Search Results for author:
Found 28 papers, 16 papers with code
HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules
In this paper, we show how to redesign a simple network to reach excellent performances, which are better than the results reproduced with CapsNet on several datasets, by replacing a layer with a Hit-or-Miss layer.
A Context-Aware Loss Function for Action Spotting in Soccer Videos
We benchmark our loss on a large dataset of soccer videos, SoccerNet, and achieve an improvement of 12. 8% over the baseline.
Ranked #3 on
Action Spotting
on SoccerNet
Real-Time Semantic Background Subtraction
Semantic background subtraction SBS has been shown to improve the performance of most background subtraction algorithms by combining them with semantic information, derived from a semantic segmentation network.
Summarizing the performances of a background subtraction algorithm measured on several videos
In this paper, we present a theoretical approach to summarize the performances for multiple videos that preserves the relationships between performance indicators.
Multimodal and multiview distillation for real-time player detection on a football field
As an alternative, we developed a system that detects players from a unique cheap and wide-angle fisheye camera assisted by a single narrow-angle thermal camera.
SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
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.
Ranked #1 on
Camera shot segmentation
on SoccerNet-v2
Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
Specifically, we distill a powerful commercial calibration tool in a recent neural network architecture on the large-scale SoccerNet dataset, composed of untrimmed broadcast videos of 500 soccer games.
M4Depth: Monocular depth estimation for autonomous vehicles in unseen environments
We use these cost volumes to leverage the visual spatio-temporal constraints imposed by motion and to make the network robust for varied scenes.
Ranked #2 on
Monocular Depth Estimation
on Mid-Air Dataset
Ordinal Pooling
More importantly, they also demonstrate that ordinal pooling leads to consistent improvements in the accuracy over average- or max-pooling operations while speeding up the training and alleviating the issue of the choice of the pooling operations and activation functions to be used in the networks.
Ghost Loss to Question the Reliability of Training Data
For that purpose, we introduce the notion of ghost loss, which can be seen as a regular loss that is zeroed out for some predicted values in a deterministic way and that allows the network to choose an alternative to the given label without being penalized.
Survey and synthesis of state of the art in driver monitoring
Road-vehicle accidents are mostly due to human errors, and many such accidents could be avoided by continuously monitoring the driver.
An exploration of the performances achievable by combining unsupervised background subtraction algorithms
Background subtraction (BGS) is a common choice for performing motion detection in video.
SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos
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.
Semi-Supervised Training to Improve Player and Ball Detection in Soccer
More precisely, we design a teacher-student approach in which the teacher produces surrogate annotations on the unlabeled data to be used later for training a student which has the same architecture as the teacher.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance
In this paper, we define a probabilistic framework and present a formal proof of an algorithm for the unsupervised many-to-infinity domain adaptation of posteriors.
Adaptive Self-Training for Object Detection
In this work, we introduce our method Adaptive Self-Training for Object Detection (ASTOD), which is a simple yet effective teacher-student method.
Ranked #11 on
Semi-Supervised Object Detection
on COCO 2% labeled data
NA-SODINN: a deep learning algorithm for exoplanet image detection based on residual noise regimes
Supervised deep learning was recently introduced in high-contrast imaging (HCI) through the SODINN algorithm, a convolutional neural network designed for exoplanet detection in angular differential imaging (ADI) datasets.
Online Distillation with Continual Learning for Cyclic Domain Shifts
In this paper, we propose a solution to this issue by leveraging the power of continual learning methods to reduce the impact of domain shifts.
Towards Active Learning for Action Spotting in Association Football Videos
In this paper, we propose an active learning framework that selects the most informative video samples to be annotated next, thus drastically reducing the annotation effort and accelerating the training of action spotting models to reach the highest accuracy at a faster pace.
VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views
The Video Assistant Referee (VAR) has revolutionized association football, enabling referees to review incidents on the pitch, make informed decisions, and ensure fairness.
SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries
By providing broadcasters with a tool to summarize the content of their video with the same level of engagement as a live game, our method could help satisfy the needs of the numerous fans who follow their team but cannot necessarily watch the live game.
A technique to jointly estimate depth and depth uncertainty for unmanned aerial vehicles
When used by autonomous vehicles for trajectory planning or obstacle avoidance, depth estimation methods need to be reliable.
Autonomous Vehicles
Depth Aleatoric Uncertainty Estimation
+2
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders
In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%).
X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model
The rapid advancement of artificial intelligence has led to significant improvements in automated decision-making.
A Universal Protocol to Benchmark Camera Calibration for Sports
In particular, real-world non-planar sports field elements (such as goals, corner flags, baskets, ...) and image distortion caused by broadcast camera lenses are out of the scope of sports field registration methods.
SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap
This tracking and identification process is crucial for reconstructing the game state, defined by the athletes' positions and identities on a 2D top-view of the pitch, (i. e. a minimap).
