Gloria Haro

Alejandro Cartas, Coloma Ballester, Gloria Haro

Action spotting in soccer videos is the task of identifying the specific time when a certain key action of the game occurs. Lately, it has received a large amount of attention and powerful methods have been introduced. Action spotting involves understanding the dynamics of the game, the complexity of events, and the variation of video sequences. Most approaches have focused on the latter, given that their models exploit the global visual features of the sequences. In this work, we focus on the former by (a) identifying and representing the players, referees, and goalkeepers as nodes in a graph, and by (b) modeling their temporal interactions as sequences of graphs. For the player identification, or player classification task, we obtain an accuracy of 97.72% in our annotated benchmark. For the action spotting task, our method obtains an overall performance of 57.83% average-mAP by combining it with other audiovisual modalities. This performance surpasses similar graph-based methods and has competitive results with heavy computing methods. Code and data are available at https://github.com/IPCV/soccer_action_spotting.

Venkatesh S. Kadandale, Juan F. Montesinos, Gloria Haro

In this paper, we address the problem of lip-voice synchronisation in videos containing human face and voice. Our approach is based on determining if the lips motion and the voice in a video are synchronised or not, depending on their audio-visual correspondence score. We propose an audio-visual cross-modal transformer-based model that outperforms several baseline models in the audio-visual synchronisation task on the standard lip-reading speech benchmark dataset LRS2. While the existing methods focus mainly on lip synchronisation in speech videos, we also consider the special case of the singing voice. The singing voice is a more challenging use case for synchronisation due to sustained vowel sounds. We also investigate the relevance of lip synchronisation models trained on speech datasets in the context of singing voice. Finally, we use the frozen visual features learned by our lip synchronisation model in the singing voice separation task to outperform a baseline audio-visual model which was trained end-to-end. The demos, source code, and the pre-trained models are available on https://ipcv.github.io/VocaLiST/

Juan F. Montesinos, Venkatesh S. Kadandale, Gloria Haro

This paper presents an audio-visual approach for voice separation which produces state-of-the-art results at a low latency in two scenarios: speech and singing voice. The model is based on a two-stage network. Motion cues are obtained with a lightweight graph convolutional network that processes face landmarks. Then, both audio and motion features are fed to an audio-visual transformer which produces a fairly good estimation of the isolated target source. In a second stage, the predominant voice is enhanced with an audio-only network. We present different ablation studies and comparison to state-of-the-art methods. Finally, we explore the transferability of models trained for speech separation in the task of singing voice separation. The demos, code, and weights are available in https://ipcv.github.io/VoViT/

Juan F. Montesinos, Daniel Michelsanti, Gloria Haro et al.

Audio and visual modalities are inherently connected in speech signals: lip movements and facial expressions are correlated with speech sounds. This motivates studies that incorporate the visual modality to enhance an acoustic speech signal or even restore missing audio information. Specifically, this paper focuses on the problem of audio-visual speech inpainting, which is the task of synthesizing the speech in a corrupted audio segment in a way that it is consistent with the corresponding visual content and the uncorrupted audio context. We present an audio-visual transformer-based deep learning model that leverages visual cues that provide information about the content of the corrupted audio. It outperforms the previous state-of-the-art audio-visual model and audio-only baselines. We also show how visual features extracted with AV-HuBERT, a large audio-visual transformer for speech recognition, are suitable for synthesizing speech.

Albert Barreiro, Roger Marí, Rafael Redondo et al.

Recent advances in digitization technologies have transformed the preservation and dissemination of cultural heritage. In this vein, Neural Radiance Fields (NeRF) have emerged as a leading technology for 3D digitization, delivering representations with exceptional realism. However, existing methods struggle to accurately model anisotropic specular surfaces, typically observed, for example, on brushed metals. In this work, we introduce ShinyNeRF, a novel framework capable of handling both isotropic and anisotropic reflections. Our method is capable of jointly estimating surface normals, tangents, specular concentration, and anisotropy magnitudes of an Anisotropic Spherical Gaussian (ASG) distribution, by learning an approximation of the outgoing radiance as an encoded mixture of isotropic von Mises-Fisher (vMF) distributions. Experimental results show that ShinyNeRF not only achieves state-of-the-art performance on digitizing anisotropic specular reflections, but also offers plausible physical interpretations and editing of material properties compared to existing methods.

Artur Díaz-Juan, Coloma Ballester, Gloria Haro

Video summarization aims to extract key shots from longer videos to produce concise and informative summaries. One of its most common applications is in sports, where highlight reels capture the most important moments of a game, along with notable reactions and specific contextual events. Automatic summary generation can support video editors in the sports media industry by reducing the time and effort required to identify key segments. However, the lack of publicly available datasets poses a challenge in developing robust models for sports highlight generation. In this paper, we address this gap by introducing a curated dataset for soccer video summarization, designed to serve as a benchmark for the task. The dataset includes shot boundaries for 237 matches from the Spanish, French, and Italian leagues, using broadcast footage sourced from the SoccerNet dataset. Alongside the dataset, we propose a baseline model specifically designed for this task, which achieves an F1 score of 0.3956 in the test set. Furthermore, we propose a new metric constrained by the length of each target summary, enabling a more objective evaluation of the generated content. The dataset and code are available at https://ipcv.github.io/SoccerHigh/.

Xavier Juanola, Giovana Morais, Magdalena Fuentes et al.

Visual sound source localization is a fundamental perception task that aims to detect the location of sounding sources in a video given its audio. Despite recent progress, we identify two shortcomings in current methods: 1) most approaches perform poorly in cases with low audio-visual semantic correspondence such as silence, noise, and offscreen sounds, i.e. in the presence of negative audio; and 2) most prior evaluations are limited to positive cases, where both datasets and metrics convey scenarios with a single visible sound source in the scene. To address this, we introduce three key contributions. First, we propose a new training strategy that incorporates silence and noise, which improves performance in positive cases, while being more robust against negative sounds. Our resulting self-supervised model, SSL-SaN, achieves state-of-the-art performance compared to other self-supervised models, both in sound localization and cross-modal retrieval. Second, we propose a new metric that quantifies the trade-off between alignment and separability of auditory and visual features across positive and negative audio-visual pairs. Third, we present IS3+, an extended and improved version of the IS3 synthetic dataset with negative audio. Our data, metrics and code are available on the https://xavijuanola.github.io/SSL-SaN/.

Adam Phillips, Daniel Grandes Rodriguez, Miriam Sánchez-Manzano et al.

In cinema, visual motifs are recurrent iconographic compositions that carry artistic or aesthetic significance. Their use throughout the history of visual arts and media is interesting to researchers and filmmakers alike. Our goal in this work is to recognise and classify these motifs by proposing a new machine learning model that uses a custom dataset to that end. We show how features extracted from a CLIP model can be leveraged by using a shallow network and an appropriate loss to classify images into 20 different motifs, with surprisingly good results: an $F_1$-score of 0.91 on our test set. We also present several ablation studies justifying the input features, architecture and hyperparameters used.

Adrià Arbués-Sangüesa, Adrián Martín, Paulino Granero et al.

Orientation is a crucial skill for football players that becomes a differential factor in a large set of events, especially the ones involving passes. However, existing orientation estimation methods, which are based on computer-vision techniques, still have a lot of room for improvement. To the best of our knowledge, this article presents the first deep learning model for estimating orientation directly from video footage. By approaching this challenge as a classification problem where classes correspond to orientation bins, and by introducing a cyclic loss function, a well-known convolutional network is refined to provide player orientation data. The model is trained by using ground-truth orientation data obtained from wearable EPTS devices, which are individually compensated with respect to the perceived orientation in the current frame. The obtained results outperform previous methods; in particular, the absolute median error is less than 12 degrees per player. An ablation study is included in order to show the potential generalization to any kind of football video footage.

Juan F. Montesinos, Venkatesh S. Kadandale, Gloria Haro

The task of isolating a target singing voice in music videos has useful applications. In this work, we explore the single-channel singing voice separation problem from a multimodal perspective, by jointly learning from audio and visual modalities. To do so, we present Acappella, a dataset spanning around 46 hours of a cappella solo singing videos sourced from YouTube. We also propose an audio-visual convolutional network based on graphs which achieves state-of-the-art singing voice separation results on our dataset and compare it against its audio-only counterpart, U-Net, and a state-of-the-art audio-visual speech separation model. We evaluate the models in the following challenging setups: i) presence of overlapping voices in the audio mixtures, ii) the target voice set to lower volume levels in the mix, and iii) combination of i) and ii). The third one being the most challenging evaluation setup. We demonstrate that our model outperforms the baseline models in the singing voice separation task in the most challenging evaluation setup. The code, the pre-trained models, and the dataset are publicly available at https://ipcv.github.io/Acappella/able at https://ipcv.github.io/Acappella/

Samuel Hurault, Coloma Ballester, Gloria Haro

In a soccer game, the information provided by detecting and tracking brings crucial clues to further analyze and understand some tactical aspects of the game, including individual and team actions. State-of-the-art tracking algorithms achieve impressive results in scenarios on which they have been trained for, but they fail in challenging ones such as soccer games. This is frequently due to the player small relative size and the similar appearance among players of the same team. Although a straightforward solution would be to retrain these models by using a more specific dataset, the lack of such publicly available annotated datasets entails searching for other effective solutions. In this work, we propose a self-supervised pipeline which is able to detect and track low-resolution soccer players under different recording conditions without any need of ground-truth data. Extensive quantitative and qualitative experimental results are presented evaluating its performance. We also present a comparison to several state-of-the-art methods showing that both the proposed detector and the proposed tracker achieve top-tier results, in particular in the presence of small players.

Juan F. Montesinos, Olga Slizovskaia, Gloria Haro

In this paper, we present a new dataset of music performance videos which can be used for training machine learning methods for multiple tasks such as audio-visual blind source separation and localization, cross-modal correspondences, cross-modal generation and, in general, any audio-visual self-supervised task. These videos, gathered from YouTube, consist of solo musical performances of 13 different instruments. Compared to previously proposed audio-visual datasets, Solos is cleaner since a big amount of its recordings are auditions and manually checked recordings, ensuring there is no background noise nor effects added in the video post-processing. Besides, it is, up to the best of our knowledge, the only dataset that contains the whole set of instruments present in the URMP\cite{URPM} dataset, a high-quality dataset of 44 audio-visual recordings of multi-instrument classical music pieces with individual audio tracks. URMP was intented to be used for source separation, thus, we evaluate the performance on the URMP dataset of two different source-separation models trained on Solos. The dataset is publicly available at https://juanfmontesinos.github.io/Solos/

Adrià Arbués-Sangüesa, Adrián Martín, Javier Fernández et al.

Given a monocular video of a soccer match, this paper presents a computational model to estimate the most feasible pass at any given time. The method leverages offensive player's orientation (plus their location) and opponents' spatial configuration to compute the feasibility of pass events within players of the same team. Orientation data is gathered from body pose estimations that are properly projected onto the 2D game field; moreover, a geometrical solution is provided, through the definition of a feasibility measure, to determine which players are better oriented towards each other. Once analyzed more than 6000 pass events, results show that, by including orientation as a feasibility measure, a robust computational model can be built, reaching more than 0.7 Top-3 accuracy. Finally, the combination of the orientation feasibility measure with the recently introduced Expected Possession Value metric is studied; promising results are obtained, thus showing that existing models can be refined by using orientation as a key feature. These models could help both coaches and analysts to have a better understanding of the game and to improve the players' decision-making process.

Olga Slizovskaia, Gloria Haro, Emilia Gómez

In music source separation, the number of sources may vary for each piece and some of the sources may belong to the same family of instruments, thus sharing timbral characteristics and making the sources more correlated. This leads to additional challenges in the source separation problem. This paper proposes a source separation method for multiple musical instruments sounding simultaneously and explores how much additional information apart from the audio stream can lift the quality of source separation. We explore conditioning techniques at different levels of a primary source separation network and utilize two extra modalities of data, namely presence or absence of instruments in the mixture, and the corresponding video stream data.

Daniel Michelsanti, Olga Slizovskaia, Gloria Haro et al.

Both acoustic and visual information influence human perception of speech. For this reason, the lack of audio in a video sequence determines an extremely low speech intelligibility for untrained lip readers. In this paper, we present a way to synthesise speech from the silent video of a talker using deep learning. The system learns a mapping function from raw video frames to acoustic features and reconstructs the speech with a vocoder synthesis algorithm. To improve speech reconstruction performance, our model is also trained to predict text information in a multi-task learning fashion and it is able to simultaneously reconstruct and recognise speech in real time. The results in terms of estimated speech quality and intelligibility show the effectiveness of our method, which exhibits an improvement over existing video-to-speech approaches.

Venkatesh S. Kadandale, Juan F. Montesinos, Gloria Haro et al.

A fairly straightforward approach for music source separation is to train independent models, wherein each model is dedicated for estimating only a specific source. Training a single model to estimate multiple sources generally does not perform as well as the independent dedicated models. However, Conditioned U-Net (C-U-Net) uses a control mechanism to train a single model for multi-source separation and attempts to achieve a performance comparable to that of the dedicated models. We propose a multi-channel U-Net (M-U-Net) trained using a weighted multi-task loss as an alternative to the C-U-Net. We investigate two weighting strategies for our multi-task loss: 1) Dynamic Weighted Average (DWA), and 2) Energy Based Weighting (EBW). DWA determines the weights by tracking the rate of change of loss of each task during training. EBW aims to neutralize the effect of the training bias arising from the difference in energy levels of each of the sources in a mixture. Our methods provide three-fold advantages compared to C-UNet: 1) Fewer effective training iterations per epoch, 2) Fewer trainable network parameters (no control parameters), and 3) Faster processing at inference. Our methods achieve performance comparable to that of C-U-Net and the dedicated U-Nets at a much lower training cost.

Adrià Arbués-Sangüesa, Adrián Martín, Javier Fernández et al.

Although orientation has proven to be a key skill of soccer players in order to succeed in a broad spectrum of plays, body orientation is a yet-little-explored area in sports analytics' research. Despite being an inherently ambiguous concept, player orientation can be defined as the projection (2D) of the normal vector placed in the center of the upper-torso of players (3D). This research presents a novel technique to obtain player orientation from monocular video recordings by mapping pose parts (shoulders and hips) in a 2D field by combining OpenPose with a super-resolution network, and merging the obtained estimation with contextual information (ball position). Results have been validated with players-held EPTS devices, obtaining a median error of 27 degrees/player. Moreover, three novel types of orientation maps are proposed in order to make raw orientation data easy to visualize and understand, thus allowing further analysis at team- or player-level.

Adrià Arbués-Sangüesa, Gloria Haro, Coloma Ballester

Tracking data is a powerful tool for basketball teams in order to extract advanced semantic information and statistics that might lead to a performance boost. However, multi-person tracking is a challenging task to solve in single-camera video sequences, given the frequent occlusions and cluttering that occur in a restricted scenario. In this paper, a novel multi-scale detection method is presented, which is later used to extract geometric and content features, resulting in a multi-person video tracking system. Having built a dataset from scratch together with its ground truth (more than 10k bounding boxes), standard metrics are evaluated, obtaining notable results both in terms of detection (F1-score) and tracking (MOTA). The presented system could be used as a source of data gathering in order to extract useful statistics and semantic analyses a posteriori.

Olga Slizovskaia, Emilia Gómez, Gloria Haro

The explainability of Convolutional Neural Networks (CNNs) is a particularly challenging task in all areas of application, and it is notably under-researched in music and audio domain. In this paper, we approach explainability by exploiting the knowledge we have on hand-crafted audio features. Our study focuses on a well-defined MIR task, the recognition of musical instruments from user-generated music recordings. We compute the similarity between a set of traditional audio features and representations learned by CNNs. We also propose a technique for measuring the similarity between activation maps and audio features which typically presented in the form of a matrix, such as chromagrams or spectrograms. We observe that some neurons' activations correspond to well-known classical audio features. In particular, for shallow layers, we found similarities between activations and harmonic and percussive components of the spectrum. For deeper layers, we compare chromagrams with high-level activation maps as well as loudness and onset rate with deep-learned embeddings.

Adrià Arbués-Sangüesa, Coloma Ballester, Gloria Haro

Tracking sports players is a widely challenging scenario, specially in single-feed videos recorded in tight courts, where cluttering and occlusions cannot be avoided. This paper presents an analysis of several geometric and semantic visual features to detect and track basketball players. An ablation study is carried out and then used to remark that a robust tracker can be built with Deep Learning features, without the need of extracting contextual ones, such as proximity or color similarity, nor applying camera stabilization techniques. The presented tracker consists of: (1) a detection step, which uses a pretrained deep learning model to estimate the players pose, followed by (2) a tracking step, which leverages pose and semantic information from the output of a convolutional layer in a VGG network. Its performance is analyzed in terms of MOTA over a basketball dataset with more than 10k instances.

Olga Slizovskaia, Leo Kim, Gloria Haro et al.

Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model? We present an extension of the Wave-U-Net model which allows end-to-end monaural source separation with a non-fixed number of sources. Furthermore, we propose multiplicative conditioning with instrument labels at the bottleneck of the Wave-U-Net and show its effect on the separation results. This approach leads to other types of conditioning such as audio-visual source separation and score-informed source separation.

Roberto P. Palomares, Enric Meinhardt-Llopis, Coloma Ballester et al.

We propose a large displacement optical flow method that introduces a new strategy to compute a good local minimum of any optical flow energy functional. The method requires a given set of discrete matches, which can be extremely sparse, and an energy functional which locally guides the interpolation from those matches. In particular, the matches are used to guide a structured coordinate-descent of the energy functional around these keypoints. It results in a two-step minimization method at the finest scale which is very robust to the inevitable outliers of the sparse matcher and able to capture large displacements of small objects. Its benefits over other variational methods that also rely on a set of sparse matches are its robustness against very few matches, high levels of noise and outliers. We validate our proposal using several optical flow variational models. The results consistently outperform the coarse-to-fine approaches and achieve good qualitative and quantitative performance on the standard optical flow benchmarks.

Maria Oliver, Gloria Haro, Mariella Dimiccoli et al.

This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others. The estimated scene interpretation is obtained by integrating some global and local cues and provides both the complete disoccluded objects that form the scene and their ordering according to depth. Our method first computes several distal scenes which are compatible with the proximal planar image. To compute these different hypothesized scenes, we propose a perceptually inspired object disocclusion method, which works by minimizing the Euler's elastica as well as by incorporating the relatability of partially occluded contours and the convexity of the disoccluded objects. Then, to estimate the preferred scene we rely on a Bayesian model and define probabilities taking into account the global complexity of the objects in the hypothesized scenes as well as the effort of bringing these objects in their relative position in the planar image, which is also measured by an Euler's elastica-based quantity. The model is illustrated with numerical experiments on, both, synthetic and real images showing the ability of our model to reconstruct the occluded objects and the preferred perceptual order among them. We also present results on images of the Berkeley dataset with provided figure-ground ground-truth labeling.