Search Results for author:
Found 52 papers, 31 papers with code
Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Dataset
This paper introduces the Raw Natural Image Noise Dataset (RawNIND), a diverse collection of paired raw images designed to support the development of denoising models that generalize across sensors, image development workflows, and styles.
Online Gaussian Test-Time Adaptation of Vision-Language Models
We demonstrate that OGA outperforms state-of-the-art methods on most datasets and runs.
Realistic Test-Time Adaptation of Vision-Language Models
Our work challenges these favorable deployment scenarios, and introduces a more realistic evaluation framework, including: (i) a variable number of effective classes for adaptation within a single batch, and (ii) non-i. i. d.
SoccerNet 2024 Challenges Results
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team.
Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification
Vision-Language Models for remote sensing have shown promising uses thanks to their extensive pretraining.
Ranked #1 on
Transductive Zero-Shot Classification
on WHURS19
MPL: Lifting 3D Human Pose from Multi-view 2D Poses
Estimating 3D human poses from 2D images is challenging due to occlusions and projective acquisition.
Sequential Representation Learning via Static-Dynamic Conditional Disentanglement
This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos.
Keypoint Promptable Re-Identification
Inspired by recent work on prompting in vision, we introduce Keypoint Promptable ReID (KPR), a novel formulation of the ReID problem that explicitly complements the input bounding box with a set of semantic keypoints indicating the intended target.
Ranked #1 on
Person Re-Identification
on Occluded-DukeMTMC
Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesis
This work introduces a novel augmentation method that increases the diversity of a train set to improve the generalization abilities of a 6D pose estimation network.
Domain Generalization for In-Orbit 6D Pose Estimation
We address the problem of estimating the relative 6D pose, i. e., position and orientation, of a target spacecraft, from a monocular image, a key capability for future autonomous Rendezvous and Proximity Operations.
Leveraging Neural Radiance Fields for Pose Estimation of an Unknown Space Object during Proximity Operations
We train the NeRF model using a sparse collection of images that depict the target, and in turn generate a large dataset that is diverse both in terms of viewpoint and illumination.
Self-supervised vision-langage alignment of deep learning representations for bone X-rays analysis
This paper proposes leveraging vision-language pretraining on bone X-rays paired with French reports to address downstream tasks of interest on bone radiography.
Self-Avatar Animation in Virtual Reality: Impact of Motion Signals Artifacts on the Full-Body Pose Reconstruction
Nevertheless, the limitations of these systems are multiples: the desynchronization between the two motion sources and occlusions are examples of significant issues that hinder the implementations of such systems.
Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments
In the era of the Internet of Things (IoT), objects connect through a dynamic network, empowered by technologies like 5G, enabling real-time data sharing.
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).
Ranked #1 on
Game State Reconstruction
on SoccerNet-GSR
Camera clustering for scalable stream-based active distillation
We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques.
Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking
To demonstrate the effectiveness of PRTreID, it is integrated with a state-of-the-art tracking method, using a part-based post-processing module to handle long-term tracking.
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
Context-Aware 3D Object Localization from Single Calibrated Images: A Study of Basketballs
Accurately localizing objects in three dimensions (3D) is crucial for various computer vision applications, such as robotics, autonomous driving, and augmented reality.
On the Importance of Denoising when Learning to Compress Images
Image noise is ubiquitous in photography.
An Experimental Investigation into the Evaluation of Explainability Methods
EXplainable Artificial Intelligence (XAI) aims to help users to grasp the reasoning behind the predictions of an Artificial Intelligence (AI) system.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?
Turning the weights to zero when training a neural network helps in reducing the computational complexity at inference.
1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results
The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection.
Body Part-Based Representation Learning for Occluded Person Re-Identification
Firstly, individual body part appearance is not as discriminative as global appearance (two distinct IDs might have the same local appearance), this means standard ReID training objectives using identity labels are not adapted to local feature learning.
Ranked #1 on
Person Re-Identification
on P-DukeMTMC-reID
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Forward Error Correction applied to JPEG-XS codestreams
JPEG-XS offers low complexity image compression for applications with constrained but reasonable bit-rate, and low latency.
Accelerating the creation of instance segmentation training sets through bounding box annotation
Various strategies are then investigated to balance the human manual annotation resources between bounding-box definition and mask correction, including when the correction of instance masks is prioritized based on their overlap with other instance bounding-boxes, or the outcome of an instance segmentation model trained on a partially annotated dataset.
Poly-CAM: High resolution class activation map for convolutional neural networks
The need for Explainable AI is increasing with the development of deep learning.
Ball 3D Localization From A Single Calibrated Image
In this work, we propose to address the task on a single image from a calibrated monocular camera by estimating ball diameter in pixels and use the knowledge of real ball diameter in meters.
DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes
In addition to the increased complexity resulting from the multiplication of single-task models, the use of the off-the-shelf models also impedes the performance due to the complexity and specificity of the team sports scenes, such as strong occlusion and motion blur.
End-to-end optimized image compression with competition of prior distributions
Convolutional autoencoders are now at the forefront of image compression research.
Learning sparse DNNs with soft thresholding of weights during training
This paper proposes a new and simple way of training sparse neural networks.
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.
ModulOM: Disseminating Deep Learning Research with Modular Output Mathematics
But this is not the case for output mathematics.
Intraclass clustering: an implicit learning ability that regularizes DNNs
Several works have shown that the regularization mechanisms underlying deep neural networks' generalization performances are still poorly understood.
Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noise
In industrial vision, the anomaly detection problem can be addressed with an autoencoder trained to map an arbitrary image, i. e. with or without any defect, to a clean image, i. e. without any defect.
How semantic and geometric information mutually reinforce each other in ToF object localization
We propose a novel approach to localize a 3D object from the intensity and depth information images provided by a Time-of-Flight (ToF) sensor.
Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup
This paper considers the task of detecting the ball from a single viewpoint in the challenging but common case where the ball interacts frequently with players while being poorly contrasted with respect to the background.
Ranked #6 on
Sports Ball Detection and Tracking
on Badminton
Adapting JPEG XS gains and priorities to tasks and contents
Most current research in the domain of image compression focuses solely on achieving state of the art compression ratio, but that is not always usable in today's workflow due to the constraints on computing resources.
Associative Embedding for Game-Agnostic Team Discrimination
Assigning team labels to players in a sport game is not a trivial task when no prior is known about the visual appearance of each team.
Natural Image Noise Dataset
We introduce the Natural Image Noise Dataset (NIND), a dataset of DSLR-like images with varying levels of ISO noise which is large enough to train models for blind denoising over a wide range of noise.
Layer rotation: a surprisingly simple indicator of generalization in deep networks?
Our work presents empirical evidence that layer rotation, i. e. the evolution across training of the cosine distance between each layer's weight vector and its initialization, constitutes an impressively consistent indicator of generalization performance.
An experimental study of layer-level training speed and its impact on generalization
How optimization influences the generalization ability of a DNN is still an active area of research.
Layer rotation: a surprisingly powerful indicator of generalization in deep networks?
Our work presents extensive empirical evidence that layer rotation, i. e. the evolution across training of the cosine distance between each layer's weight vector and its initialization, constitutes an impressively consistent indicator of generalization performance.
I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images
This represents an important advantage of the I-HAZE dataset that allows us to objectively compare the existing image dehazing techniques using traditional image quality metrics such as PSNR and SSIM.
O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images
Haze removal or dehazing is a challenging ill-posed problem that has drawn a significant attention in the last few years.
Discovering the mechanics of hidden neurons
Neural networks trained through stochastic gradient descent (SGD) have been around for more than 30 years, but they still escape our understanding.
Piecewise-Planar 3D Approximation From Wide-Baseline Stereo
This paper approximates the 3D geometry of a scene by a small number of 3D planes.
Cell segmentation with random ferns and graph-cuts
To isolate individual cells in live imaging data, we introduce an elegant image segmentation framework that effectively extracts cell boundaries, even in the presence of poor edge details.
Iterative hypothesis testing for multi-object tracking in presence of features with variable reliability
This paper assumes prior detections of multiple targets at each time instant, and uses a graph-based approach to connect those detections across time, based on their position and appearance estimates.
Discriminative and Efficient Label Propagation on Complementary Graphs for Multi-Object Tracking
Given a set of detections, detected at each time instant independently, we investigate how to associate them across time.
Compressive Optical Deflectometric Tomography: A Constrained Total-Variation Minimization Approach
Optical Deflectometric Tomography (ODT) provides an accurate characterization of transparent materials whose complex surfaces present a real challenge for manufacture and control.
