arXiv subjects

Petros Maragos

Publications and source records attributed to Petros Maragos.

At least 37 records · Page 2Linked to original sources

arXiv2025

A Machine Learning Approach for MIDI to Guitar Tablature Conversion

Guitar tablature transcription consists in deducing the string and the fret number on which each note should be played to reproduce the actual musical part. This assignment should lead to playable string-fret combinations throughout the entire track and, in general, preserve parsimonious motion between successive combinations. Throughout the history of guitar playing, specific chord fingerings have been developed across different musical styles that facilitate common idiomatic voicing combinations and motion between them. This paper presents a method for assigning guitar tablature notation to a given MIDI-based musical part (possibly consisting of multiple polyphonic tracks), i.e. no information about guitar-idiomatic expressional characteristics is involved (e.g. bending etc.) The current strategy is based on machine learning and requires a basic assumption about how much fingers can stretch on a fretboard; only standard 6-string guitar tuning is examined. The proposed method also examines the transcription of music pieces that was not meant to be played or could not possibly be played by a guitar (e.g. potentially a symphonic orchestra part), employing a rudimentary method for augmenting musical information and training/testing the system with artificial data. The results present interesting aspects about what the system can achieve when trained on the initial and augmented dataset, showing that the training with augmented data improves the performance even in simple, e.g. monophonic, cases. Results also indicate weaknesses and lead to useful conclusions about possible improvements.

cs.SD↗

arXiv2025

CVSM: Contrastive Vocal Similarity Modeling

The availability of large, unlabeled datasets across various domains has contributed to the development of a plethora of methods that learn representations for multiple target (downstream) tasks through self-supervised pre-training. In this work, we introduce CVSM (Contrastive Vocal Similarity Modeling), a contrastive self-supervised procedure for music signal representation learning in the audio domain that can be utilized for musical and vocal similarity modeling. Our method operates under a contrastive framework, maximizing the similarity between vocal excerpts and musical mixtures containing the same vocals; we devise both a label-informed protocol, leveraging artist identity information to sample the contrastive pairs, and a label-agnostic scheme, involving artificial mixture creation from randomly sampled vocal and accompaniment excerpts, which are paired with vocals from the same audio segment. We evaluate our proposed method in measuring vocal similarity both objectively, through linear probing on a suite of appropriate downstream tasks, and subjectively, via conducting a user study consisting of pairwise comparisons between different models in a recommendation-by-query setting. Our results indicate that the representations learned through CVSM are effective in musical and vocal similarity modeling, outperforming numerous baselines across both isolated vocals and complete musical mixtures. Moreover, while the availability of artist identity labels during pre-training leads to overall more consistent performance both in the evaluated downstream tasks and the user study, a label-agnostic CVSM variant incorporating hybrid pre-training with real and artificial mixtures achieves comparable performance to the label-informed one in artist identification and perceived vocal similarity.

eess.AS↗

arXiv2025

Shared-Weights Extender and Gradient Voting for Neural Network Expansion

Expanding neural networks during training is a promising way to augment capacity without retraining larger models from scratch. However, newly added neurons often fail to adjust to a trained network and become inactive, providing no contribution to capacity growth. We propose the Shared-Weights Extender (SWE), a novel method explicitly designed to prevent inactivity of new neurons by coupling them with existing ones for smooth integration. In parallel, we introduce the Steepest Voting Distributor (SVoD), a gradient-based method for allocating neurons across layers during deep network expansion. Our extensive benchmarking on four datasets shows that our method can effectively suppress neuron inactivity and achieve better performance compared to other expanding methods and baselines.

cs.LG↗

arXiv2025

Classical Guitar Duet Separation using GuitarDuets -- a Dataset of Real and Synthesized Guitar Recordings

Recent advancements in music source separation (MSS) have focused in the multi-timbral case, with existing architectures tailored for the separation of distinct instruments, overlooking thus the challenge of separating instruments with similar timbral characteristics. Addressing this gap, our work focuses on monotimbral MSS, specifically within the context of classical guitar duets. To this end, we introduce the GuitarDuets dataset, featuring a combined total of approximately three hours of real and synthesized classical guitar duet recordings, as well as note-level annotations of the synthesized duets. We perform an extensive cross-dataset evaluation by adapting Demucs, a state-of-the-art MSS architecture, to monotimbral source separation. Furthermore, we develop a joint permutation-invariant transcription and separation framework, to exploit note event predictions as auxiliary information. Our results indicate that utilizing both the real and synthesized subsets of GuitarDuets leads to improved separation performance in an independently recorded test set compared to utilizing solely one subset. We also find that while the availability of ground-truth note labels greatly helps the performance of the separation network, the predicted note estimates result only in marginal improvement. Finally, we discuss the behavior of commonly utilized metrics, such as SDR and SI-SDR, in the context of monotimbral MSS.

eess.AS↗

arXiv2025

Only-Style: Stylistic Consistency in Image Generation without Content Leakage

Generating images in a consistent reference visual style remains a challenging computer vision task. State-of-the-art methods aiming for style-consistent generation struggle to effectively separate semantic content from stylistic elements, leading to content leakage from the image provided as a reference to the targets. To address this challenge, we propose Only-Style: a method designed to mitigate content leakage in a semantically coherent manner while preserving stylistic consistency. Only-Style works by localizing content leakage during inference, allowing the adaptive tuning of a parameter that controls the style alignment process, specifically within the image patches containing the subject in the reference image. This adaptive process best balances stylistic consistency with leakage elimination. Moreover, the localization of content leakage can function as a standalone component, given a reference-target image pair, allowing the adaptive tuning of any method-specific parameter that provides control over the impact of the stylistic reference. In addition, we propose a novel evaluation framework to quantify the success of style-consistent generations in avoiding undesired content leakage. Our approach demonstrates a significant improvement over state-of-the-art methods through extensive evaluation across diverse instances, consistently achieving robust stylistic consistency without undesired content leakage.

cs.CV↗

arXiv2025

Category-Level 6D Object Pose Estimation in Agricultural Settings Using a Lattice-Deformation Framework and Diffusion-Augmented Synthetic Data

Accurate 6D object pose estimation is essential for robotic grasping and manipulation, particularly in agriculture, where fruits and vegetables exhibit high intra-class variability in shape, size, and texture. The vast majority of existing methods rely on instance-specific CAD models or require depth sensors to resolve geometric ambiguities, making them impractical for real-world agricultural applications. In this work, we introduce PLANTPose, a novel framework for category-level 6D pose estimation that operates purely on RGB input. PLANTPose predicts both the 6D pose and deformation parameters relative to a base mesh, allowing a single category-level CAD model to adapt to unseen instances. This enables accurate pose estimation across varying shapes without relying on instance-specific data. To enhance realism and improve generalization, we also leverage Stable Diffusion to refine synthetic training images with realistic texturing, mimicking variations due to ripeness and environmental factors and bridging the domain gap between synthetic data and the real world. Our evaluations on a challenging benchmark that includes bananas of various shapes, sizes, and ripeness status demonstrate the effectiveness of our framework in handling large intraclass variations while maintaining accurate 6D pose predictions, significantly outperforming the state-of-the-art RGB-based approach MegaPose.

cs.CV↗

arXiv2025

Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning

Learning visual representations from observing actions to benefit robot visuo-motor policy generation is a promising direction that closely resembles human cognitive function and perception. Motivated by this, and further inspired by psychological theories suggesting that humans process scenes in an object-based fashion, we propose an object-centric encoder that performs semantic segmentation and visual representation generation in a coupled manner, unlike other works, which treat these as separate processes. To achieve this, we leverage the Slot Attention mechanism and use the SOLV model, pretrained in large out-of-domain datasets, to bootstrap fine-tuning on human action video data. Through simulated robotic tasks, we demonstrate that visual representations can enhance reinforcement and imitation learning training, highlighting the effectiveness of our integrated approach for semantic segmentation and encoding. Furthermore, we show that exploiting models pretrained on out-of-domain datasets can benefit this process, and that fine-tuning on datasets depicting human actions -- although still out-of-domain -- , can significantly improve performance due to close alignment with robotic tasks. These findings show the capability to reduce reliance on annotated or robot-specific action datasets and the potential to build on existing visual encoders to accelerate training and improve generalizability.

cs.RO↗

arXiv2025

Multi-task Learning For Joint Action and Gesture Recognition

In practical applications, computer vision tasks often need to be addressed simultaneously. Multitask learning typically achieves this by jointly training a single deep neural network to learn shared representations, providing efficiency and improving generalization. Although action and gesture recognition are closely related tasks, since they focus on body and hand movements, current state-of-the-art methods handle them separately. In this paper, we show that employing a multi-task learning paradigm for action and gesture recognition results in more efficient, robust and generalizable visual representations, by leveraging the synergies between these tasks. Extensive experiments on multiple action and gesture datasets demonstrate that handling actions and gestures in a single architecture can achieve better performance for both tasks in comparison to their single-task learning variants.

cs.CV↗

arXiv2025

Proactive tactile exploration for object-agnostic shape reconstruction from minimal visual priors

The perception of an object's surface is important for robotic applications enabling robust object manipulation. The level of accuracy in such a representation affects the outcome of the action planning, especially during tasks that require physical contact, e.g. grasping. In this paper, we propose a novel iterative method for 3D shape reconstruction consisting of two steps. At first, a mesh is fitted on data points acquired from the object's surface, based on a single primitive template. Subsequently, the mesh is properly adjusted to adequately represent local deformities. Moreover, a novel proactive tactile exploration strategy aims at minimizing the total uncertainty with the least number of contacts, while reducing the risk of contact failure in case the estimated surface differs significantly from the real one. The performance of the methodology is evaluated both in 3D simulation and on a real setup.

cs.RO↗

arXiv2025

Sparse Hybrid Linear-Morphological Networks

We investigate hybrid linear-morphological networks. Recent studies highlight the inherent affinity of morphological layers to pruning, but also their difficulty in training. We propose a hybrid network structure, wherein morphological layers are inserted between the linear layers of the network, in place of activation functions. We experiment with the following morphological layers: 1) maxout pooling layers (as a special case of a morphological layer), 2) fully connected dense morphological layers, and 3) a novel, sparsely initialized variant of (2). We conduct experiments on the Magna-Tag-A-Tune (music auto-tagging) and CIFAR-10 (image classification) datasets, replacing the linear classification heads of state-of-the-art convolutional network architectures with our proposed network structure for the various morphological layers. We demonstrate that these networks induce sparsity to their linear layers, making them more prunable under L1 unstructured pruning. We also show that on MTAT our proposed sparsely initialized layer achieves slightly better performance than ReLU, maxout, and densely initialized max-plus layers, and exhibits faster initial convergence.

cs.LG↗

arXiv2025

Diffusion-Based Forecasting for Uncertainty-Aware Model Predictive Control

We propose Diffusion-Informed Model Predictive Control (D-I MPC), a generic framework for uncertainty-aware prediction and decision-making in partially observable stochastic systems by integrating diffusion-based time series forecasting models in Model Predictive Control algorithms. In our approach, a diffusion-based time series forecasting model is used to probabilistically estimate the evolution of the system's stochastic components. These forecasts are then incorporated into MPC algorithms to estimate future trajectories and optimize action selection under the uncertainty of the future. We evaluate the framework on the task of energy arbitrage, where a Battery Energy Storage System participates in the day-ahead electricity market of the New York state. Experimental results indicate that our model-based approach with a diffusion-based forecaster significantly outperforms both implementations with classical forecasting methods and model-free reinforcement learning baselines.

cs.LG↗

arXiv2025

SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis

While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely observed expressions. We improve upon these methods with SMIRK (Spatial Modeling for Image-based Reconstruction of Kinesics), which faithfully reconstructs expressive 3D faces from images. We identify two key limitations in existing methods: shortcomings in their self-supervised training formulation, and a lack of expression diversity in the training images. For training, most methods employ differentiable rendering to compare a predicted face mesh with the input image, along with a plethora of additional loss functions. This differentiable rendering loss not only has to provide supervision to optimize for 3D face geometry, camera, albedo, and lighting, which is an ill-posed optimization problem, but the domain gap between rendering and input image further hinders the learning process. Instead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the rendered predicted mesh geometry, and sparsely sampled pixels of the input image, generates a face image. As the neural rendering gets color information from sampled image pixels, supervising with neural rendering-based reconstruction loss can focus solely on the geometry. Further, it enables us to generate images of the input identity with varying expressions while training. These are then utilized as input to the reconstruction model and used as supervision with ground truth geometry. This effectively augments the training data and enhances the generalization for diverse expressions. Our qualitative, quantitative and particularly our perceptual evaluations demonstrate that SMIRK achieves the new state-of-the art performance on accurate expression reconstruction. Project webpage: https://georgeretsi.github.io/smirk/.

cs.CV↗

arXiv2025

A Transformer-Based Framework for Greek Sign Language Production using Extended Skeletal Motion Representations

Sign Languages are the primary form of communication for Deaf communities across the world. To break the communication barriers between the Deaf and Hard-of-Hearing and the hearing communities, it is imperative to build systems capable of translating the spoken language into sign language and vice versa. Building on insights from previous research, we propose a deep learning model for Sign Language Production (SLP), which to our knowledge is the first attempt on Greek SLP. We tackle this task by utilizing a transformer-based architecture that enables the translation from text input to human pose keypoints, and the opposite. We evaluate the effectiveness of the proposed pipeline on the Greek SL dataset Elementary23, through a series of comparative analyses and ablation studies. Our pipeline's components, which include data-driven gloss generation, training through video to text translation and a scheduling algorithm for teacher forcing - auto-regressive decoding seem to actively enhance the quality of produced SL videos.

cs.LG↗

arXiv2024

Pre-training for Action Recognition with Automatically Generated Fractal Datasets

In recent years, interest in synthetic data has grown, particularly in the context of pre-training the image modality to support a range of computer vision tasks, including object classification, medical imaging etc. Previous work has demonstrated that synthetic samples, automatically produced by various generative processes, can replace real counterparts and yield strong visual representations. This approach resolves issues associated with real data such as collection and labeling costs, copyright and privacy. We extend this trend to the video domain applying it to the task of action recognition. Employing fractal geometry, we present methods to automatically produce large-scale datasets of short synthetic video clips, which can be utilized for pre-training neural models. The generated video clips are characterized by notable variety, stemmed by the innate ability of fractals to generate complex multi-scale structures. To narrow the domain gap, we further identify key properties of real videos and carefully emulate them during pre-training. Through thorough ablations, we determine the attributes that strengthen downstream results and offer general guidelines for pre-training with synthetic videos. The proposed approach is evaluated by fine-tuning pre-trained models on established action recognition datasets HMDB51 and UCF101 as well as four other video benchmarks related to group action recognition, fine-grained action recognition and dynamic scenes. Compared to standard Kinetics pre-training, our reported results come close and are even superior on a portion of downstream datasets. Code and samples of synthetic videos are available at https://github.com/davidsvy/fractal_video .

cs.CV↗

arXiv2024

Pre-training Music Classification Models via Music Source Separation

In this paper, we study whether music source separation can be used as a pre-training strategy for music representation learning, targeted at music classification tasks. To this end, we first pre-train U-Net networks under various music source separation objectives, such as the isolation of vocal or instrumental sources from a musical piece; afterwards, we attach a classification network to the pre-trained U-Net and jointly finetune the whole network. The features learned by the separation network are also propagated to the tail network through a convolutional feature adaptation module. Experimental results in two widely used and publicly available datasets indicate that pre-training the U-Nets with a music source separation objective can improve performance compared to both training the whole network from scratch and using the tail network as a standalone in two music classification tasks, music auto-tagging and music genre classification. We also show that our proposed framework can be successfully integrated into both convolutional and Transformer-based backends, highlighting its modularity.

eess.AS↗

arXiv2024

Mushroom Segmentation and 3D Pose Estimation from Point Clouds using Fully Convolutional Geometric Features and Implicit Pose Encoding

Modern agricultural applications rely more and more on deep learning solutions. However, training well-performing deep networks requires a large amount of annotated data that may not be available and in the case of 3D annotation may not even be feasible for human annotators. In this work, we develop a deep learning approach to segment mushrooms and estimate their pose on 3D data, in the form of point clouds acquired by depth sensors. To circumvent the annotation problem, we create a synthetic dataset of mushroom scenes, where we are fully aware of 3D information, such as the pose of each mushroom. The proposed network has a fully convolutional backbone, that parses sparse 3D data, and predicts pose information that implicitly defines both instance segmentation and pose estimation task. We have validated the effectiveness of the proposed implicit-based approach for a synthetic test set, as well as provided qualitative results for a small set of real acquired point clouds with depth sensors. Code is publicly available at https://github.com/georgeretsi/mushroom-pose.

cs.CV↗

arXiv2023

Neural Text to Articulate Talk: Deep Text to Audiovisual Speech Synthesis achieving both Auditory and Photo-realism

Recent advances in deep learning for sequential data have given rise to fast and powerful models that produce realistic videos of talking humans. The state of the art in talking face generation focuses mainly on lip-syncing, being conditioned on audio clips. However, having the ability to synthesize talking humans from text transcriptions rather than audio is particularly beneficial for many applications and is expected to receive more and more attention, following the recent breakthroughs in large language models. For that, most methods implement a cascaded 2-stage architecture of a text-to-speech module followed by an audio-driven talking face generator, but this ignores the highly complex interplay between audio and visual streams that occurs during speaking. In this paper, we propose the first, to the best of our knowledge, text-driven audiovisual speech synthesizer that uses Transformers and does not follow a cascaded approach. Our method, which we call NEUral Text to ARticulate Talk (NEUTART), is a talking face generator that uses a joint audiovisual feature space, as well as speech-informed 3D facial reconstructions and a lip-reading loss for visual supervision. The proposed model produces photorealistic talking face videos with human-like articulation and well-synced audiovisual streams. Our experiments on audiovisual datasets as well as in-the-wild videos reveal state-of-the-art generation quality both in terms of objective metrics and human evaluation.

cs.CV↗

arXiv2023

OVeNet: Offset Vector Network for Semantic Segmentation

Semantic segmentation is a fundamental task in visual scene understanding. We focus on the supervised setting, where ground-truth semantic annotations are available. Based on knowledge about the high regularity of real-world scenes, we propose a method for improving class predictions by learning to selectively exploit information from neighboring pixels. In particular, our method is based on the prior that for each pixel, there is a seed pixel in its close neighborhood sharing the same prediction with the former. Motivated by this prior, we design a novel two-head network, named Offset Vector Network (OVeNet), which generates both standard semantic predictions and a dense 2D offset vector field indicating the offset from each pixel to the respective seed pixel, which is used to compute an alternative, seed-based semantic prediction. The two predictions are adaptively fused at each pixel using a learnt dense confidence map for the predicted offset vector field. We supervise offset vectors indirectly via optimizing the seed-based prediction and via a novel loss on the confidence map. Compared to the baseline state-of-the-art architectures HRNet and HRNet+OCR on which OVeNet is built, the latter achieves significant performance gains on three prominent benchmarks for semantic segmentation, namely Cityscapes, ACDC and ADE20K. Code is available at https://github.com/stamatisalex/OVeNet

cs.CV↗