Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–23 of 23 results for author: Deliege, A

Searching in archive cs. Search in all archives.
.
  1. arXiv:2607.04372  [pdf, ps, other

    cs.CV

    Event Detection in Videos: A Framework for the Development of New Methods

    Authors: Anastasia Zakharova, Thierry Bouwmans, Anthony Cioppa, Adrien Deliège, Antonio Greco, Anaïs Halin, Kamil Jeziorek, Meghna Kapoor, Tomasz Kryjak, Islam Osman, Sébastien Piérard, Carlo Sansone, Mohamed S. Shehata, Renaud Vandeghen, Marc Van Droogenbroeck, Bruno Vento

    Abstract: Event detection tasks in videos, the most important aspect of video surveillance, aim to detect events either at the pixel-level, frame-level, or clip-level. Plenty of methods intended for event detection in different environments, for various applications, and within different acquisition techniques were introduced. Naturally, the attempts were made as well to classify these algorithms in terms o… ▽ More

    Submitted 5 July, 2026; originally announced July 2026.

    Comments: 22 pages, 8 figures, 1 table

  2. arXiv:2605.23656  [pdf, ps, other

    cs.CV

    Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models

    Authors: Maxim Henry, Adrien Deliège, Sébastien Piérard, Marc Van Droogenbroeck

    Abstract: Training high-capacity vision models from scratch requires substantial computational resources. To improve training efficiency of a wide target model, existing growth methods often assume the availability of narrower models, obscuring the true computational cost of the entire pipeline. We propose an efficient training protocol, RBDC, that builds wide models by coupling in a parameter-free block-di… ▽ More

    Submitted 22 May, 2026; originally announced May 2026.

    Comments: 22 pages, 3 figures, 4 tables, and 34 references

  3. arXiv:2512.08715  [pdf, ps, other

    cs.PF cs.AI cs.CV cs.LG

    Multi-domain performance analysis with scores tailored to user preferences

    Authors: Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck

    Abstract: The performance of algorithms, methods, and models tends to depend heavily on the distribution of cases on which they are applied, this distribution being specific to the applicative domain. After performing an evaluation in several domains, it is highly informative to compute a (weighted) mean performance and, as shown in this paper, to scrutinize what happens during this averaging. To achieve th… ▽ More

    Submitted 9 December, 2025; originally announced December 2025.

  4. arXiv:2511.22442  [pdf, ps, other

    cs.PF cs.AI cs.CV cs.LG stat.ML

    What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely $F_1$

    Authors: Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck

    Abstract: Ranking methods or models based on their performance is of prime importance but is tricky because performance is fundamentally multidimensional. In the case of classification, precision and recall are scores with probabilistic interpretations that are both important to consider and complementary. The rankings induced by these two scores are often in partial contradiction. In practice, therefore, i… ▽ More

    Submitted 30 March, 2026; v1 submitted 27 November, 2025; originally announced November 2025.

    Comments: CVPR 2026

  5. Gaze-Based Indicators of Driver Cognitive Distraction: Effects of Different Traffic Conditions and Adaptive Cruise Control Use

    Authors: Anaïs Halin, Adrien Deliège, Christel Devue, Marc Van Droogenbroeck

    Abstract: In this simulator study, we investigate how gaze parameters reflect driver cognitive distraction under varying traffic conditions and adaptive cruise control (ACC) use. Participants completed six driving scenarios that combined two levels of cognitive distraction (with/without mental calculations) and three levels of driving environment complexity. Throughout the experiment, participants were free… ▽ More

    Submitted 14 August, 2025; originally announced August 2025.

  6. LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation

    Authors: Maxim Henry, Adrien Deliège, Anthony Cioppa, Marc Van Droogenbroeck

    Abstract: Convolutional Neural Networks (CNN) are widely used in many computer vision tasks. Yet, their increasing size and complexity pose significant challenges for efficient deployment on resource-constrained platforms. Hence, network pruning has emerged as an effective way of reducing the size and computational requirements of neural networks by removing redundant or unimportant parameters. However, a f… ▽ More

    Submitted 29 July, 2025; originally announced July 2025.

    Comments: 10 pages, 4 figures, 5 tables, 45 references

  7. arXiv:2505.19175  [pdf, other

    cs.CV

    Triangle Splatting for Real-Time Radiance Field Rendering

    Authors: Jan Held, Renaud Vandeghen, Adrien Deliege, Abdullah Hamdi, Silvio Giancola, Anthony Cioppa, Andrea Vedaldi, Bernard Ghanem, Andrea Tagliasacchi, Marc Van Droogenbroeck

    Abstract: The field of computer graphics was revolutionized by models such as Neural Radiance Fields and 3D Gaussian Splatting, displacing triangles as the dominant representation for photogrammetry. In this paper, we argue for a triangle comeback. We develop a differentiable renderer that directly optimizes triangles via end-to-end gradients. We achieve this by rendering each triangle as differentiable spl… ▽ More

    Submitted 25 May, 2025; originally announced May 2025.

    Comments: 18 pages, 13 figures, 10 tables

  8. A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains

    Authors: Sébastien Piérard, Adrien Deliège, Anaïs Halin, Marc Van Droogenbroeck

    Abstract: Frequently, multiple entities (methods, algorithms, procedures, solutions, etc.) can be developed for a common task and applied across various domains that differ in the distribution of scenarios encountered. For example, in computer vision, the input data provided to image analysis methods depend on the type of sensor used, its location, and the scene content. However, a crucial difficulty remain… ▽ More

    Submitted 21 May, 2025; originally announced May 2025.

  9. arXiv:2412.04309  [pdf, other

    cs.CV cs.LG cs.PF

    The Tile: A 2D Map of Ranking Scores for Two-Class Classification

    Authors: Sébastien Piérard, Anaïs Halin, Anthony Cioppa, Adrien Deliège, Marc Van Droogenbroeck

    Abstract: In the computer vision and machine learning communities, as well as in many other research domains, rigorous evaluation of any new method, including classifiers, is essential. One key component of the evaluation process is the ability to compare and rank methods. However, ranking classifiers and accurately comparing their performances, especially when taking application-specific preferences into a… ▽ More

    Submitted 18 December, 2024; v1 submitted 5 December, 2024; originally announced December 2024.

  10. Foundations of the Theory of Performance-Based Ranking

    Authors: Sébastien Piérard, Anaïs Halin, Anthony Cioppa, Adrien Deliège, Marc Van Droogenbroeck

    Abstract: Ranking entities such as algorithms, devices, methods, or models based on their performances, while accounting for application-specific preferences, is a challenge. To address this challenge, we establish the foundations of a universal theory for performance-based ranking. First, we introduce a rigorous framework built on top of both the probability and order theories. Our new framework encompasse… ▽ More

    Submitted 24 March, 2025; v1 submitted 5 December, 2024; originally announced December 2024.

  11. arXiv:2411.14974  [pdf, other

    cs.CV

    3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes

    Authors: Jan Held, Renaud Vandeghen, Abdullah Hamdi, Adrien Deliege, Anthony Cioppa, Silvio Giancola, Andrea Vedaldi, Bernard Ghanem, Marc Van Droogenbroeck

    Abstract: Recent advances in radiance field reconstruction, such as 3D Gaussian Splatting (3DGS), have achieved high-quality novel view synthesis and fast rendering by representing scenes with compositions of Gaussian primitives. However, 3D Gaussians present several limitations for scene reconstruction. Accurately capturing hard edges is challenging without significantly increasing the number of Gaussians,… ▽ More

    Submitted 25 May, 2025; v1 submitted 22 November, 2024; originally announced November 2024.

    Comments: Accepted at CVPR 2025 as Highlight. 13 pages, 13 figures, 10 tables

  12. arXiv:2409.10587  [pdf, other

    cs.CV

    SoccerNet 2024 Challenges Results

    Authors: Anthony Cioppa, Silvio Giancola, Vladimir Somers, Victor Joos, Floriane Magera, Jan Held, Seyed Abolfazl Ghasemzadeh, Xin Zhou, Karolina Seweryn, Mateusz Kowalczyk, Zuzanna Mróz, Szymon Łukasik, Michał Hałoń, Hassan Mkhallati, Adrien Deliège, Carlos Hinojosa, Karen Sanchez, Amir M. Mansourian, Pierre Miralles, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Adam Gorski , et al. (59 additional authors not shown)

    Abstract: The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely loca… ▽ More

    Submitted 16 September, 2024; originally announced September 2024.

    Comments: 7 pages, 1 figure

  13. SoccerNet 2023 Challenges Results

    Authors: Anthony Cioppa, Silvio Giancola, Vladimir Somers, Floriane Magera, Xin Zhou, Hassan Mkhallati, Adrien Deliège, Jan Held, Carlos Hinojosa, Amir M. Mansourian, Pierre Miralles, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdullah Kamal, Adrien Maglo, Albert Clapés, Amr Abdelaziz, Artur Xarles, Astrid Orcesi, Atom Scott, Bin Liu, Byoungkwon Lim , et al. (77 additional authors not shown)

    Abstract: The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, fo… ▽ More

    Submitted 12 September, 2023; originally announced September 2023.

  14. SoccerNet 2022 Challenges Results

    Authors: Silvio Giancola, Anthony Cioppa, Adrien Deliège, Floriane Magera, Vladimir Somers, Le Kang, Xin Zhou, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdulrahman Darwish, Adrien Maglo, Albert Clapés, Andreas Luyts, Andrei Boiarov, Artur Xarles, Astrid Orcesi, Avijit Shah, Baoyu Fan, Bharath Comandur, Chen Chen, Chen Zhang, Chen Zhao , et al. (69 additional authors not shown)

    Abstract: The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on det… ▽ More

    Submitted 5 October, 2022; originally announced October 2022.

    Comments: Accepted at ACM MMSports 2022

  15. SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos

    Authors: Anthony Cioppa, Silvio Giancola, Adrien Deliege, Le Kang, Xin Zhou, Zhiyu Cheng, Bernard Ghanem, Marc Van Droogenbroeck

    Abstract: Tracking objects in soccer videos is extremely important to gather both player and team statistics, whether it is to estimate the total distance run, the ball possession or the team formation. Video processing can help automating the extraction of those information, without the need of any invasive sensor, hence applicable to any team on any stadium. Yet, the availability of datasets to train lear… ▽ More

    Submitted 20 April, 2022; v1 submitted 14 April, 2022; originally announced April 2022.

    Comments: Paper accepted for the CVsports workshop at CVPR2022. This document contains 8 pages + references

  16. arXiv:2109.01561  [pdf, other

    cs.CV

    Ordinal Pooling

    Authors: Adrien Deliège, Maxime Istasse, Ashwani Kumar, Christophe De Vleeschouwer, Marc Van Droogenbroeck

    Abstract: In the framework of convolutional neural networks, downsampling is often performed with an average-pooling, where all the activations are treated equally, or with a max-pooling operation that only retains an element with maximum activation while discarding the others. Both of these operations are restrictive and have previously been shown to be sub-optimal. To address this issue, a novel pooling s… ▽ More

    Submitted 3 September, 2021; originally announced September 2021.

    Comments: This is the authors' preprint version of a paper published at BMVC 2019. Please cite it as follows: A. Deliège, M. Istasse, A. Kumar, C. De Vleeschouwer and M. Van Droogenbroeck, "Ordinal Pooling", in British Machine Vision Conference, 2019

    Journal ref: A. Deliege, M. Istasse, A. Kumar, C. De Vleeschouwer and M. Van Droogenbroeck, "Ordinal Pooling", in British Machine Vision Conference, 2019

  17. Ghost Loss to Question the Reliability of Training Data

    Authors: Adrien Deliège, Anthony Cioppa, Marc Van Droogenbroeck

    Abstract: Supervised image classification problems rely on training data assumed to have been correctly annotated; this assumption underpins most works in the field of deep learning. In consequence, during its training, a network is forced to match the label provided by the annotator and is not given the flexibility to choose an alternative to inconsistencies that it might be able to detect. Therefore, erro… ▽ More

    Submitted 3 September, 2021; originally announced September 2021.

    Comments: This is the authors' preprint version of a paper published in IEEE Access in 2020. Please cite it as follows: A. Deliège, A. Cioppa and M. Van Droogenbroeck, "Ghost Loss to Question the Reliability of Training Data", in IEEE Access, vol. 8, pp. 44774-44782, 2020, doi: 10.1109/ACCESS.2020.2978283

    Journal ref: in IEEE Access, vol. 8, pp. 44774-44782, 2020

  18. arXiv:2104.09333  [pdf, other

    cs.CV

    Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting

    Authors: Anthony Cioppa, Adrien Deliège, Floriane Magera, Silvio Giancola, Olivier Barnich, Bernard Ghanem, Marc Van Droogenbroeck

    Abstract: Soccer broadcast video understanding has been drawing a lot of attention in recent years within data scientists and industrial companies. This is mainly due to the lucrative potential unlocked by effective deep learning techniques developed in the field of computer vision. In this work, we focus on the topic of camera calibration and on its current limitations for the scientific community. More pr… ▽ More

    Submitted 19 April, 2021; originally announced April 2021.

    Comments: Paper accepted at the CVsports workshop at CVPR2021

  19. arXiv:2011.13367  [pdf, other

    cs.CV

    SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos

    Authors: Adrien Deliège, Anthony Cioppa, Silvio Giancola, Meisam J. Seikavandi, Jacob V. Dueholm, Kamal Nasrollahi, Bernard Ghanem, Thomas B. Moeslund, Marc Van Droogenbroeck

    Abstract: Understanding broadcast videos is a challenging task in computer vision, as it requires generic reasoning capabilities to appreciate the content offered by the video editing. In this work, we propose SoccerNet-v2, a novel large-scale corpus of manual annotations for the SoccerNet video dataset, along with open challenges to encourage more research in soccer understanding and broadcast production.… ▽ More

    Submitted 19 April, 2021; v1 submitted 26 November, 2020; originally announced November 2020.

    Comments: Paper accepted for the CVsports workshop at CVPR2021. This document contains 8 pages + references + supplementary material

  20. arXiv:2004.07544  [pdf, other

    cs.CV eess.IV

    Multimodal and multiview distillation for real-time player detection on a football field

    Authors: Anthony Cioppa, Adrien Deliège, Noor Ul Huda, Rikke Gade, Marc Van Droogenbroeck, Thomas B. Moeslund

    Abstract: Monitoring the occupancy of public sports facilities is essential to assess their use and to motivate their construction in new places. In the case of a football field, the area to cover is large, thus several regular cameras should be used, which makes the setup expensive and complex. As an alternative, we developed a system that detects players from a unique cheap and wide-angle fisheye camera a… ▽ More

    Submitted 16 April, 2020; originally announced April 2020.

    Comments: Accepted for the CVSports workshop of CVPR 2020 ; 8 pages + references

  21. arXiv:1912.01326  [pdf, other

    cs.CV cs.LG eess.IV

    A Context-Aware Loss Function for Action Spotting in Soccer Videos

    Authors: Anthony Cioppa, Adrien Deliège, Silvio Giancola, Bernard Ghanem, Marc Van Droogenbroeck, Rikke Gade, Thomas B. Moeslund

    Abstract: In video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In this paper, we propose a novel loss function that specifically considers the temporal context naturally present around each action, rather than focusing on the single annotated frame to spot. We benchmark our loss on a large dataset of soccer videos, SoccerNet, and ac… ▽ More

    Submitted 30 March, 2020; v1 submitted 3 December, 2019; originally announced December 2019.

    Comments: Accepted for CVPR2020 main conference. This document contains 8 pages + references + supplementary material

  22. arXiv:1911.05588  [pdf, other

    cs.LG cs.AI cs.CV stat.ML

    An Effective Hit-or-Miss Layer Favoring Feature Interpretation as Learned Prototypes Deformations

    Authors: A. Deliege, A. Cioppa, M. Van Droogenbroeck

    Abstract: Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of more effective networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers, but this often comes at the expense of producing uninterpretable black boxes. In this paper,… ▽ More

    Submitted 22 February, 2019; originally announced November 2019.

    Comments: In AAAI-19 Workshop on Network Interpretability for Deep Learning. Published version of arXiv:1806.06519

  23. arXiv:1806.06519  [pdf, other

    cs.CV cs.AI

    HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules

    Authors: Adrien Deliège, Anthony Cioppa, Marc Van Droogenbroeck

    Abstract: Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of better networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers. In this paper, we show how to redesign a simple network to reach excellent performances, which are b… ▽ More

    Submitted 18 June, 2018; originally announced June 2018.