earned unanimous recognition from five experts in the field. The proposed OpenRR-5k dataset is available at https://huggingface.co/datasets/qiuzhangTiTi/OpenRR-5k, and the homepage of this challenge is at https://github.com/caijie0620/OpenRR-5k.

cs.CV↗

arXiv2026

CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization

Color ambient lighting normalization under multi-colored illumination is challenging due to severe chromatic shifts, highlight saturation, and material-dependent reflectance. Existing geometric and low-level priors are insufficient for recovering object-intrinsic color when illumination-induced chromatic bias dominates. We observe that DINOv3's self-supervised features remain highly consistent between colored-light inputs and ambient-lit ground truth, motivating their use as illumination-robust semantic priors. We propose CANDLE (Color Ambient Normalization with DINO Layer Enhancement), which introduces DINO Omni-layer Guidance (D.O.G.) to adaptively inject multi-layer DINOv3 features into successive encoder stages, and a color-frequency refinement design (BFACG + SFFB) to suppress decoder-side chromatic collapse and detail contamination. Experiments on CL3AN show a +1.22 dB PSNR gain over the strongest prior method. CANDLE achieves 3rd place on the NTIRE 2026 ALN Color Lighting Challenge and 2nd place in fidelity on the White Lighting track with the lowest FID, confirming strong generalization across both chromatic and luminance-dominant illumination conditions. Code is available at https://github.com/ron941/CANDLE.

cs.CV↗

arXiv2026

VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection

Capsule endoscopy event detection is challenging because diagnostically relevant findings are sparse, visually heterogeneous, and embedded in long, noisy video streams, while evaluation is performed at the event level rather than by frame accuracy alone. We therefore formulate the RARE-VISION task as a metric-aligned event detection problem instead of a purely frame-wise classification task. Our framework combines two complementary backbones, EndoFM-LV for local temporal context and DINOv3 ViT-L/16 for strong frame-level visual semantics, followed by a Diverse Head Ensemble, Validation-Guided Hierarchical Fusion, and Anatomy-Aware Temporal Event Decoding. The fusion stage uses validation-derived class-wise model weighting, backbone weighting, and probability calibration, while the decoding stage applies temporal smoothing, anatomical constraints, threshold refinement, and per-label event generation to produce stable event predictions. Validation ablations indicate that complementary backbones, validation-guided fusion, and anatomy-aware temporal decoding all contribute to event-level performance. On the official hidden test set, the proposed method achieved an overall temporal mAP@0.5 of 0.3530 and temporal mAP@0.95 of 0.3235.

cs.CV↗

arXiv2026

GTATrack: Winner Solution to SoccerTrack 2025 with Deep-EIoU and Global Tracklet Association

Multi-object tracking (MOT) in sports is highly challenging due to irregular player motion, uniform appearances, and frequent occlusions. These difficulties are further exacerbated by the geometric distortion and extreme scale variation introduced by static fisheye cameras. In this work, we present GTATrack, a hierarchical tracking framework that win first place in the SoccerTrack Challenge 2025. GTATrack integrates two core components: Deep Expansion IoU (Deep-EIoU) for motion-agnostic online association and Global Tracklet Association (GTA) for trajectory-level refinement. This two-stage design enables both robust short-term matching and long-term identity consistency. Additionally, a pseudo-labeling strategy is used to boost detector recall on small and distorted targets. The synergy between local association and global reasoning effectively addresses identity switches, occlusions, and tracking fragmentation. Our method achieved a winning HOTA score of 0.60 and significantly reduced false positives to 982, demonstrating state-of-the-art accuracy in fisheye-based soccer tracking. Our code is available at https://github.com/ron941/GTATrack-STC2025.

cs.CV↗

arXiv2026

HSSDCT: Factorized Spatial-Spectral Correlation for Hyperspectral Image Fusion

Hyperspectral image (HSI) fusion aims to reconstruct a high-resolution HSI (HR-HSI) by combining the rich spectral information of a low-resolution HSI (LR-HSI) with the fine spatial details of a high-resolution multispectral image (HR-MSI). Although recent deep learning methods have achieved notable progress, they still suffer from limited receptive fields, redundant spectral bands, and the quadratic complexity of self-attention, which restrict both efficiency and robustness. To overcome these challenges, we propose the Hierarchical Spatial-Spectral Dense Correlation Network (HSSDCT). The framework introduces two key modules: (i) a Hierarchical Dense-Residue Transformer Block (HDRTB) that progressively enlarges windows and employs dense-residue connections for multi-scale feature aggregation, and (ii) a Spatial-Spectral Correlation Layer (SSCL) that explicitly factorizes spatial and spectral dependencies, reducing self-attention to linear complexity while mitigating spectral redundancy. Extensive experiments on benchmark datasets demonstrate that HSSDCT delivers superior reconstruction quality with significantly lower computational costs, achieving new state-of-the-art performance in HSI fusion. Our code is available at https://github.com/jemmyleee/HSSDCT.

cs.CV↗

arXiv2026

ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation

Single Image Reflection Separation (SIRS) disentangles mixed images into transmission and reflection layers. Existing methods suffer from transmission-reflection confusion under nonlinear mixing, particularly in deep decoder layers, due to implicit fusion mechanisms and inadequate multi-scale coordination. We propose ReflexSplit, a dual-stream framework with three key innovations. (1) Cross-scale Gated Fusion (CrGF) adaptively aggregates semantic priors, texture details, and decoder context across hierarchical depths, stabilizing gradient flow and maintaining feature consistency. (2) Layer Fusion-Separation Blocks (LFSB) alternate between fusion for shared structure extraction and differential separation for layer-specific disentanglement. Inspired by Differential Transformer, we extend attention cancellation to dual-stream separation via cross-stream subtraction. (3) Curriculum training progressively strengthens differential separation through depth-dependent initialization and epoch-wise warmup. Extensive experiments on synthetic and real-world benchmarks demonstrate state-of-the-art performance with superior perceptual quality and robust generalization. Our code is available at https://github.com/wuw2135/ReflexSplit.

cs.CV↗

arXiv2026

PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors

Shadow removal under diverse lighting conditions requires disentangling illumination from intrinsic reflectance, a challenge compounded when physical priors are not properly aligned. We propose PhaSR (Physically Aligned Shadow Removal), addressing this through dual-level prior alignment to enable robust performance from single-light shadows to multi-source ambient lighting. First, Physically Aligned Normalization (PAN) performs closed-form illumination correction via Gray-world normalization, log-domain Retinex decomposition, and dynamic range recombination, suppressing chromatic bias. Second, Geometric-Semantic Rectification Attention (GSRA) extends differential attention to cross-modal alignment, harmonizing depth-derived geometry with DINO-v2 semantic embeddings to resolve modal conflicts under varying illumination. Experiments show competitive performance in shadow removal with lower complexity and generalization to ambient lighting where traditional methods fail under multi-source illumination. Our source code is available at https://github.com/ming053l/PhaSR.

cs.CV↗

arXiv2025

Towards Robust DeepFake Detection under Unstable Face Sequences: Adaptive Sparse Graph Embedding with Order-Free Representation and Explicit Laplacian Spectral Prior

Ensuring the authenticity of video content remains challenging as DeepFake generation becomes increasingly realistic and robust against detection. Most existing detectors implicitly assume temporally consistent and clean facial sequences, an assumption that rarely holds in real-world scenarios where compression artifacts, occlusions, and adversarial attacks destabilize face detection and often lead to invalid or misdetected faces. To address these challenges, we propose a Laplacian-Regularized Graph Convolutional Network (LR-GCN) that robustly detects DeepFakes from noisy or unordered face sequences, while being trained only on clean facial data. Our method constructs an Order-Free Temporal Graph Embedding (OF-TGE) that organizes frame-wise CNN features into an adaptive sparse graph based on semantic affinities. Unlike traditional methods constrained by strict temporal continuity, OF-TGE captures intrinsic feature consistency across frames, making it resilient to shuffled, missing, or heavily corrupted inputs. We further impose a dual-level sparsity mechanism on both graph structure and node features to suppress the influence of invalid faces. Crucially, we introduce an explicit Graph Laplacian Spectral Prior that acts as a high-pass operator in the graph spectral domain, highlighting structural anomalies and forgery artifacts, which are then consolidated by a low-pass GCN aggregation. This sequential design effectively realizes a task-driven spectral band-pass mechanism that suppresses background information and random noise while preserving manipulation cues. Extensive experiments on FF++, Celeb-DFv2, and DFDC demonstrate that LR-GCN achieves state-of-the-art performance and significantly improved robustness under severe global and local disruptions, including missing faces, occlusions, and adversarially perturbed face detections.

cs.CV↗

arXiv2025

UMCL: Unimodal-generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection

In deepfake detection, the varying degrees of compression employed by social media platforms pose significant challenges for model generalization and reliability. Although existing methods have progressed from single-modal to multimodal approaches, they face critical limitations: single-modal methods struggle with feature degradation under data compression in social media streaming, while multimodal approaches require expensive data collection and labeling and suffer from inconsistent modal quality or accessibility in real-world scenarios. To address these challenges, we propose a novel Unimodal-generated Multimodal Contrastive Learning (UMCL) framework for robust cross-compression-rate (CCR) deepfake detection. In the training stage, our approach transforms a single visual modality into three complementary features: compression-robust rPPG signals, temporal landmark dynamics, and semantic embeddings from pre-trained vision-language models. These features are explicitly aligned through an affinity-driven semantic alignment (ASA) strategy, which models inter-modal relationships through affinity matrices and optimizes their consistency through contrastive learning. Subsequently, our cross-quality similarity learning (CQSL) strategy enhances feature robustness across compression rates. Extensive experiments demonstrate that our method achieves superior performance across various compression rates and manipulation types, establishing a new benchmark for robust deepfake detection. Notably, our approach maintains high detection accuracy even when individual features degrade, while providing interpretable insights into feature relationships through explicit alignment.

cs.CV↗

arXiv2025

WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement

Underwater Image Enhancement (UIE) aims to restore visibility and correct color distortions caused by wavelength-dependent absorption and scattering. Recent hybrid approaches, which couple domain priors with modern deep neural architectures, have achieved strong performance but incur high computational cost, limiting their practicality in real-time scenarios. In this work, we propose WWE-UIE, a compact and efficient enhancement network that integrates three interpretable priors. First, adaptive white balance alleviates the strong wavelength-dependent color attenuation, particularly the dominance of blue-green tones. Second, a wavelet-based enhancement block (WEB) performs multi-band decomposition, enabling the network to capture both global structures and fine textures, which are critical for underwater restoration. Third, a gradient-aware module (SGFB) leverages Sobel operators with learnable gating to explicitly preserve edge structures degraded by scattering. Extensive experiments on benchmark datasets demonstrate that WWE-UIE achieves competitive restoration quality with substantially fewer parameters and FLOPs, enabling real-time inference on resource-limited platforms. Ablation studies and visualizations further validate the contribution of each component. The source code is available at https://github.com/chingheng0808/WWE-UIE.

cs.CV↗

arXiv2025

Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization

Multi-source CT-scan classification suffers from domain shifts that impair cross-source generalization. While preprocessing pipelines combining Spatial-Slice Feature Learning (SSFL++) and Kernel-Density-based Slice Sampling (KDS) have shown empirical success, the mechanisms underlying their domain robustness remain underexplored. This study analyzes how this input-space standardization manages the trade-off between local discriminability and cross-source generalization. The SSFL++ and KDS pipeline performs spatial and temporal standardization to reduce inter-source variance, effectively mapping disparate inputs into a consistent target space. This preemptive alignment mitigates domain shift and simplifies the learning task for network optimization. Experimental validation demonstrates consistent improvements across architectures, proving the benefits stem from the preprocessing itself. The approach's effectiveness was validated by securing first place in a competitive challenge, supporting input-space standardization as a robust and practical solution for multi-institutional medical imaging.

eess.IV↗

arXiv2025

Anchoring Trends: Mitigating Social Media Popularity Prediction Drift via Feature Clustering and Expansion

Predicting online video popularity faces a critical challenge: prediction drift, where models trained on historical data rapidly degrade due to evolving viral trends and user behaviors. To address this temporal distribution shift, we propose an Anchored Multi-modal Clustering and Feature Generation (AMCFG) framework that discovers temporally-invariant patterns across data distributions. Our approach employs multi-modal clustering to reveal content structure, then leverages Large Language Models (LLMs) to generate semantic Anchor Features, such as audience demographics, content themes, and engagement patterns that transcend superficial trend variations. These semantic anchors, combined with cluster-derived statistical features, enable prediction based on stable principles rather than ephemeral signals. Experiments demonstrate that AMCFG significantly enhances both predictive accuracy and temporal robustness, achieving superior performance on out-of-distribution data and providing a viable solution for real-world video popularity prediction.

cs.MM↗

arXiv2025

DenseSR: Image Shadow Removal as Dense Prediction

Shadows are a common factor degrading image quality. Single-image shadow removal (SR), particularly under challenging indirect illumination, is hampered by non-uniform content degradation and inherent ambiguity. Consequently, traditional methods often fail to simultaneously recover intra-shadow details and maintain sharp boundaries, resulting in inconsistent restoration and blurring that negatively affect both downstream applications and the overall viewing experience. To overcome these limitations, we propose the DenseSR, approaching the problem from a dense prediction perspective to emphasize restoration quality. This framework uniquely synergizes two key strategies: (1) deep scene understanding guided by geometric-semantic priors to resolve ambiguity and implicitly localize shadows, and (2) high-fidelity restoration via a novel Dense Fusion Block (DFB) in the decoder. The DFB employs adaptive component processing-using an Adaptive Content Smoothing Module (ACSM) for consistent appearance and a Texture-Boundary Recuperation Module (TBRM) for fine textures and sharp boundaries-thereby directly tackling the inconsistent restoration and blurring issues. These purposefully processed components are effectively fused, yielding an optimized feature representation preserving both consistency and fidelity. Extensive experimental results demonstrate the merits of our approach over existing methods. Our code can be available on https://github$.$com/VanLinLin/DenseSR

cs.CV↗