Search Results for author:
Found 81 papers, 24 papers with code
MMCBE: Multi-modality Dataset for Crop Biomass Prediction and Beyond
Addressing this gap, we introduce a new dataset in this domain, i. e. Multi-modality dataset for crop biomass estimation (MMCBE).
Orientation-conditioned Facial Texture Mapping for Video-based Facial Remote Photoplethysmography Estimation
We demonstrate significant performance improvements of up to 29. 6% in all tested motion scenarios in cross-dataset testing on MMPD, even in the presence of dynamic and unconstrained subject motion, emphasizing the benefits of disentangling motion through modeling the 3D facial surface for motion robust facial rPPG estimation.
Backpropagation-free Network for 3D Test-time Adaptation
Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data.
RG-CAT: Detection Pipeline and Catalogue of Radio Galaxies in the EMU Pilot Survey
The Gal-DINO network is trained and evaluated on approximately 5, 000 visually inspected radio galaxies and their infrared hosts, encompassing both compact and extended radio morphologies.
Deep Learning Approaches for Seizure Video Analysis: A Review
Historically, these approaches have been used for disease detection, classification, and prediction using diagnostic data; however, there has been limited exploration of their application in evaluating video-based motion detection in the clinical epileptology setting.
A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection
We present a novel multimodal dataset developed by expert astronomers to automate the detection and localisation of multi-component extended radio galaxies and their corresponding infrared hosts.
RadioGalaxyNET: Dataset and Novel Computer Vision Algorithms for the Detection of Extended Radio Galaxies and Infrared Hosts
Creating radio galaxy catalogues from next-generation deep surveys requires automated identification of associated components of extended sources and their corresponding infrared hosts.
Ranked #1 on
2D Object Detection
on RadioGalaxyNET Dataset
Syn3DWound: A Synthetic Dataset for 3D Wound Bed Analysis
Wound management poses a significant challenge, particularly for bedridden patients and the elderly.
Continual Test-time Domain Adaptation via Dynamic Sample Selection
DSS consists of dynamic thresholding, positive learning, and negative learning processes.
Hyperbolic Audio-visual Zero-shot Learning
Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training.
Ranked #2 on
GZSL Video Classification
on ActivityNet-GZSL (cls)
Deep Learning for Morphological Identification of Extended Radio Galaxies using Weak Labels
The CAMs are further refined using an inter-pixel relations network (IRNet) to get instance segmentation masks over radio galaxies and the positions of their infrared hosts.
Automatic Illumination Spectrum Recovery
We develop a deep learning network to estimate the illumination spectrum of hyperspectral images under various lighting conditions.
CVB: A Video Dataset of Cattle Visual Behaviors
Therefore, we introduce a new dataset, called Cattle Visual Behaviors (CVB), that consists of 502 video clips, each fifteen seconds long, captured in natural lighting conditions, and annotated with eleven visually perceptible behaviors of grazing cattle.
Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey
This paper is about where and how optimal transport is used in machine learning with a focus on the question of scalable optimal transport.
Topological Deep Learning: A Review of an Emerging Paradigm
The summaries obtained by these methods are principled global descriptions of multi-dimensional data whilst exhibiting stable properties such as robustness to deformation and noise.
A Hyperspectral and RGB Dataset for Building Facade Segmentation
Hyperspectral Imaging (HSI) provides detailed spectral information and has been utilised in many real-world applications.
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partial known data.
What Images are More Memorable to Machines?
This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence.
Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning
Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process.
Learning Deep Optimal Embeddings with Sinkhorn Divergences
Deep Metric Learning algorithms aim to learn an efficient embedding space to preserve the similarity relationships among the input data.
Curved Geometric Networks for Visual Anomaly Recognition
Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature.
CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping
We present a simple method, CropMix, for the purpose of producing a rich input distribution from the original dataset distribution.
Monitoring of Pigmented Skin Lesions Using 3D Whole Body Imaging
A modular camera rig arranged in a cylindrical configuration was designed to automatically capture images of the entire skin surface of a subject synchronously from multiple angles.
Pyramidal Attention for Saliency Detection
Consequently, we present a new SOD perspective of generating RGB-D SOD without acquiring depth data during training and testing and assist RGB methods with depth clues for improved performance.
Towards Open-Set Object Detection and Discovery
This new task aims to extend the ability of open-set object detectors to further discover the categories of unknown objects based on their visual appearance without human effort.
Learning Dense Correspondence from Synthetic Environments
Results show that training 2D-3D mapping network models on synthetic data is a viable alternative to using real data.
GOSS: Towards Generalized Open-set Semantic Segmentation
In this paper, we present and study a new image segmentation task, called Generalized Open-set Semantic Segmentation (GOSS).
Continuous Human Action Recognition for Human-Machine Interaction: A Review
With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams.
You Only Cut Once: Boosting Data Augmentation with a Single Cut
We present You Only Cut Once (YOCO) for performing data augmentations.
Transcribing Natural Languages for The Deaf via Neural Editing Programs
This work studies the task of glossification, of which the aim is to em transcribe natural spoken language sentences for the Deaf (hard-of-hearing) community to ordered sign language glosses.
In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains
Medical applications have benefited greatly from the rapid advancement in computer vision.
Towards a Robust Differentiable Architecture Search under Label Noise
Our empirical evaluations show that the noise injecting operation does not degrade the performance of the NAS algorithm if the data is indeed clean.
Declarative nets that are equilibrium models
We show that using a kernelised generalised linear model (kGLM) as an inner problem in a DDN yields a large class of commonly used DEQ architectures with a closed-form expression for the hidden layer parameters in terms of the kernel.
Feature Correlation Aggregation: on the Path to Better Graph Neural Networks
The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbors.
Blind Image Decomposition
We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown.
A Survey on Graph-Based Deep Learning for Computational Histopathology
With the remarkable success of representation learning for prediction problems, we have witnessed a rapid expansion of the use of machine learning and deep learning for the analysis of digital pathology and biopsy image patches.
Underwater Image Restoration via Contrastive Learning and a Real-world Dataset
There are 2000 reference restored images and 6003 original underwater images in the unpaired training set.
Towards Interpretable Attention Networks for Cervical Cancer Analysis
Here, we evaluate various state-of-the-art deep learning models and attention-based frameworks for the classification of images of multiple cervical cells.
Video-Based Inpatient Fall Risk Assessment: A Case Study
Inpatient falls are a serious safety issue in hospitals and healthcare facilities.
Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
It has become critical to explore how machine learning and specifically deep learning methods can be exploited to analyse healthcare data.
Dual Contrastive Learning for Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data.
Zero-Shot Learning on 3D Point Cloud Objects and Beyond
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification.
Reinforced Attention for Few-Shot Learning and Beyond
Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images.
Single Underwater Image Restoration by Contrastive Learning
Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world.
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces
In this paper, we propose addressing this problem using a mixture of subspaces.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Kernel Methods in Hyperbolic Spaces
However, working in hyperbolic spaces is not without difficulties as a result of its curved geometry (e. g., computing the Frechet mean of a set of points requires an iterative algorithm).
Set Augmented Triplet Loss for Video Person Re-Identification
Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss.
Channel Recurrent Attention Networks for Video Pedestrian Retrieval
Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks.
Cross-Correlated Attention Networks for Person Re-Identification
Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered.
Attention Based Real Image Restoration
Furthermore, the evaluation in terms of quantitative metrics and visual quality for four restoration tasks i. e. Denoising, Super-resolution, Raindrop Removal, and JPEG Compression on 11 real degraded datasets against more than 30 state-of-the-art algorithms demonstrate the superiority of our R$^2$Net.
Mosaic Super-resolution via Sequential Feature Pyramid Networks
Additionally, to the best of our knowledge, our method is the first specialized method to super-resolve mosaic images, whether it be multi-spectral or Bayer.
A Systematic Evaluation: Fine-Grained CNN vs. Traditional CNN Classifiers
In this work, we investigate the performance of the landmark general CNN classifiers, which presented top-notch results on large scale classification datasets, on the fine-grained datasets, and compare it against state-of-the-art fine-grained classifiers.
Transferring Cross-domain Knowledge for Video Sign Language Recognition
To this end, we extract news signs using a base WSLR model, and then design a classifier jointly trained on news and isolated signs to coarsely align these two domain features.
Contextually Plausible and Diverse 3D Human Motion Prediction
We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses.
Transductive Zero-Shot Learning for 3D Point Cloud Classification
This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification.
Neural Memory Networks for Seizure Type Classification
Inspired by recent advances in neural memory networks (NMNs), we introduce a novel approach for the classification of seizure type using electrophysiological data.
CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation
We present a new approach for a single view, image-based object pose estimation.
Ranked #13 on
6D Pose Estimation using RGB
on Occlusion LineMOD
Multi-FAN: Multi-Spectral Mosaic Super-Resolution Via Multi-Scale Feature Aggregation Network
This mosaic image is then merged with the mosaic image generated by the SR network to produce a quantitatively superior image.
Super-resolved Chromatic Mapping of Snapshot Mosaic Image Sensors via a Texture Sensitive Residual Network
This paper introduces a novel method to simultaneously super-resolve and colour-predict images acquired by snapshot mosaic sensors.
Learning Variations in Human Motion via Mix-and-Match Perturbation
In this paper, we introduce an approach to stochastically combine the root of variations with previous pose information, which forces the model to take the noise into account.
Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
In this paper, we therefore propose a loss to specifically address the hubness problem.
Zero-shot Learning of 3D Point Cloud Objects
A challenge for a 3D point cloud recognition system is, then, to classify objects from new, unseen, classes.
The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation
Determining the position and orientation of a calibrated camera from a single image with respect to a 3D model is an essential task for many applications.
3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds
This paper introduces the 3DCapsule, which is a 3D extension of the recently introduced Capsule concept that makes it applicable to unordered point sets.
VIENA2: A Driving Anticipation Dataset
Action anticipation is critical in scenarios where one needs to react before the action is finalized.
Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
Our approach builds on the observation that foreground and background classes are not affected in the same manner by the domain shift, and thus should be treated differently.
Improving Object Localization with Fitness NMS and Bounded IoU Loss
We demonstrate that many detection methods are designed to identify only a sufficently accurate bounding box, rather than the best available one.
Soft Correspondences in Multimodal Scene Parsing
We propose to address this issue, by formulating multimodal semantic labeling as inference in a CRF and introducing latent nodes to explicitly model inconsistencies between two modalities.
Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence
Estimating the 6-DoF pose of a camera from a single image relative to a pre-computed 3D point-set is an important task for many computer vision applications.
Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation
Our experiments demonstrate the benefits of our classifier heatmaps and of our two-stream architecture on challenging urban scene datasets and on the YouTube-Objects benchmark, where we obtain state-of-the-art results.
Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
We then show how to obtain multi-class masks by the fusion of foreground/background ones with information extracted from a weakly-supervised localization network.
DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
Subsequently we identify a sparse distribution estimation scheme, Directed Sparse Sampling, and employ it in a single end-to-end CNN based detection model.
Ranked #17 on
Object Detection
on PASCAL VOC 2007
Encouraging LSTMs to Anticipate Actions Very Early
In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos.
Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation
We outperform the state-of-the-art methods that, as us, rely only on RGB frames as input for both action recognition and anticipation.
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
Hence, weak supervision using only image tags could have a significant impact in semantic segmentation.
DecomposeMe: Simplifying ConvNets for End-to-End Learning
Deep learning and convolutional neural networks (ConvNets) have been successfully applied to most relevant tasks in the computer vision community.
GOGMA: Globally-Optimal Gaussian Mixture Alignment
Gaussian mixture alignment is a family of approaches that are frequently used for robustly solving the point-set registration problem.
Cutting Edge: Soft Correspondences in Multimodal Scene Parsing
In this paper, we address the problem of data misalignment and label inconsistencies, e. g., due to moving objects, in semantic labeling, which violate the assumption of existing techniques.
Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering
By contrast, nonparametric approaches, which bypass any learning phase and directly transfer the labels from the training data to the query images, can readily exploit new labeled samples as they become available.
An Adaptive Data Representation for Robust Point-Set Registration and Merging
This paper presents a framework for rigid point-set registration and merging using a robust continuous data representation.
