CNN
-
Semantic Video Communication via Multi-Scale Convolution and Dynamic Routing for Next-Generation Networks
2026-07-06 13:52:46Gengtian Shi, Jinze Yu, Chenhao Wu, Shaofei Wang, Eiji Fukuzawa, Junjie Tang, Hiroshi Onoda, Jiang LiuAbstract
The exponential growth of video traffic demands novel semantic communication paradigms that transmit meaning rather than raw bits. We present a generative AI-enabled framework for semantic video communication addressing two critical challenges: efficient hierarchical temporal modeling for bandwidth-constrained transmission and robust semantic alignment between video content and natural language queries at network edge devices. Our approach introduces a multi-scale temporal convolutional encoder that captures motion patterns across different temporal granularities with O(T) complexity suitable for resource-constrained IoT deployments. We further propose a capsule-based dynamic routing mechanism that iteratively refines segment-query associations, enabling flexible modeling of non-monotonic semantic alignments essential for goal-oriented communication. These components are unified through a multi-task learning objective optimizing temporal boundary regression, cross-modal alignment, and capsule diversity. Experiments on ActivityNet Captions demonstrate significant improvements, achieving 42.9% Recall@0.5 and 41.1% mean IoU while maintaining computational efficiency critical for edge deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2607.05093
PDF
-
Unsupervised Detection of Underground Tunnels in Ground-Penetrating Radar Using Depth-Restricted Reconstruction Scoring
2026-07-06 10:02:37Muhammad Junaid, Shoab A. Khan, Nisar AhmedAbstract
Clandestine tunneling beneath oil and gas pipelines enables fuel theft, smuggling, and sabotage, yet conventional monitoring detects damage only after a pipeline has been compromised. Ground-penetrating radar (GPR) can image such tunnels non-invasively, but manual radargram interpretation does not scale to continuous corridor surveillance, and supervised detectors require tunnel examples that are scarce in practice. We present a fully unsupervised detection pipeline trained exclusively on normal subsurface radargrams collected at a purpose-built field site containing three buried tunnels at 1.5-3 m depth. A denoising convolutional autoencoder learns the structure of anomaly-free ground; at inference, tunnels are flagged by reconstruction error. Our central contribution is a depth-restricted top-k anomaly score, which pools the highest reconstruction errors only within the depth band where tunnels can physically occur. This physically motivated rule raises AUC from 0.986 to 0.994 and cuts missed detections from 74 to 17 of 634 tunnel windows, relative to whole-image scoring, without any retraining or labels. We further show that the optimal top-k fraction interacts with the depth restriction - 1% pooling is best on full images, 5% once scoring is depth-restricted - and that spatial voting across overlapping survey windows helps weak per-image detectors but offers no benefit once the scoring rule is strong. The final system attains AUC 0.994, F1 0.975, recall 0.973, and precision 0.976 on 1,600 field test windows spanning 55 survey lines, at a 1.6% false-alarm rate, using no tunnel labels for training, scoring, or threshold calibration.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04882
PDF
-
A Task-Driven Evaluation of UAV Detection and Tracking under Synthetic Fog
2026-07-06 07:06:37Amir Pouladi, Vesal Ahsani, Haijun Li, Homayoun Najjaran, Afzal SulemanAbstract
Fog severely degrades the visibility of small unmanned aerial vehicles (UAVs) in skydominant, long-range imagery, reducing the reliability of downstream detection and tracking. This paper presents a task-driven evaluation framework that links depth-aware synthetic fog generation, image restoration, object detection, and tracking within a unified pipeline. Given the practical difficulty of collecting and annotating foggy UAV scenes, synthetic fog is generated from real clear-weather outdoor images containing UAV targets using monocular depth estimation and the atmospheric scattering model. Representative restoration methods from classical, convolutional neural network (CNN)-based, and transformer-based families are first compared, after which the selected restoration model is integrated into the downstream perception pipeline. Detection is evaluated under both clean-only and fog-inclusive training regimes using multiple detector variants, while tracking-by-detection is assessed on clean, foggy, and restored video sequences. Beyond image-level restoration metrics, the study evaluates how fog and restoration affect detection robustness and tracking performance. The results show that fog substantially degrades both detection and tracking, primarily through increased missed detections. Fog-inclusive training provides the most consistent improvement in robustness, whereas test-time restoration is most beneficial when the detector has been trained only on clean imagery. These findings show that restoration quality does not necessarily translate into proportional gains in downstream perception and therefore should be evaluated jointly with detection and tracking performance.
Abstract (translated)
URL
https://arxiv.org/abs/2607.05467
PDF
-
A non-invasive video-based method for individual identification of wildlife using gait dynamics
2026-07-05 21:47:21Muhammad Aamir, Matthew Wijers, Sangyun Shin, Andrew Loveridge, Andrew MarkhamAbstract
Gait is a distinctive behavioral characteristic that enables non-invasive individual identification without requiring physical interaction with an animal. While gait-based analysis has been extensively studied in humans, its application to wildlife remains limited due to environmental variability and the lack of scalable identification methods. This paper presents a fully automated, video-based pipeline for wildlife gait analysis and individual identification using deep spatiotemporal representation learning. The proposed pipeline uses the Segment Anything Model 3 (SAM3) to generate high-quality RGB and binary silhouette masks, robustly isolating animals from complex natural backgrounds. Segmented video sequences are processed using a convolutional neural network (ResNet18) for spatial feature extraction and a transformer-based video model (VideoPrism) for temporal motion modeling. Both models are fine-tuned using a classification objective and subsequently used as feature extractors to generate discriminative gait representations. Cosine similarity is then used to compare gait signatures, enabling similarity-based clustering of individuals without reliance on physical markings or invasive tagging. Experiments conducted on multi-source wildlife video data across multiple species demonstrate strong intra-individual consistency and clear inter-individual separation. Quantitative results using cosine similarity distributions and silhouette scores confirm the effectiveness of the proposed method. These findings demonstrate that gait dynamics provide a viable, non-invasive approach for individual identification in wildlife and highlight the potential of video-based deep learning pipelines for scalable ecological monitoring.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04518
PDF
-
PulmoSight-XAI: An Explainable Multi-View Attention Ensemble with Gradient Boosting Meta-Learning for Multi-Label Chest X-Ray Classification
2026-07-05 19:50:53Moshiur Rahman, Shafqat Alam, Tasnia Binte MamunAbstract
Automated chest X-ray classification remains challenging due to severe class imbalance, co-occurring pathologies, and the loss of localized features in conventional architectures. To address these, we propose an explainable hierarchical multi-view ensemble framework for the robust classification of 14 thoracic pathologies. The framework employs view-specific training by independently modeling frontal and lateral radiographs using an ensemble of five complementary convolutional neural networks. Replacing global average pooling, a multi-scale feature fusion strategy augmented with Convolutional Block Attention Modules (CBAM) preserves fine-grained intermediate representations while emphasizing high-level pathology-specific semantic features. To mitigate positive-negative imbalance and varying inter-class difficulty, models are optimized using a novel hybrid objective combining Asymmetric Loss with Adaptive Focal Loss. Beyond simple probability averaging, the framework incorporates a hierarchical meta-learning strategy where test-time augmentation (TTA) predictions and cross-model uncertainty measures are integrated into Level-1 gradient-boosting meta-learners (XGBoost, LightGBM, and CatBoost), followed by Level-2 stacking with optimized alpha blending. Evaluated on a large-scale CheXpert-style dataset, the framework achieves state-of-the-art macro-average AUROC scores of 0.9319 for frontal and 0.9154 for lateral radiographs. Furthermore, comprehensive explainability analysis using seven post-hoc attribution techniques demonstrates strong anatomical consistency and clinically meaningful decision localization. By integrating architectural diversity, multi-scale attention, hierarchical meta-learning, and rigorous explainability, the proposed framework provides a transparent, highly accurate, and clinically practical computer-aided diagnosis system for thoracic disease classification.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04478
PDF
-
Robustness Verification of an Autonomous Underwater Vehicle-based Plankton Classifier
2026-07-05 18:32:59Abdelrahman Sayed Sayed, Pierre-Jean Meyer, Asgeir J. S{\o}rensen, Mohamed GhazelAbstract
The assessment of planktonic standing stocks and microorganism structures is critical for understanding upper ocean biological processes. Currently, autonomous underwater vehicles (AUVs) equipped with in-situ optical imaging and artificial intelligence (AI) methods offer a promising solution for persistent surveillance, mapping and monitoring of planktonic life. However, current AI methods often lack robustness in dynamic, unstructured environments, where environmental noise and non-biological artifacts lead to frequent misclassifications. Standard convolutional neural network (CNN) classifiers often struggle with such conditions, leading to misclassifications that require time-consuming manual validation by marine biologists. To address this issue, we propose a novel robustness verification framework for in-situ plankton classifiers based on reachability analysis. We also introduce a continuous-time neural ordinary differential equation (neural ODE) classification model leveraging the high-resolution imaging capabilities of the SilCam particle imager. In this paper, we demonstrate the effectiveness of the proposed framework by formally verifying the robustness of the neural ODE model against environmental perturbations. We demonstrate that our verification framework acts as an automated filter providing formal guarantees of model stability against ambiguous data, thereby improving the reliability of autonomous sampling and reducing the post-processing workload.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04453
PDF
-
CoFINN: Conservation Flux Informed Neural Networks for Physics Problems Governed by Conservation Laws
2026-07-05 15:21:12Adnan Harun Do\u{g}an, Mert Deniz, Hande Alemdar, \"Ozg\"ur U\u{g}ra\c{s} BaranAbstract
We present CoFINN (Conservation Flux Informed Neural Networks), a physics-informed deep learning framework for predicting compressible flow fields governed by conservation laws. Unlike conventional data-driven convolutional neural networks (CNNs), which optimize only pixel-wise similarity metrics, CoFINN embeds finite-volume conservation physics directly into the training process. Unlike classical physics-informed methods which enforce differential-equation residuals at collocation points through automatic differentiation, CoFINN adopts a finite-volume perspective consistent with modern CFD methodology. CoFINN interprets CNN output fields as structured computational grids, where each pixel represents a finite-volume cell, and enforces conservation consistency through sophisticated numerical flux calculations. The framework is evaluated on transonic flow prediction around airfoils at (M=0.7, Re=6 * 10^6), including challenging conditions involving shock waves and high angles of attack. Results show that CoFINN improves aerodynamic force prediction accuracy, reducing drag prediction error by up to 34% at extreme angles of attack and by approximately 15% on average across the test set. Improvements are particularly significant in limited-data regimes, demonstrating that the conservation-based loss acts as an effective physical regularizer. The proposed approach maintains the computational efficiency advantages of CNN surrogates while significantly improving physical consistency and conservation behavior. The framework is architecture-agnostic and extensible to broader classes of conservation-law-governed physical systems.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06587
PDF
-
EEG-Based Imagined Speech Decoding Using a Hybrid CNN-SNN Architecture
2026-07-04 12:23:46Fatima Shalhoub, Mariam Al Mawla, Kabalan Chaccour, Iv\'an L\'opez-Espejo, Hoda FaresAbstract
Imagined speech decoding using EEG signals has emerged as a promising frontier in brain-computer interface (BCI) research, particularly to restore communication for individuals with severe speech impairments. However, decoding imagined speech remains a complex task due to the non-stationary, low-amplitude, and highly variable nature of EEG signals. Existing methods often rely on classical machine learning or deep learning models that fail to exploit spike-based temporal dynamics or event-driven firing mechanisms of biological neurons, which are naturally modeled by spiking neural networks (SNNs). In this study, we propose a hybrid decoding pipeline that extracts temporal representations using convolutional neural networks (CNNs) followed by biologically inspired temporal classification via SNNs. To our knowledge, this is the first study to integrate SNNs into EEG-based imagined speech decoding. Experimental results show that the proposed CNN-SNN architecture achieves an accuracy of 80.13% on the 2020 BCI Competition III benchmark, surpassing existing methods reported in the literature (up to 70.19%) under comparable evaluation settings. These findings demonstrate the effectiveness of spike-based temporal decoding for imagined speech, highlighting the promise of biologically grounded pipelines for next generation neuromorphic BCI applications.
Abstract (translated)
URL
https://arxiv.org/abs/2607.03844
PDF
-
HyperDCM: Dynamic Cluster Memory Replay in Hyperbolic Space for Continual Robotic Navigation Across Scenes
2026-07-04 01:21:12Zhengfei Lu, Jian Yang, Muyu Wang, Shaowen Chen, Jinpeng Mi, Ke Li, Xiong You, Qi Wu, Xuan Tang, Xian WeiAbstract
Continual learning in visual navigation remains challenging due to catastrophic forgetting and the difficulties associated with adapting to diverse and evolving environments. To address these issues, we propose Hyperbolic Dynamic Cluster Memory (HyperDCM), a structure-aware memory mechanism that enhances diffusion policy-based navigation through scene graph modeling and principled memory replay. HyperDCM extracts semantic scene triples from RGB observations using large vision-language models, encodes them into scene graph embeddings via a Relational Graph Convolutional Network (R-GCN), and projects the embeddings into hyperbolic space to enhance structural separability and retention in continual navigation. A dynamic clustering and structure-sensitive update strategy selects representative samples for memory replay, thereby preserving knowledge diversity and mitigating catastrophic forgetting. Experiments on multi-scene indoor and outdoor datasets demonstrate that HyperDCM achieves superior retention of past navigation capabilities and improved generalization compared to representative continual learning baselines adapted to diffusion policy navigation.
Abstract (translated)
URL
https://arxiv.org/abs/2607.16267
PDF
-
Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing
2026-07-03 23:54:52Ayush Prasad, Swarnalee MazumderAbstract
Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, radar, gravity, and elemental composition. Yet these datasets remain fragmented across archives, and no benchmark exists for evaluating machine learning on lunar data. We introduce Moonstone, the first multi-modal foundation model benchmark for lunar remote sensing. Our contributions are: (1) a 28-channel, 128 pixels-per-degree (~237 m) global lunar pretraining dataset from seven instrument families across five missions, (2) MG-MAE, a modality-grouped masked autoencoder with per-group convolutional tokenizers, a shared Vision Transformer encoder, attention masking for missing modalities, coverage-adaptive masking for heterogeneous spatial coverage, and spectral continuity regularization for physically plausible reconstructions, and (3) a benchmark of six downstream tasks covering classification, regression, and segmentation. MG-MAE pretrained features outperform scratch baselines on all tasks and surpass both ImageNet-pretrained and vanilla MAE baselines by large margins. Data and code are available at this https URL and this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2607.03644
PDF
-
When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures
2026-07-03 19:47:07Mojtaba Faramarzi, Alex Lamb, Irina RishAbstract
Diffusion architectures now encompass convolutional UNets as well as transformer-based designs such as Diffusion Transformers (DiTs), inspired by Vision Transformers (ViTs), yet the effects of structured geometric perturbations within these architectures remain poorly understood. We study this question through a unified framework that applies reflection-based elements of the dihedral group to intermediate hidden states as controlled internal interventions, contrasting geometrically consistent and inconsistent variants. Using activation-level diagnostics, including Self-Consistency Shift (SCS), Activation Mass Scatter (AMS), and Drift, we analyze feature stability and geometric drift. We find that consistent transformations improve stability, while inconsistent ones induce predictable, architecture-specific failures. In the main Stable Diffusion 2.1 U-Net study, we evaluate seven intervention modes over three seeds and complement the internal diagnostics with image-level FID, KID, CLIP score, and LPIPS diversity. Taken together with supporting ViT and controlled DiT analyses, these results establish geometric consistency as a key principle for stable hidden-state interventions in spatially structured vision and diffusion models.
Abstract (translated)
URL
https://arxiv.org/abs/2607.03580
PDF
-
Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
2026-07-03 13:26:00Sarthak Choudhary, Atharv Singh Patlan, Nils Palumbo, Ashish Hooda, Kassem Fawaz, Somesh JhaAbstract
We present Sparse Backdoor, a supply-chain attack that plants a provably undetectable backdoor in pre-trained image classifiers, including convolutional networks and Vision Transformers. The attack injects a structured sparse perturbation along a randomly chosen direction into a small subset of columns at each fully connected layer, propagating a trigger signal to an adversary-chosen target class, and masks the perturbation with an independent isotropic Gaussian dither. The dither serves a single technical purpose: it induces a clean reference distribution anchored at the pre-trained weights, against which undetectability can be formalized. Under a mild margin condition on the pre-trained classifier, we show that the dithered reference is functionally equivalent to the original classifier. We prove that distinguishing the backdoor-injected model from this reference is at least as hard as Sparse PCA detection, which is computationally infeasible under standard hardness assumptions. The guarantee holds against any probabilistic polynomial-time distinguisher with white-box access to the parameters.
Abstract (translated)
URL
https://arxiv.org/abs/2605.04209
PDF
-
Seeing Through WiFi: Lightweight Human Pose Estimation with Dynamic Kernel Attention
2026-07-03 11:04:05Toan D. Gian, Van-Dinh Nguyen, Vo Phi Son, Nhan Thanh Nguyen, Dinh Thai Hoang, Diep N. Nguyen, Nguyen Cong Luong, Symeon ChatzinotasAbstract
WiFi-based human pose estimation (HPE) enables the detection and interpretation of human body positions and movements without the need for wearable devices while preserving individual privacy concerns. Implementing this solution requires enhancing model performance and maintaining efficiency, especially on resource-constrained devices. This paper introduces a novel framework, WiLHPE, for lightweight and efficient human pose estimation using WiFi CSI signals. Empowered by a camera-based model during training, WiLHPE processes raw WiFi signals directly to estimate human poses in the testing phase. It employs a novel neural network architecture to dynamically learn convolutional kernels and apply attention mechanisms across channel and frequency spaces. This innovative method diversifies the kernels to improve the recognition capabilities of WiFi signals without adding complexity, ensuring efficiency. Additionally, the Tree-Structured Parzen Estimator algorithm is employed to optimize the critical hyperparameters of the neural network efficiently, minimizing the time required for optimal hyperparameter search compared to heuristic methods. Results from experiments on both the MM-Fi and WiPose datasets highlight the superiority of WiLHPE over state-of-the-art approaches, achieving 85.96% and 94.27% at PCK50, respectively, with minimal computational overhead. Notably, WiLHPE performs impressively even under challenging conditions, maintaining around 80% at PCK50 under AWGN noise with an error variance of 0.5.
Abstract (translated)
URL
https://arxiv.org/abs/2607.03196
PDF
-
Attention-Guided Efficientnet Architecture For Precise Criminal Identification in Surveillance Images
2026-07-03 08:09:27Savitha N J, Lata B TAbstract
Criminal identification from surveillance imagery has become a critical research area in intelligent forensic surveillance systems due to the increasing deployment of CCTV cameras in public and private environments. However, surveillance-based face recognition remains highly challenging because of low image resolution, illumination variation, motion blur, pose changes, facial occlusion, and background clutter. To address these limitations, this paper proposes an Attention-Guided EfficientNet (AG-EfficientNet) framework for precise criminal identification in surveillance images. The proposed framework integrates EfficientNet-B0 with Convolutional Block Attention Modules (CBAM) to enhance discriminative facial feature learning under degraded surveillance conditions. In addition, a multi-scale surveillance feature fusion strategy is introduced to preserve both local texture information and high-level semantic identity representations. A hybrid Softmax-Triplet optimization mechanism is further employed to improve inter-class separability and intra-class compactness for robust criminal identity discrimination. The proposed framework was experimentally evaluated using the Labeled Faces in the Wild (LFW) and SCFace datasets. Experimental results demonstrate that the proposed AG-EfficientNet framework achieved superior surveillance recognition performance with an identification accuracy of 98.2%, Precision of 97.9%, Recall of 97.6%, F1-Score of 97.7%, and ROC-AUC of 0.99, outperforming conventional deep learning architectures including AlexNet, VGG16, ResNet50, MobileNetV2, and standard EfficientNet-B0. Furthermore, Grad-CAM visualization and ablation analysis confirm the effectiveness of the proposed attention-guided feature learning strategy.
Abstract (translated)
URL
https://arxiv.org/abs/2607.03073
PDF
-
EEG-to-Report: An Annotation and Feature-Text Framework for Training Language Models on Clinical EEG
2026-07-03 07:44:36Xuan-The Tran, Le Trung Kien NguyenAbstract
Clinical electroencephalography (EEG) reporting remains largely manual and time-consuming, and current EEG software ecosystems do not produce the structured EEG-text supervision needed for training modern language models. Most toolboxes focus on visualization or preprocessing, providing limited support for workflows that generate high-quality datasets for AI. We introduce EEG-to-Report, a browser-based annotation and feature-text framework that links routine EEG review with the construction of AI-ready datasets. The framework integrates multi-format EEG ingestion, channel standardization, and an interactive viewer with a multimodal annotation layer that combines typed text and transcribed voice notes. For each annotated segment, a feature extraction engine computes a standardized set of spectral, temporal, entropy, Hjorth, connectivity, and spike-related descriptors, stored alongside clinical descriptions in a portable JSON schema. This yields aligned feature-text pairs designed to supervise multimodal EEG-language models. The framework also includes an auto-report module that couples an ensemble of convolutional networks with a large language model to draft clinical narratives for neurologist review. Using pilot annotations, we describe how EEG-to-Report streamlines annotation workflows and produces editable draft reports, providing a reusable foundation for automated EEG reporting systems.
Abstract (translated)
URL
https://arxiv.org/abs/2608.26153
PDF
-
MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model
2026-07-03 06:46:45Wanshu Fan, Xiangyu Li, Cong Wang, Kin-man Lam, Xin Yang, Haiyan Zhang, Dongsheng ZhouAbstract
Images captured by consumer electronic devices, such as mobile phones and digital cameras, often suffer from low-light degradation due to sensor limitations and imaging pipelines, which degrades visual quality and affects downstream vision tasks. Existing methods based on Convolutional Neural Networks (CNNs) and Transformers have dominated current low-light image enhancement (LIE) due to their excellent ability to model hierarchical features. However, CNNs operate in local receptive fields that cannot model long-range dependencies, while Transformers overcome this problem but incur substantial computational costs. To address these challenges, we propose MambaLIE, a Scene Light Intensity-Boosted Low-Light Image Enhancement method based on a State Space Model (SSM). We first introduce scene light intensity to improve the structural distribution of illumination, which is then gated with the low-light input to guide enhancement. To better model the illumination while maintaining computational efficiency, we propose the Locally Enhanced State Space Model (LESSM) for efficient light enhancement. Our LESSM contains two branches: an SSM branch and a Local Enhanced branch, where the former is used to model the long-range dependencies with linear time complexity, while the latter is used to enhance local feature representations. Extensive experiments demonstrate that MambaLIE outperforms state-of-the-art CNN-based and Transformer-based LIE methods on four widely used synthetic benchmarks and five publicly available real-world benchmarks in terms of accuracy, speed, and model size, making it suitable for practical deployment on resource-constrained devices.
Abstract (translated)
URL
https://arxiv.org/abs/2607.03013
PDF
-
Pooling-Based Context Modeling for Convolution-Free Deep Image Prior
2026-07-03 04:56:45Gihyun Kim, Jong-Seok LeeAbstract
Convolutional Neural Networks (CNNs) achieve strong denoising performance by exploiting spatial context from neighboring pixels. Deep Image Prior (DIP) leverages this property to restore images from a single noisy input without requiring large datasets. However, the over-parameterized architecture of DIP often leads to noise fitting during optimization. In this paper, we propose Pool-DIP, a convolution-free architecture that incorporates pooling-based contrast modeling to capture spatial context efficiently. Pool-DIP improves denoising performance while significantly reducing the number of parameters and computational complexity compared to convolution-based DIP models. Experimental results show that Pool-DIP achieves competitive performance across multiple datasets, including a real-world benchmark. Spectral analysis further reveals that Pool-DIP stabilizes the evolution of high-frequency components during optimization and suppresses erroneous high-frequency signals. The proposed architecture also generalizes well to other image restoration tasks such as super-resolution and inpainting.
Abstract (translated)
URL
https://arxiv.org/abs/2607.02952
PDF
-
Speaker head orientation estimation with a single microphone array using phase spectrogram features
2026-07-02 13:05:36Balint Turi, Archontis Politis, Parthasaarathy Sudarsanam, Tuomas VirtanenAbstract
Estimating a speaker's head orientation from audio can provide valuable information in smart environments, meetings, and driver monitoring. We propose a novel approach that leverages the phase component of the short-time Fourier transform from a single microphone array as input to a deep neural network combining convolutional, recurrent, and self-attention layers. Unlike prior methods that use physics-informed handcrafted features or raw waveform inputs, our approach enables robust learning from simulated and real data. Trained on a large-scale dataset generated with voice directivity patterns and fine-tuned on real recordings, our model achieves state-of-the-art accuracy, outperforming baselines under both clean and noisy conditions. Personalization experiments further demonstrate significant gains, reaching a mean angular error of 11.3 degrees when adapting to individual users and environments.
Abstract (translated)
URL
https://arxiv.org/abs/2607.02129
PDF
-
Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency
Abstract
Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation. This study compares nine lightweight CNN model packages across CIFAR-10, CIFAR-100, and Tiny ImageNet under a shared downstream protocol. We report top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 storage, GMACs, batch-size-1 latency on an NVIDIA L4 and AMD Ryzen 5 5500U CPU, peak PyTorch CUDA allocated tensor memory, and point estimate Pareto frontiers. EfficientNetV2-S achieves the highest observed top-1 accuracy on CIFAR-10 and CIFAR-100 at 97.57% and 86.98%, while RepViT-M1.0 leads Tiny ImageNet at 79.87%. EfficientNet-B0 remains within 0.22, 0.85, and 1.79 percentage points of the best result on the three datasets while using approximately 79% fewer parameters and 86% fewer GMACs than EfficientNetV2-S. It also appears on every evaluated accuracy and resource Pareto frontier, making it the most consistently competitive intermediate-budget option. MobileNetV3-Small has the lowest GMAC count, is the fastest model under both CPU thread settings, and records higher observed accuracy than MobileNetV4-Conv-S on all three datasets. Under random initialization, it leads MobileNetV4-Conv-S by 2.55, 1.76, and 0.99 points, with paired test-set intervals excluding zero for the fixed trained models. EfficientNet-B0 remains 3.29, 10.10, and 17.54 points below its pretrained counterpart after 100 epochs of scratch training, despite requiring about five times the recorded training time. SqueezeNet1.1 has the fewest parameters and lowest peak CUDA allocation, but substantially weaker accuracy. Latency rankings differ sharply between the L4 and CPU environments, showing that GMACs alone do not predict measured inference performance. Overall, newer designs provide selective rather than universal gains
Abstract (translated)
URL
https://arxiv.org/abs/2607.01984
PDF
-
Neural Audio Codec with Adjustable Token Temporal Resolution Using Sampling-Frequency-Independent Convolutional Layers
2026-07-02 08:20:03Tomohiko Nakamura, Wataru Nakata, Kanami Imamura, Yuki SaitoAbstract
Discrete tokens obtained from neural audio codecs (NACs) have been used as compact representations in audio generation and understanding models. In such token-based systems, token temporal resolution (TTR), defined as the time interval between adjacent token frames, is important because it controls the trade-off between representing rapid acoustic events and reducing token-sequence length. However, most NACs are trained at a single TTR and require separate training for each TTR. This paper proposes a mechanism that enables a single NAC to operate at multiple TTRs using sampling-frequency-independent convolutional layers. The mechanism regards TTR as the sampling period of the token sequence and generates TTR-dependent convolutional kernels from a shared parameter set, while adjusting the kernel size and stride for each TTR. We incorporate the mechanism into Descript Audio Codec, leaving the quantizer unchanged. Experiments on environmental sound reconstruction show that the proposed model outperforms a single-model baseline that switches TTR-specific layers for each TTR.
Abstract (translated)
URL
https://arxiv.org/abs/2607.01865
PDF
