Search Results for author:
Found 36 papers, 19 papers with code
MC-hands-1M: A glove-wearing hand dataset for pose estimation
Nowadays, the need for large amounts of carefully and complexly annotated data for the training of computer vision modules continues to grow.
Multi-manifold Attention for Vision Transformers
Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition.
Ranked #1 on
Image Classification
on Tiny-ImageNet
(Top-1 Accuracy metric)
Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture
In this work we introduce a biologically inspired long-range skip connection for the UNet architecture that relies on the perceptual illusion of hybrid images, being images that simultaneously encode two images.
Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues
Spherical cameras capture scenes in a holistic manner and have been used for room layout estimation.
SHREC 2022: Protein-ligand binding site recognition
This paper presents the methods that have participated in the SHREC 2022 contest on protein-ligand binding site recognition.
A benchmark with decomposed distribution shifts for 360 monocular depth estimation
In this work we contribute a distribution shift benchmark for a computer vision task; monocular depth estimation.
On Coordinate Decoding for Keypoint Estimation Tasks
A series of 2D (and 3D) keypoint estimation tasks are built upon heatmap coordinate representation, i. e. a probability map that allows for learnable and spatially aware encoding and decoding of keypoint coordinates on grids, even allowing for sub-pixel coordinate accuracy.
HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media
HUMAN4D is introduced to the computer vision and graphics research communities to enable joint research on spatio-temporally aligned pose, volumetric, mRGBD and audio data cues.
DeepMoCap: Deep Optical Motion Capture Using Multiple Depth Sensors and Retro-Reflectors
DeepMoCap explores motion capture by automatically localizing and labeling reflectors on depth images and, subsequently, on 3D space.
Pano3D: A Holistic Benchmark and a Solid Baseline for $360^o$ Depth Estimation
Pano3D is a new benchmark for depth estimation from spherical panoramas.
Continuous Sign Language Recognition through a Context-Aware Generative Adversarial Network
The proposed network architecture consists of a generator that recognizes sign language glosses by extracting spatial and temporal features from video sequences, as well as a discriminator that evaluates the quality of the generator’s predictions by modeling text information at the sentence and gloss levels.
Serverless Streaming for Emerging Media: Towards 5G Network-Driven Cost Optimization
Immersive 3D media is an emerging type of media that captures, encodes and reconstructs the 3D appearance of people and objects, with applications in tele-presence, teleconference, entertainment, gaming and other fields.
Networking and Internet Architecture Multimedia
Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas
In this work we show how to estimate full room layouts in a single-shot, eliminating the need for postprocessing.
[Re] On end-to-end 6{DoF} object pose estimation and robustness to object scale
We communicated with the authors of [1] through GitHub, and we would like to thank them as they provided a fast and detailed response.
SHREC 2020 track: 6D Object Pose Estimation
From captured color and depth images, we use this simulator to generate a 3D dataset which has 400 photo-realistic synthesized color-and-depth image pairs with various view angles for training, and another 100 captured and synthetic images for testing.
Comprehensive Comparison of Deep Learning Models for Lung and COVID-19 Lesion Segmentation in CT scans
In this paper, an extensive comparison of DL models for lung and COVID-19 lesion segmentation in Computerized Tomography (CT) scans is presented, which can also be used as a benchmark for testing medical image segmentation models.
DronePose: Photorealistic UAV-Assistant Dataset Synthesis for 3D Pose Estimation via a Smooth Silhouette Loss
In this context, the 3D localisation of the UAV assistant is an important task that can facilitate the exchange of spatial information between the user and the UAV.
Ranked #1 on
Drone Pose Estimation
on UAVA
Multi-view adaptive graph convolutions for graph classification
In this paper, a novel multi-view methodology for graph-based neural networks is proposed.
A Comprehensive Study on Deep Learning-based Methods for Sign Language Recognition
In this paper, a comparative experimental assessment of computer vision-based methods for sign language recognition is conducted.
Neural Network Compression Using Higher-Order Statistics and AuxiliaryReconstruction Losses
In this paper, the problem of pruning and compressingthe weights of various layers of deep neural networks is in-vestigated.
Deep Lighting Environment Map Estimation from Spherical Panoramas
We approach this problem differently, exploiting the availability of surface geometry to employ image-based relighting as a data generator and supervision mechanism.
Continuous Sign Language Recognition Through Cross-Modal Alignment of Video and Text Embeddings in a Joint-Latent Space
The proposed method is trained jointly with video and text latent representations.
A Deep Learning Approach to Object Affordance Segmentation
In particular, we design an autoencoder that is trained using ground-truth labels of only the last frame of the sequence, and is able to infer pixel-wise affordance labels in both videos and static images.
Deep Soft Procrustes for Markerless Volumetric Sensor Alignment
This is accomplished by a soft, differentiable procrustes analysis that regularizes the segmentation and achieves higher extrinsic calibration performance in expanded sensor placement configurations, while being unrestricted by the number of sensors of the volumetric capture system.
DeepSurf: A surface-based deep learning approach for the prediction of ligand binding sites on proteins
The knowledge of potentially druggable binding sites on proteins is an important preliminary step towards the discovery of novel drugs.
An Improved Tobit Kalman Filter with Adaptive Censoring Limits
Firstly, the exact covariance matrix of the censored measurements is calculated by taking into account the censoring limits.
Restyling Data: Application to Unsupervised Domain Adaptation
Machine learning is driven by data, yet while their availability is constantly increasing, training data require laborious, time consuming and error-prone labelling or ground truth acquisition, which in some cases is very difficult or even impossible.
Spherical View Synthesis for Self-Supervised 360 Depth Estimation
This has led to the utilization of view synthesis as an indirect objective for learning depth estimation using efficient data acquisition procedures.
$360^o$ Surface Regression with a Hyper-Sphere Loss
We present a dataset of $360^o$ images of indoor spaces with their corresponding ground truth surface normal, and train a deep convolutional neural network (CNN) on the task of monocular 360 surface estimation.
Self-Supervised Deep Depth Denoising
Specifically, the proposed autoencoder exploits multiple views of the same scene from different points of view in order to learn to suppress noise in a self-supervised end-to-end manner using depth and color information during training, yet only depth during inference.
A Low-Cost, Flexible and Portable Volumetric Capturing System
Multi-view capture systems are complex systems to engineer.
Examining Deep Learning Architectures for Crime Classification and Prediction
In this paper, a detailed study on crime classification and prediction using deep learning architectures is presented.
OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas
Recent work on depth estimation up to now has only focused on projective images ignoring 360 content which is now increasingly and more easily produced.
Ranked #18 on
Depth Estimation
on Stanford2D3D Panoramic
An Integrated Platform for Live 3D Human Reconstruction and Motion Capturing
The latest developments in 3D capturing, processing, and rendering provide means to unlock novel 3D application pathways.
Non-linear Convolution Filters for CNN-based Learning
However, while recent research results of neuroscience prove the existence of non-linear operations in the response of complex visual cells, little effort has been devoted to extend the convolution technique to non-linear forms.
Deep Affordance-grounded Sensorimotor Object Recognition
It is well-established by cognitive neuroscience that human perception of objects constitutes a complex process, where object appearance information is combined with evidence about the so-called object "affordances", namely the types of actions that humans typically perform when interacting with them.
