90 citations · 279 across the 30 of their papers we have counts for
30 papers
RAIDAL: Redundancy-Aware Information Density Active Learning for CTC-Based Continuous Sign Language Recognition
Rafael A. Diniz Augusto, Gabriel L. Oliveira, Erickson R. Nascimento
Continuous sign language recognition (CSLR) is a key technology for accessibility, yet its development remains limited by the high cost of annotating continuous video streams. Acti…
Improving the matching of deformable objects by learning to detect keypoints
Felipe Cadar, Welerson Melo, Vaishnavi Kanagasabapathi +3
We propose a novel learned keypoint detection method to increase the number of correct matches for the task of non-rigid image correspondence. By leveraging true correspondences ac…
Enhancing Deformable Local Features by Jointly Learning to Detect and Describe Keypoints
Guilherme Potje, Felipe Cadar, Andre Araujo +2
Local feature extraction is a standard approach in computer vision for tackling important tasks such as image matching and retrieval. The core assumption of most methods is that im…
Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images
Welerson Melo, Guilherme Potje, Felipe Cadar +2
We present a novel learned keypoint detection method designed to maximize the number of correct matches for the task of non-rigid image correspondence. Our training framework uses…
Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approach
Abdulrahman Kerim, Felipe Chamone, Washington Ramos +3
Recent semantic segmentation models perform well under standard weather conditions and sufficient illumination but struggle with adverse weather conditions and nighttime. Collectin…
Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions
Abdulrahman Kerim, Washington L. S. Ramos, Leandro Soriano Marcolino +2
Video stabilization plays a central role to improve videos quality. However, despite the substantial progress made by these methods, they were, mainly, tested under standard weathe…
Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method
Washington Ramos, Michel Silva, Edson Araujo +4
The growth of videos in our digital age and the users' limited time raise the demand for processing untrimmed videos to produce shorter versions conveying the same information. Des…
Learning Geodesic-Aware Local Features from RGB-D Images
Guilherme Potje, Renato Martins, Felipe Cadar +1
Most of the existing handcrafted and learning-based local descriptors are still at best approximately invariant to affine image transformations, often disregarding deformable surfa…
Extracting Deformation-Aware Local Features by Learning to Deform
Guilherme Potje, Renato Martins, Felipe Cadar +1
Despite the advances in extracting local features achieved by handcrafted and learning-based descriptors, they are still limited by the lack of invariance to non-rigid transformati…
Creating and Reenacting Controllable 3D Humans with Differentiable Rendering
Thiago L. Gomes, Thiago M. Coutinho, Rafael Azevedo +2
This paper proposes a new end-to-end neural rendering architecture to transfer appearance and reenact human actors. Our method leverages a carefully designed graph convolutional ne…
Introducing the structural bases of typicality effects in deep learning
Omar Vidal Pino, Erickson Rangel Nascimento, Mario Fernando Montenegro Campos
In this paper, we hypothesize that the effects of the degree of typicality in natural semantic categories can be generated based on the structure of artificial categories learned w…
A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos
Thiago L. Gomes, Renato Martins, João Ferreira +3
Transferring human motion and appearance between videos of human actors remains one of the key challenges in Computer Vision. Despite the advances from recent image-to-image transl…
Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio
João P. Ferreira, Thiago M. Coutinho, Thiago L. Gomes +4
Synthesizing human motion through learning techniques is becoming an increasingly popular approach to alleviating the requirement of new data capture to produce animations. Learnin…
A Sparse Sampling-based framework for Semantic Fast-Forward of First-Person Videos
Michel Melo Silva, Washington Luis Souza Ramos, Mario Fernando Montenegro Campos +1
Technological advances in sensors have paved the way for digital cameras to become increasingly ubiquitous, which, in turn, led to the popularity of the self-recording culture. As…
A gaze driven fast-forward method for first-person videos
Alan Carvalho Neves, Michel Melo Silva, Mario Fernando Montenegro Campos +1
The growing data sharing and life-logging cultures are driving an unprecedented increase in the amount of unedited First-Person Videos. In this paper, we address the problem of acc…
Straight to the Point: Fast-forwarding Videos via Reinforcement Learning Using Textual Data
Washington Ramos, Michel Silva, Edson Araujo +2
The rapid increase in the amount of published visual data and the limited time of users bring the demand for processing untrimmed videos to produce shorter versions that convey the…
Extending Maps with Semantic and Contextual Object Information for Robot Navigation: a Learning-Based Framework using Visual and Depth Cues
Renato Martins, Dhiego Bersan, Mario F. M. Campos +1
This paper addresses the problem of building augmented metric representations of scenes with semantic information from RGB-D images. We propose a complete framework to create an en…
Do As I Do: Transferring Human Motion and Appearance between Monocular Videos with Spatial and Temporal Constraints
Thiago L. Gomes, Renato Martins, João Ferreira +1
Creating plausible virtual actors from images of real actors remains one of the key challenges in computer vision and computer graphics. Marker-less human motion estimation and sha…
Personalizing Fast-Forward Videos Based on Visual and Textual Features from Social Network
Washington L. S. Ramos, Michel M. Silva, Edson R. Araujo +2
The growth of Social Networks has fueled the habit of people logging their day-to-day activities, and long First-Person Videos (FPVs) are one of the main tools in this new habit. S…
Global Semantic Description of Objects based on Prototype Theory
Omar Vidal Pino, Erickson Rangel Nascimento, Mario Fernando Montenegro Campos
In this paper, we introduce a novel semantic description approach inspired on Prototype Theory foundations. We propose a Computational Prototype Model (CPM) that encodes and stores…
Visual-Quality-Driven Learning for Underwater Vision Enhancement
Walysson Vital Barbosa, Henrique Grandinetti Barbosa Amaral, Thiago Lages Rocha +1
The image processing community has witnessed remarkable advances in enhancing and restoring images. Nevertheless, restoring the visual quality of underwater images remains a great…
A Two-Step Learning Method For Detecting Landmarks on Faces From Different Domains
Bruna Vieira Frade, Erickson R. Nascimento
The detection of fiducial points on faces has significantly been favored by the rapid progress in the field of machine learning, in particular in the convolution networks. However,…
Fast forwarding Egocentric Videos by Listening and Watching
Vinicius S. Furlan, Ruzena Bajcsy, Erickson R. Nascimento
The remarkable technological advance in well-equipped wearable devices is pushing an increasing production of long first-person videos. However, since most of these videos have lon…
A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos
Michel Melo Silva, Washington Luis Souza Ramos, Joao Klock Ferreira +3
Thanks to the advances in the technology of low-cost digital cameras and the popularity of the self-recording culture, the amount of visual data on the Internet is going to the opp…