Truong Nguyen

Runfa Blark Li, Kuang-Ting Tu, Nikola Raicevic et al.

Bimanual dexterous tool use remains challenging for robots due to high-dimensional hand configurations and complex hand-tool-object dynamics and contact. Most existing control policies depend on future configuration references provided from demonstrations, while future action-conditioned world models require slow online planning over high-dimensional action sequences. A significant challenge is generating a dynamically consistent future reference trajectory without relying on privileged states from demonstrations or slow counterfactual planning. We propose DexFuture, a hierarchical system that couples a high-level Future-State Visuomotor Target Predictor with a low-level Target-Conditioned Structured Dexterous Policy. Conditioned on egocentric RGB, proprioceptive and geometric history, the high-level predictor constructs structured hand-tool-object visuomotor embeddings and uses a horizon-conditioned transformer to generate a multi-step future target trajectory. Then, the low-level policy tracks them with a target-conditioned per-link transformer. This hierarchy decouples coarse future reference generation from fine-grained action control, and slow long-horizon semantic prediction from high-frequency execution. On OakInk2 bimanual tool-use tasks, DexFuture achieves 90% of the privileged-oracle performance, compared to 7% for a no-reference policy. DexFuture operates at 60 Hz, approximately 250 times faster than DexWM-style Cross-Entropy Method (CEM) planning with a future action-conditioned world model.

Ilona Ambartsumyan, Vincent J. Ervin, Truong Nguyen et al.

We develop and analyze a model for the interaction of a quasi-Newtonian free fluid with a poroelastic medium. The flow in the fluid region is described by the nonlinear Stokes equations and in the poroelastic medium by the nonlinear quasi-static Biot model. Equilibrium and kinematic conditions are imposed on the interface. We establish existence and uniqueness of a solution to the weak formulation and its semidiscrete continuous-in-time finite element approximation. We present error analysis, complemented by numerical experiments.

Jianzhi Long, Jicang Cai, Abdullah Al-Battal et al.

Ultrasound is progressing toward becoming an affordable and versatile solution to medical imaging. With the advent of COVID-19 global pandemic, there is a need to fully automate ultrasound imaging as it requires trained operators in close proximity to patients for a long period of time, therefore increasing risk of infection. In this work, we investigate the important yet seldom-studied problem of scan target localization, under the setting of lung ultrasound imaging. We propose a purely vision-based, data driven method that incorporates learning-based computer vision techniques. We combine a human pose estimation model with a specially designed regression model to predict the lung ultrasound scan targets, and deploy multiview stereo vision to enhance the consistency of 3D target localization. While related works mostly focus on phantom experiments, we collect data from 30 human subjects for testing. Our method attains an accuracy level of 16.00(9.79) mm for probe positioning and 4.44(3.75) degree for probe orientation, with a success rate above 80% under an error threshold of 25mm for all scan targets. Moreover, our approach can serve as a general solution to other types of ultrasound modalities. The code for implementation has been released.

Cam Le, Lam Pham, Nghia NVN et al.

In this paper, we present a robust and low complexity deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the scene of a remote sensing image. In particular, we firstly evaluate different low complexity and benchmark deep neural networks: MobileNetV1, MobileNetV2, NASNetMobile, and EfficientNetB0, which present the number of trainable parameters lower than 5 Million (M). After indicating best network architecture, we further improve the network performance by applying attention schemes to multiple feature maps extracted from middle layers of the network. To deal with the issue of increasing the model footprint as using attention schemes, we apply the quantization technique to satisfy the maximum of 20 MB memory occupation. By conducting extensive experiments on the benchmark datasets NWPU-RESISC45, we achieve a robust and low-complexity model, which is very competitive to the state-of-the-art systems and potential for real-life applications on edge devices.

Xin Lin, Meixi Song, Dizhe Zhang et al.

In this work, we present a panoramic metric depth foundation model that generalizes across diverse scene distances. We explore a data-in-the-loop paradigm from the view of both data construction and framework design. We collect a large-scale dataset by combining public datasets, high-quality synthetic data from our UE5 simulator and text-to-image models, and real panoramic images from the web. To reduce domain gaps between indoor/outdoor and synthetic/real data, we introduce a three-stage pseudo-label curation pipeline to generate reliable ground truth for unlabeled images. For the model, we adopt DINOv3-Large as the backbone for its strong pre-trained generalization, and introduce a plug-and-play range mask head, sharpness-centric optimization, and geometry-centric optimization to improve robustness to varying distances and enforce geometric consistency across views. Experiments on multiple benchmarks (e.g., Stanford2D3D, Matterport3D, and Deep360) demonstrate strong performance and zero-shot generalization, with particularly robust and stable metric predictions in diverse real-world scenes. The project page can be found at: \href{https://insta360-research-team.github.io/DAP_website/} {https://insta360-research-team.github.io/DAP\_website/}

Lam Pham, Phat Lam, Truong Nguyen et al.

In this paper, we propose a deep learning based system for the task of deepfake audio detection. In particular, the draw input audio is first transformed into various spectrograms using three transformation methods of Short-time Fourier Transform (STFT), Constant-Q Transform (CQT), Wavelet Transform (WT) combined with different auditory-based filters of Mel, Gammatone, linear filters (LF), and discrete cosine transform (DCT). Given the spectrograms, we evaluate a wide range of classification models based on three deep learning approaches. The first approach is to train directly the spectrograms using our proposed baseline models of CNN-based model (CNN-baseline), RNN-based model (RNN-baseline), C-RNN model (C-RNN baseline). Meanwhile, the second approach is transfer learning from computer vision models such as ResNet-18, MobileNet-V3, EfficientNet-B0, DenseNet-121, SuffleNet-V2, Swint, Convnext-Tiny, GoogLeNet, MNASsnet, RegNet. In the third approach, we leverage the state-of-the-art audio pre-trained models of Whisper, Seamless, Speechbrain, and Pyannote to extract audio embeddings from the input spectrograms. Then, the audio embeddings are explored by a Multilayer perceptron (MLP) model to detect the fake or real audio samples. Finally, high-performance deep learning models from these approaches are fused to achieve the best performance. We evaluated our proposed models on ASVspoof 2019 benchmark dataset. Our best ensemble model achieved an Equal Error Rate (EER) of 0.03, which is highly competitive to top-performing systems in the ASVspoofing 2019 challenge. Experimental results also highlight the potential of selective spectrograms and deep learning approaches to enhance the task of audio deepfake detection.

Nhat-Tan Bui, Dinh-Hieu Hoang, Quoc-Huy Trinh et al.

Negation is a fundamental linguistic concept used by humans to convey information that they do not desire. Despite this, minimal research has focused on negation within text-guided image editing. This lack of research means that vision-language models (VLMs) for image editing may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving human-level intelligence is the lack of a standard collection by which research into negation can be evaluated. This paper presents the first large-scale dataset, Negative Instruction (NeIn), for studying negation within instruction-based image editing. Our dataset comprises 366,957 quintuplets, i.e., source image, original caption, selected object, negative sentence, and target image in total, including 342,775 queries for training and 24,182 queries for benchmarking image editing methods. Specifically, we automatically generate NeIn based on a large, existing vision-language dataset, MS-COCO, via two steps: generation and filtering. During the generation phase, we leverage two VLMs, BLIP and InstructPix2Pix (fine-tuned on MagicBrush dataset), to generate NeIn's samples and the negative clauses that expresses the content of the source image. In the subsequent filtering phase, we apply BLIP and LLaVA-NeXT to remove erroneous samples. Additionally, we introduce an evaluation protocol to assess the negation understanding for image editing models. Extensive experiments using our dataset across multiple VLMs for text-guided image editing demonstrate that even recent state-of-the-art VLMs struggle to understand negative queries.

Tien-Phat Nguyen, Truong Nguyen, Minh-Phuc Truong et al.

Muon orthogonalizes the momentum buffer before each update, replacing its singular values with ones via Newton-Schulz iterations. This simple change lets Muon tolerate far larger learning rates and converge faster than other optimizers, but why? We show that the mechanism is spectral flattening, and develop two results around it. First, we prove that Muon's maximal stable step size scales with the average singular value of the gradient rather than the largest, which bottlenecks standard gradient descent. Second, we recast Muon as a preconditioned gradient method and show, under a Kronecker-factored curvature model, that it improves the effective convergence factor, with the improvement controlled by the spectrum of the gradient covariance. Extensive experiments validate both results: Muon remains stable at learning rates that cause SGD to diverge within the first few iterations, and reaches accuracy milestones several epochs earlier even at identical step sizes. Taken together, our results offer a principled, geometric explanation for Muon's empirical success.

Tien-Phat Nguyen, Truong Nguyen, Thin Nguyen et al.

Aligning language models for both helpfulness and safety typically requires complex pipelines-separate reward and cost models, online reinforcement learning, and primal-dual updates. Recent direct preference optimization approaches simplify training but incorporate safety through ad-hoc modifications such as multi-stage procedures or heuristic margin terms, lacking a principled derivation. We show that the likelihood ratio of the optimal safe policy admits a closed-form decomposition that reduces safety alignment to a density ratio matching problem. Minimizing Bregman divergences between the data and model ratios yields Bregman Safety Optimization (BSO), a family of single-stage loss functions, each induced by a convex generator, that provably recover the optimal safe policy. BSO is both general and simple: it requires no auxiliary models, introduces only one hyperparameter beyond standard preference optimization, and recovers existing safety-aware methods as special cases. Experiments across safety alignment benchmarks show that BSO consistently improves the safety-helpfulness trade-off.

Truong Nguyen, Tien-Phat Nguyen, Linh Ngo Van et al.

Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions. Existing token-level extensions typically decompose a sequence-level Bradley-Terry objective across timesteps, leaving per-prefix (state-wise) optimality implicit. We study how to recover token-level preference optimality using only standard sequence-level pairwise comparisons. We introduce Token-level Bregman Preference Optimization (TBPO), which posits a token-level Bradley-Terry preference model over next-token actions conditioned on the prefix, and derive a Bregman-divergence density-ratio matching objective that generalizes the logistic/DPO loss while preserving the optimal policy induced by the token-level model and maintaining DPO-like simplicity. We introduce two instantiations: TBPO-Q, which explicitly learns a lightweight state baseline, and TBPO-A, which removes the baseline through advantage normalization. Across instruction following, helpfulness/harmlessness, and summarization benchmarks, TBPO improves alignment quality and training stability and increases output diversity relative to strong sequence-level and token-level baselines.

Xinshuang Liu, Runfa Blark Li, Truong Nguyen

Text-to-video generation is expensive, so only a few samples are typically produced per prompt. In this low-sample regime, maximizing the value of each batch requires high cross-video diversity. Recent methods improve diversity for image generation, but for videos they often degrade within-video temporal consistency and require costly backpropagation through a video decoder. We propose a joint-sampling framework for flow-matching video generators that improves batch diversity while preserving temporal consistency. Our approach applies diversity-driven updates and then removes only the components that would decrease a temporal-consistency objective. To avoid image-space gradients, we compute both objectives with lightweight latent-space models, avoiding video decoding and decoder backpropagation. Experiments on a state-of-the-art text-to-video flow-matching model show diversity comparable to strong joint-sampling baselines while substantially improving temporal consistency and color naturalness. Code will be released.

Xinshuang Liu, Runfa Blark Li, Keito Suzuki et al.

3D Gaussian Splatting (3DGS) has attracted considerable attention for enabling high-quality real-time rendering. Although 3DGS compression methods have been proposed for deployment on storage-constrained devices, two limitations hinder archival use: (1) they compress medium-scale scenes only to the megabyte range, which remains impractical for large-scale scenes or extensive scene collections; and (2) they lack mechanisms to accommodate scene changes after long-term archival. To address these limitations, we propose an Image-Conditioned Gaussian Splat Quantizer (ICGS-Quantizer) that substantially enhances compression efficiency and provides adaptability to scene changes after archiving. ICGS-Quantizer improves quantization efficiency by jointly exploiting inter-Gaussian and inter-attribute correlations and by using shared codebooks across all training scenes, which are then fixed and applied to previously unseen test scenes, eliminating the overhead of per-scene codebooks. This approach effectively reduces the storage requirements for 3DGS to the kilobyte range while preserving visual fidelity. To enable adaptability to post-archival scene changes, ICGS-Quantizer conditions scene decoding on images captured at decoding time. The encoding, quantization, and decoding processes are trained jointly, ensuring that the codes, which are quantized representations of the scene, are effective for conditional decoding. We evaluate ICGS-Quantizer on 3D scene compression and 3D scene updating. Experimental results show that ICGS-Quantizer consistently outperforms state-of-the-art methods in compression efficiency and adaptability to scene changes. Our code, model, and data will be publicly available on GitHub.

Subarna Tripathi, Serge Belongie, Youngbae Hwang et al.

We explore the efficiency of the CRF inference beyond image level semantic segmentation and perform joint inference in video frames. The key idea is to combine best of two worlds: semantic co-labeling and more expressive models. Our formulation enables us to perform inference over ten thousand images within seconds and makes the system amenable to perform video semantic segmentation most effectively. On CamVid dataset, with TextonBoost unaries, our proposed method achieves up to 8% improvement in accuracy over individual semantic image segmentation without additional time overhead. The source code is available at https://github.com/subtri/video_inference

Bo Wen, Dillon Lohr, Yatong An et al.

Retinal image-based eye tracking is widely used in ophthalmic imaging and vision science, and is a promising path to deliver higher gaze accuracy than the pupil- and cornea-based approaches commonly used in modern AR/VR devices. Nevertheless, existing retinal tracking algorithms still primarily rely on classical template-matching registration, which can be insufficiently robust to retinal feature variability and real-world imaging conditions. In this work, we propose a novel weakly-supervised, learning-based framework for robust retinal eye tracking. Initial studies demonstrate high accuracy, achieving the 95th-percentile gaze error < 0.45 deg across a cohort of 6 participants.

Peng Shurui, Xin Lin, Shi Luo et al.

Image restoration under diverse degradations remains challenging for unified all-in-one frameworks due to feature interference and insufficient expert specialization. We propose SLER-IR, a spherical layer-wise expert routing framework that dynamically activates specialized experts across network layers. To ensure reliable routing, we introduce a Spherical Uniform Degradation Embedding with contrastive learning, which maps degradation representations onto a hypersphere to eliminate geometry bias in linear embedding spaces. In addition, a Global-Local Granularity Fusion (GLGF) module integrates global semantics and local degradation cues to address spatially non-uniform degradations and the train-test granularity gap. Experiments on three-task and five-task benchmarks demonstrate that SLER-IR achieves consistent improvements over state-of-the-art methods in both PSNR and SSIM. Code and models will be publicly released.

Keito Suzuki, Bang Du, Girish Krishnan et al.

3D part segmentation is still an open problem in the field of 3D vision and AR/VR. Due to limited 3D labeled data, traditional supervised segmentation methods fall short in generalizing to unseen shapes and categories. Recently, the advancement in vision-language models' zero-shot abilities has brought a surge in open-world 3D segmentation methods. While these methods show promising results for 3D scenes or objects, they do not generalize well to 3D humans. In this paper, we present the first open-vocabulary segmentation method capable of handling 3D human. Our framework can segment the human category into desired fine-grained parts based on the textual prompt. We design a simple segmentation pipeline, leveraging SAM to generate multi-view proposals in 2D and proposing a novel HumanCLIP model to create unified embeddings for visual and textual inputs. Compared with existing pre-trained CLIP models, the HumanCLIP model yields more accurate embeddings for human-centric contents. We also design a simple-yet-effective MaskFusion module, which classifies and fuses multi-view features into 3D semantic masks without complex voting and grouping mechanisms. The design of decoupling mask proposals and text input also significantly boosts the efficiency of per-prompt inference. Experimental results on various 3D human datasets show that our method outperforms current state-of-the-art open-vocabulary 3D segmentation methods by a large margin. In addition, we show that our method can be directly applied to various 3D representations including meshes, point clouds, and 3D Gaussian Splatting.

Runfa Blark Li, Keito Suzuki, Bang Du et al.

A signed distance function (SDF) is a useful representation for continuous-space geometry and many related operations, including rendering, collision checking, and mesh generation. Hence, reconstructing SDF from image observations accurately and efficiently is a fundamental problem. Recently, neural implicit SDF (SDF-NeRF) techniques, trained using volumetric rendering, have gained a lot of attention. Compared to earlier truncated SDF (TSDF) fusion algorithms that rely on depth maps and voxelize continuous space, SDF-NeRF enables continuous-space SDF reconstruction with better geometric and photometric accuracy. However, the accuracy and convergence speed of scene-level SDF reconstruction require further improvements for many applications. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, several works have focused on improving SDF-NeRF by introducing consistency losses on depth and surface normals between 3DGS and SDF-NeRF. However, loss-level connections alone lead to incremental improvements. We propose a novel neural implicit SDF called "SplatSDF" to fuse 3DGSandSDF-NeRF at an architecture level with significant boosts to geometric and photometric accuracy and convergence speed. Our SplatSDF relies on 3DGS as input only during training, and keeps the same complexity and efficiency as the original SDF-NeRF during inference. Our method outperforms state-of-the-art SDF-NeRF models on geometric and photometric evaluation by the time of submission.

Runfa Blark Li, Mahdi Shaghaghi, Keito Suzuki et al.

Simultaneous Localization and Mapping (SLAM) is one of the most important environment-perception and navigation algorithms for computer vision, robotics, and autonomous cars/drones. Hence, high quality and fast mapping becomes a fundamental problem. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, state-of-the-art (SOTA) works introduce GS to SLAM. Compared to classical pointcloud-SLAM, GS-SLAM generates photometric information by learning from input camera views and synthesize unseen views with high-quality textures. However, these GS-SLAM fail when moving objects occupy the scene that violate the static assumption of bundle adjustment. The failed updates of moving GS affects the static GS and contaminates the full map over long frames. Although some efforts have been made by concurrent works to consider moving objects for GS-SLAM, they simply detect and remove the moving regions from GS rendering ("anti'' dynamic GS-SLAM), where only the static background could benefit from GS. To this end, we propose the first real-time GS-SLAM, "DynaGSLAM'', that achieves high-quality online GS rendering, tracking, motion predictions of moving objects in dynamic scenes while jointly estimating accurate ego motion. Our DynaGSLAM outperforms SOTA static & "Anti'' dynamic GS-SLAM on three dynamic real datasets, while keeping speed and memory efficiency in practice.

Runfa Li, Upal Mahbub, Vasudev Bhaskaran et al.

Current monocular 3D scene reconstruction (3DR) works are either fully-supervised, or not generalizable, or implicit in 3D representation. We propose a novel framework - MonoSelfRecon that for the first time achieves explicit 3D mesh reconstruction for generalizable indoor scenes with monocular RGB views by purely self-supervision on voxel-SDF (signed distance function). MonoSelfRecon follows an Autoencoder-based architecture, decodes voxel-SDF and a generalizable Neural Radiance Field (NeRF), which is used to guide voxel-SDF in self-supervision. We propose novel self-supervised losses, which not only support pure self-supervision, but can be used together with supervised signals to further boost supervised training. Our experiments show that "MonoSelfRecon" trained in pure self-supervision outperforms current best self-supervised indoor depth estimation models and is comparable to 3DR models trained in fully supervision with depth annotations. MonoSelfRecon is not restricted by specific model design, which can be used to any models with voxel-SDF for purely self-supervised manner.

Hung Nguyen, Blark Runfa Li, Truong Nguyen

Neural Radiance Fields (NeRF) has achieved superior performance in novel view synthesis and 3D scene representation, but its practical applications are hindered by slow convergence and reliance on dense training views. To this end, we present DWTNeRF, a unified framework based on Instant-NGP's fast-training hash encoding. It is coupled with regularization terms designed for few-shot NeRF, which operates on sparse training views. Our DWTNeRF additionally includes a novel Discrete Wavelet loss that allows explicit prioritization of low frequencies directly in the training objective, reducing few-shot NeRF's overfitting on high frequencies in earlier training stages. We also introduce a model-based approach, based on multi-head attention, that is compatible with INGP, which are sensitive to architectural changes. On the 3-shot LLFF benchmark, DWTNeRF outperforms Vanilla INGP by 15.07% in PSNR, 24.45% in SSIM and 36.30% in LPIPS. Our approach encourages a re-thinking of current few-shot approaches for fast-converging implicit representations like INGP or 3DGS.

Hung Nguyen, An Le, Runfa Li et al.

3D Gaussian Splatting has emerged as a powerful approach in novel view synthesis, delivering rapid training and rendering but at the cost of an ever-growing set of Gaussian primitives that strains memory and bandwidth. We introduce AutoOpti3DGS, a training-time framework that automatically restrains Gaussian proliferation without sacrificing visual fidelity. The key idea is to feed the input images to a sequence of learnable Forward and Inverse Discrete Wavelet Transforms, where low-pass filters are kept fixed, high-pass filters are learnable and initialized to zero, and an auxiliary orthogonality loss gradually activates fine frequencies. This wavelet-driven, coarse-to-fine process delays the formation of redundant fine Gaussians, allowing 3DGS to capture global structure first and refine detail only when necessary. Through extensive experiments, AutoOpti3DGS requires just a single filter learning-rate hyper-parameter, integrates seamlessly with existing efficient 3DGS frameworks, and consistently produces sparser scene representations more compatible with memory or storage-constrained hardware.

Hung Nguyen, Runfa Li, An Le et al.

Sparse-view 3D Gaussian Splatting (3DGS) presents significant challenges in reconstructing high-quality novel views, as it often overfits to the widely-varying high-frequency (HF) details of the sparse training views. While frequency regularization can be a promising approach, its typical reliance on Fourier transforms causes difficult parameter tuning and biases towards detrimental HF learning. We propose DWTGS, a framework that rethinks frequency regularization by leveraging wavelet-space losses that provide additional spatial supervision. Specifically, we supervise only the low-frequency (LF) LL subbands at multiple DWT levels, while enforcing sparsity on the HF HH subband in a self-supervised manner. Experiments across benchmarks show that DWTGS consistently outperforms Fourier-based counterparts, as this LF-centric strategy improves generalization and reduces HF hallucinations.

Lam Pham, Cam Le, Hieu Tang et al.

In recent years, landslide disasters have reported frequently due to the extreme weather events of droughts, floods , storms, or the consequence of human activities such as deforestation, excessive exploitation of natural resources. However, automatically observing landslide is challenging due to the extremely large observing area and the rugged topography such as mountain or highland. This motivates us to propose an end-to-end deep-learning-based model which explores the remote sensing images for automatically observing landslide events. By considering remote sensing images as the input data, we can obtain free resource, observe large and rough terrains by time. To explore the remote sensing images, we proposed a novel neural network architecture which is for two tasks of landslide detection and landslide segmentation. We evaluated our proposed model on three different benchmark datasets of LandSlide4Sense, Bijie, and Nepal. By conducting extensive experiments, we achieve F1 scores of 98.23, 93.83 for the landslide detection task on LandSlide4Sense, Bijie datasets; mIoU scores of 63.74, 76.88 on the segmentation tasks regarding LandSlide4Sense, Nepal datasets. These experimental results prove potential to integrate our proposed model into real-life landslide observation systems.

An Le, Nehal Mehta, William Freeman et al.

In this study, we developed deep learning-based method to classify the type of surgery performed for epiretinal membrane (ERM) removal, either internal limiting membrane (ILM) removal or ERM-alone removal. Our model, based on the ResNet18 convolutional neural network (CNN) architecture, utilizes postoperative optical coherence tomography (OCT) center scans as inputs. We evaluated the model using both original scans and scans preprocessed with energy crop and wavelet denoising, achieving 72% accuracy on preprocessed inputs, outperforming the 66% accuracy achieved on original scans. To further improve accuracy, we integrated tunable wavelet units with two key adaptations: Orthogonal Lattice-based Wavelet Units (OrthLatt-UwU) and Perfect Reconstruction Relaxation-based Wavelet Units (PR-Relax-UwU). These units allowed the model to automatically adjust filter coefficients during training and were incorporated into downsampling, stride-two convolution, and pooling layers, enhancing its ability to distinguish between ERM-ILM removal and ERM-alone removal, with OrthLattUwU boosting accuracy to 76% and PR-Relax-UwU increasing performance to 78%. Performance comparisons showed that our AI model outperformed a trained human grader, who achieved only 50% accuracy in classifying the removal surgery types from postoperative OCT scans. These findings highlight the potential of CNN based models to improve clinical decision-making by providing more accurate and reliable classifications. To the best of our knowledge, this is the first work to employ tunable wavelets for classifying different types of ERM removal surgery.

An Le, Hung Nguyen, Sungbal Seo et al.

This work introduces a novel biorthogonal tunable wavelet unit constructed using a lifting scheme that relaxes both the orthogonality and equal filter length constraints, providing greater flexibility in filter design. The proposed unit enhances convolution, pooling, and downsampling operations, leading to improved image classification and anomaly detection in convolutional neural networks (CNN). When integrated into an 18-layer residual neural network (ResNet-18), the approach improved classification accuracy on CIFAR-10 by 2.12% and on the Describable Textures Dataset (DTD) by 9.73%, demonstrating its effectiveness in capturing fine-grained details. Similar improvements were observed in ResNet-34. For anomaly detection in the hazelnut category of the MVTec Anomaly Detection dataset, the proposed method achieved competitive and wellbalanced performance in both segmentation and detection tasks, outperforming existing approaches in terms of accuracy and robustness.

Minh Ngoc Ta, Dong Cao Van, Duc-Anh Hoang et al.

The growing collaboration between humans and AI models in generative tasks has introduced new challenges in distinguishing between human-written, LLM-generated, and human--LLM collaborative texts. In this work, we collect a multilingual, multi-domain, multi-generator dataset FAIDSet. We further introduce a fine-grained detection framework FAID to classify text into these three categories, and also to identify the underlying LLM family of the generator. Unlike existing binary classifiers, FAID is built to capture both authorship and model-specific characteristics. Our method combines multi-level contrastive learning with multi-task auxiliary classification to learn subtle stylistic cues. By modeling LLM families as distinct stylistic entities, we incorporate an adaptation to address distributional shifts without retraining for unseen data. Our experimental results demonstrate that FAID outperforms several baselines, particularly enhancing the generalization accuracy on unseen domains and new LLMs, thus offering a potential solution for improving transparency and accountability in AI-assisted writing.

Shiwei Jin, Zhen Wang, Lei Wang et al.

Facial action unit (AU) intensity plays a pivotal role in quantifying fine-grained expression behaviors, which is an effective condition for facial expression manipulation. However, publicly available datasets containing intensity annotations for multiple AUs remain severely limited, often featuring a restricted number of subjects. This limitation places challenges to the AU intensity manipulation in images due to disentanglement issues, leading researchers to resort to other large datasets with pretrained AU intensity estimators for pseudo labels. In addressing this constraint and fully leveraging manual annotations of AU intensities for precise manipulation, we introduce AUEditNet. Our proposed model achieves impressive intensity manipulation across 12 AUs, trained effectively with only 18 subjects. Utilizing a dual-branch architecture, our approach achieves comprehensive disentanglement of facial attributes and identity without necessitating additional loss functions or implementing with large batch sizes. This approach offers a potential solution to achieve desired facial attribute editing despite the dataset's limited subject count. Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool. AUEditNet allows conditioning by either intensity values or target images, eliminating the need for constructing AU combinations for specific facial expression synthesis. Moreover, AU intensity estimation, as a downstream task, validates the consistency between real and edited images, confirming the effectiveness of our proposed AU intensity manipulation method.

Bang Du, Runfa Blark Li, Chen Du et al.

The reconstruction of 3D objects from calibrated photographs represents a fundamental yet intricate challenge in the domains of computer graphics and vision. Although neural reconstruction approaches based on Neural Radiance Fields (NeRF) have shown remarkable capabilities, their processing costs remain substantial. Recently, the advent of 3D Gaussian Splatting (3D-GS) largely improves the training efficiency and facilitates to generate realistic rendering in real-time. However, due to the limited ability of Spherical Harmonics (SH) to represent high-frequency information, 3D-GS falls short in reconstructing glossy objects. Researchers have turned to enhance the specular expressiveness of 3D-GS through inverse rendering. Yet these methods often struggle to maintain the training and rendering efficiency, undermining the benefits of Gaussian Splatting techniques. In this paper, we introduce GlossGau, an efficient inverse rendering framework that reconstructs scenes with glossy surfaces while maintaining training and rendering speeds comparable to vanilla 3D-GS. Specifically, we explicitly model the surface normals, Bidirectional Reflectance Distribution Function (BRDF) parameters, as well as incident lights and use Anisotropic Spherical Gaussian (ASG) to approximate the per-Gaussian Normal Distribution Function under the microfacet model. We utilize 2D Gaussian Splatting (2D-GS) as foundational primitives and apply regularization to significantly alleviate the normal estimation challenge encountered in related works. Experiments demonstrate that GlossGau achieves competitive or superior reconstruction on datasets with glossy surfaces. Compared with previous GS-based works that address the specular surface, our optimization time is considerably less.

Bo Wen, Anna Heinke, Akshay Agnihotri et al.

We identify two major limitations in the existing studies on retinal vessel segmentation: (1) Most existing works are restricted to one modality, i.e., the Color Fundus (CF). However, multi-modality retinal images are used every day in the study of the retina and diagnosis of retinal diseases, and the study of vessel segmentation on other modalities is scarce; (2) Even though a few works extended their experiments to new modalities such as the Multi-Color Scanning Laser Ophthalmoscopy (MC), these works still require fine-tuning a separate model for the new modality. The fine-tuning will require extra training data, which is difficult to acquire. In this work, we present a novel universal vessel segmentation model (URVSM) for multi-modality retinal images. In addition to performing the study on a much wider range of image modalities, we also propose a universal model to segment the vessels in all these commonly used modalities. While being much more versatile compared with existing methods, our universal model also demonstrates comparable performance to the state-of-the-art fine-tuned methods. To the best of our knowledge, this is the first work that achieves modality-agnostic retinal vessel segmentation and the first to study retinal vessel segmentation in several novel modalities.

Huong Hoang, Truong Nguyen, Pamela Cosman

The compression of real-world scanned 3D human dynamic meshes is an emerging research area, driven by applications such as telepresence, virtual reality, and 3D digital streaming. Unlike synthesized dynamic meshes with fixed topology, scanned dynamic meshes often not only have varying topology across frames but also scan defects such as holes and outliers, increasing the complexity of prediction and compression. Additionally, human meshes often combine rigid and non-rigid motions, making accurate prediction and encoding significantly more difficult compared to objects that exhibit purely rigid motion. To address these challenges, we propose a compression method designed for real-world scanned human dynamic meshes, leveraging embedded key nodes. The temporal motion of each vertex is formulated as a distance-weighted combination of transformations from neighboring key nodes, requiring the transmission of solely the key nodes' transformations. To enhance the quality of the KeyNode-driven prediction, we introduce an octree-based residual coding scheme and a Dual-direction prediction mode, which uses I-frames from both directions. Extensive experiments demonstrate that our method achieves significant improvements over the state-of-the-art, with an average bitrate savings of 58.43% across the evaluated sequences, particularly excelling at low bitrates.

Hung Nguyen, An Le, Truong Nguyen

3D Gaussian Splatting (3DGS) has emerged as a powerful approach for novel view synthesis. However, the number of Gaussian primitives often grows substantially during training as finer scene details are reconstructed, leading to increased memory and storage costs. Recent coarse-to-fine strategies regulate Gaussian growth by modulating the frequency content of the ground-truth images. In particular, AutoOpti3DGS employs the learnable Discrete Wavelet Transform (DWT) to enable data-adaptive frequency modulation. Nevertheless, its modulation depth is limited by the 1-level DWT, and jointly optimizing wavelet regularization with 3D reconstruction introduces gradient competition that promotes excessive Gaussian densification. In this paper, we propose a multi-level DWT-based frequency modulation framework for 3DGS. By recursively decomposing the low-frequency subband, we construct a deeper curriculum that provides progressively coarser supervision during early training, consistently reducing Gaussian counts. Furthermore, we show that the modulation can be performed using only a single scaling parameter, rather than learning the full 2-tap high-pass filter. Experimental results on standard benchmarks demonstrate that our method further reduces Gaussian counts while maintaining competitive rendering quality.

Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei et al.

Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets. Independent sampling often yields high-variance estimates, especially when rare but high-impact outcomes dominate the expectation. We propose a non-IID sampling framework that jointly draws multiple samples to cover diverse, salient regions of a flow matching model's generative distribution. To balance diversity and quality, we introduce a score-based regularization for the diversity mechanism (SR), which uses the score function, i.e., the gradient of the log probability, to ensure samples are pushed apart within high-density regions of the data manifold, mitigating off-manifold drift. To enable unbiased estimation when desired, we further develop an approach for importance weighting of non-IID flow samples by learning a residual velocity field that reproduces the marginal distribution of the non-IID samples and by evolving importance weights along trajectories. Empirically, our method produces diverse, high-quality samples and accurate estimates of both importance weights and expectations, advancing the reliable characterization of flow matching model outputs. Our code will be publicly available on GitHub.

Hung Nguyen, Runfa Li, An Le et al.

3D Gaussian Splatting (3DGS) has become a powerful representation for image-based object reconstruction, yet its performance drops sharply in sparse-view settings. Prior works address this limitation by employing diffusion models to repair corrupted renders, subsequently using them as pseudo ground truths for later optimization. While effective, such approaches incur heavy computation from the diffusion fine-tuning and repair steps. We present WaveletGaussian, a framework for more efficient sparse-view 3D Gaussian object reconstruction. Our key idea is to shift diffusion into the wavelet domain: diffusion is applied only to the low-resolution LL subband, while high-frequency subbands are refined with a lightweight network. We further propose an efficient online random masking strategy to curate training pairs for diffusion fine-tuning, replacing the commonly used, but inefficient, leave-one-out strategy. Experiments across two benchmark datasets, Mip-NeRF 360 and OmniObject3D, show WaveletGaussian achieves competitive rendering quality while substantially reducing training time.

Hieu Tang, Truong Vo, Dong Pham et al.

The use of satellite imagery combined with deep learning to support automatic landslide detection is becoming increasingly widespread. However, selecting an appropriate deep learning architecture to optimize performance while avoiding overfitting remains a critical challenge. To address these issues, we propose a deep-learning based framework for landslide detection from remote sensing image in this paper. The proposed framework presents an effective combination of the online an offline data augmentation to tackle the imbalanced data, a backbone EfficientNet\_Large deep learning model for extracting robust embedding features, and a post-processing SVM classifier to balance and enhance the classification performance. The proposed model achieved an F1-score of 0.8938 on the public test set of the Zindi challenge.

Khang Truong, Lam Pham, Hieu Tang et al.

Image captioning has emerged as a crucial task in the intersection of computer vision and natural language processing, enabling automated generation of descriptive text from visual content. In the context of remote sensing, image captioning plays a significant role in interpreting vast and complex satellite imagery, aiding applications such as environmental monitoring, disaster assessment, and urban planning. This motivates us, in this paper, to present a transformer based network architecture for remote sensing image captioning (RSIC) in which multiple techniques of Static Expansion, Memory-Augmented Self-Attention, Mesh Transformer are evaluated and integrated. We evaluate our proposed models using two benchmark remote sensing image datasets of UCM-Caption and NWPU-Caption. Our best model outperforms the state-of-the-art systems on most of evaluation metrics, which demonstrates potential to apply for real-life remote sensing image systems.

Keito Suzuki, Bang Du, Runfa Blark Li et al.

Understanding dynamic 3D human representation has become increasingly critical in virtual and extended reality applications. However, existing human part segmentation methods are constrained by reliance on closed-set datasets and prolonged inference times, which significantly restrict their applicability. In this paper, we introduce the first 4D human parsing framework that simultaneously addresses these challenges by reducing the inference time and introducing open-vocabulary capabilities. Building upon state-of-the-art open-vocabulary 3D human parsing techniques, our approach extends the support to 4D human-centric video with three key innovations: 1) We adopt mask-based video object tracking to efficiently establish spatial and temporal correspondences, avoiding the necessity of segmenting all frames. 2) A novel Mask Validation module is designed to manage new target identification and mitigate tracking failures. 3) We propose a 4D Mask Fusion module, integrating memory-conditioned attention and logits equalization for robust embedding fusion. Extensive experiments demonstrate the effectiveness and flexibility of the proposed method on 4D human-centric parsing tasks, achieving up to 93.3% acceleration compared to the previous state-of-the-art method, which was limited to parsing fixed classes.

Shiwei Jin, Zhen Wang, Lei Wang et al.

Learning-based gaze estimation methods require large amounts of training data with accurate gaze annotations. Facing such demanding requirements of gaze data collection and annotation, several image synthesis methods were proposed, which successfully redirected gaze directions precisely given the assigned conditions. However, these methods focused on changing gaze directions of the images that only include eyes or restricted ranges of faces with low resolution (less than $128\times128$) to largely reduce interference from other attributes such as hairs, which limits application scenarios. To cope with this limitation, we proposed a portable network, called ReDirTrans, achieving latent-to-latent translation for redirecting gaze directions and head orientations in an interpretable manner. ReDirTrans projects input latent vectors into aimed-attribute embeddings only and redirects these embeddings with assigned pitch and yaw values. Then both the initial and edited embeddings are projected back (deprojected) to the initial latent space as residuals to modify the input latent vectors by subtraction and addition, representing old status removal and new status addition. The projection of aimed attributes only and subtraction-addition operations for status replacement essentially mitigate impacts on other attributes and the distribution of latent vectors. Thus, by combining ReDirTrans with a pretrained fixed e4e-StyleGAN pair, we created ReDirTrans-GAN, which enables accurately redirecting gaze in full-face images with $1024\times1024$ resolution while preserving other attributes such as identity, expression, and hairstyle. Furthermore, we presented improvements for the downstream learning-based gaze estimation task, using redirected samples as dataset augmentation.

Runfa Li, Truong Nguyen

Mapping and 3D detection are two major issues in vision-based robotics, and self-driving. While previous works only focus on each task separately, we present an innovative and efficient multi-task deep learning framework (SM3D) for Simultaneous Mapping and 3D Detection by bridging the gap with robust depth estimation and "Pseudo-LiDAR" point cloud for the first time. The Mapping module takes consecutive monocular frames to generate depth and pose estimation. In 3D Detection module, the depth estimation is projected into 3D space to generate "Pseudo-LiDAR" point cloud, where LiDAR-based 3D detector can be leveraged on point cloud for vehicular 3D detection and localization. By end-to-end training of both modules, the proposed mapping and 3D detection method outperforms the state-of-the-art baseline by 10.0% and 13.2% in accuracy, respectively. While achieving better accuracy, our monocular multi-task SM3D is more than 2 times faster than pure stereo 3D detector, and 18.3% faster than using two modules separately.

Runfa Li, Truong Nguyen

Real-scale scene flow estimation has become increasingly important for 3D computer vision. Some works successfully estimate real-scale 3D scene flow with LiDAR. However, these ubiquitous and expensive sensors are still unlikely to be equipped widely for real application. Other works use monocular images to estimate scene flow, but their scene flow estimations are normalized with scale ambiguity, where additional depth or point cloud ground truth are required to recover the real scale. Even though they perform well in 2D, these works do not provide accurate and reliable 3D estimates. We present a deep learning architecture on permutohedral lattice - MonoPLFlowNet. Different from all previous works, our MonoPLFlowNet is the first work where only two consecutive monocular images are used as input, while both depth and 3D scene flow are estimated in real scale. Our real-scale scene flow estimation outperforms all state-of-the-art monocular-image based works recovered to real scale by ground truth, and is comparable to LiDAR approaches. As a by-product, our real-scale depth estimation also outperforms other state-of-the-art works.

Dat Ngo, Lam Pham, Anh Nguyen et al.

This paper proposes a robust deep learning framework used for classifying anomaly of respiratory cycles. Initially, our framework starts with front-end feature extraction step. This step aims to transform the respiratory input sound into a two-dimensional spectrogram where both spectral and temporal features are well presented. Next, an ensemble of C- DNN and Autoencoder networks is then applied to classify into four categories of respiratory anomaly cycles. In this work, we conducted experiments over 2017 Internal Conference on Biomedical Health Informatics (ICBHI) benchmark dataset. As a result, we achieve competitive performances with ICBHI average score of 0.49, ICBHI harmonic score of 0.42.

Truong Nguyen, Guangye Chen, Luis Chacon

We propose an Anderson Acceleration (AA) scheme for the adaptive Expectation-Maximization (EM) algorithm for unsupervised learning a finite mixture model from multivariate data (Figueiredo and Jain 2002). The proposed algorithm is able to determine the optimal number of mixture components autonomously, and converges to the optimal solution much faster than its non-accelerated version. The success of the AA-based algorithm stems from several developments rather than a single breakthrough (and without these, our tests demonstrate that AA fails catastrophically). To begin, we ensure the monotonicity of the likelihood function (a the key feature of the standard EM algorithm) with a recently proposed monotonicity-control algorithm (Henderson and Varahdan 2019), enhanced by a novel monotonicity test with little overhead. We propose nimble strategies for AA to preserve the positive definiteness of the Gaussian weights and covariance matrices strictly, and to conserve up to the second moments of the observed data set exactly. Finally, we employ a K-means clustering algorithm using the gap statistic to avoid excessively overestimating the initial number of components, thereby maximizing performance. We demonstrate the accuracy and efficiency of the algorithm with several synthetic data sets that are mixtures of Gaussians distributions of known number of components, as well as data sets generated from particle-in-cell simulations. Our numerical results demonstrate speed-ups with respect to non-accelerated EM of up to 60X when the exact number of mixture components is known, and between a few and more than an order of magnitude with component adaptivity.

Chen Du, Byeongkeun Kang, Zheng Xu et al.

De-fencing is to eliminate the captured fence on an image or a video, providing a clear view of the scene. It has been applied for many purposes including assisting photographers and improving the performance of computer vision algorithms such as object detection and recognition. However, the state-of-the-art de-fencing methods have limited performance caused by the difficulty of fence segmentation and also suffer from the motion of the camera or objects. To overcome these problems, we propose a novel method consisting of segmentation using convolutional neural networks and a fast/robust recovery algorithm. The segmentation algorithm using convolutional neural network achieves significant improvement in the accuracy of fence segmentation. The recovery algorithm using optical flow produces plausible de-fenced images and videos. The proposed method is experimented on both our diverse and complex dataset and publicly available datasets. The experimental results demonstrate that the proposed method achieves the state-of-the-art performance for both segmentation and content recovery.

Subarna Tripathi, Gokce Dane, Byeongkeun Kang et al.

Deep convolutional Neural Networks (CNN) are the state-of-the-art performers for object detection task. It is well known that object detection requires more computation and memory than image classification. Thus the consolidation of a CNN-based object detection for an embedded system is more challenging. In this work, we propose LCDet, a fully-convolutional neural network for generic object detection that aims to work in embedded systems. We design and develop an end-to-end TensorFlow(TF)-based model. Additionally, we employ 8-bit quantization on the learned weights. We use face detection as a use case. Our TF-Slim based network can predict different faces of different shapes and sizes in a single forward pass. Our experimental results show that the proposed method achieves comparative accuracy comparing with state-of-the-art CNN-based face detection methods, while reducing the model size by 3x and memory-BW by ~4x comparing with one of the best real-time CNN-based object detector such as YOLO. TF 8-bit quantized model provides additional 4x memory reduction while keeping the accuracy as good as the floating point model. The proposed model thus becomes amenable for embedded implementations.

Subarna Tripathi, Zachary C. Lipton, Serge Belongie et al.

Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial frame-level variability, even in videos that appear smooth to the eye. Additionally, video datasets tend to have sparsely annotated frames. We present a new framework for improving object detection in videos that captures temporal context and encourages consistency of predictions. First, we train a pseudo-labeler, that is, a domain-adapted convolutional neural network for object detection. The pseudo-labeler is first trained individually on the subset of labeled frames, and then subsequently applied to all frames. Then we train a recurrent neural network that takes as input sequences of pseudo-labeled frames and optimizes an objective that encourages both accuracy on the target frame and consistency across consecutive frames. The approach incorporates strong supervision of target frames, weak-supervision on context frames, and regularization via a smoothness penalty. Our approach achieves mean Average Precision (mAP) of 68.73, an improvement of 7.1 over the strongest image-based baselines for the Youtube-Video Objects dataset. Our experiments demonstrate that neighboring frames can provide valuable information, even absent labels.

Subarna Tripathi, Serge Belongie, Youngbae Hwang et al.

Object proposals for detecting moving or static video objects need to address issues such as speed, memory complexity and temporal consistency. We propose an efficient Video Object Proposal (VOP) generation method and show its efficacy in learning a better video object detector. A deep-learning based video object detector learned using the proposed VOP achieves state-of-the-art detection performance on the Youtube-Objects dataset. We further propose a clustering of VOPs which can efficiently be used for detecting objects in video in a streaming fashion. As opposed to applying per-frame convolutional neural network (CNN) based object detection, our proposed method called Objects in Video Enabler thRough LAbel Propagation (OVERLAP) needs to classify only a small fraction of all candidate proposals in every video frame through streaming clustering of object proposals and class-label propagation. Source code will be made available soon.

Subarna Tripathi, Serge Belongie, Truong Nguyen

We explore the efficiency of the CRF inference module beyond image level semantic segmentation. The key idea is to combine the best of two worlds of semantic co-labeling and exploiting more expressive models. Similar to [Alvarez14] our formulation enables us perform inference over ten thousand images within seconds. On the other hand, it can handle higher-order clique potentials similar to [vineet2014] in terms of region-level label consistency and context in terms of co-occurrences. We follow the mean-field updates for higher order potentials similar to [vineet2014] and extend the spatial smoothness and appearance kernels [DenseCRF13] to address video data inspired by [Alvarez14]; thus making the system amenable to perform video semantic segmentation most effectively.

Subarna Tripathi, Youngbae Hwang, Serge Belongie et al.

Despite recent advances in video segmentation, many opportunities remain to improve it using a variety of low and mid-level visual cues. We propose improvements to the leading streaming graph-based hierarchical video segmentation (streamGBH) method based on early and mid level visual processing. The extensive experimental analysis of our approach validates the improvement of hierarchical supervoxel representation by incorporating motion and color with effective filtering. We also pose and illuminate some open questions towards intermediate level video analysis as further extension to streamGBH. We exploit the supervoxels as an initialization towards estimation of dominant affine motion regions, followed by merging of such motion regions in order to hierarchically segment a video in a novel motion-segmentation framework which aims at subsequent applications such as foreground recognition.