Accepted Papers
Full Papers
ID | Paper Title | Author Names | | Poster | Pitch | Citation |
|---|---|---|---|---|---|---|
| 3 | Talking with signs: A simple method to detect nouns and numbers in a non-annotated signs language corpus Action Recognition Full Paper Poster | Huiza, Eric Huiza; Olivares, César |  |  |  | Huiza, E. et al., (2021). Talking with signs: A simple method to detect nouns and numbers in a non-annotated signs language corpus [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/3_CameraReady_03.pdf |
| 4 | Assistive Signals for Deep Neural Network Classifiers Explainable AI Full Paper Poster | Pestana, Camilo Andres Pestana; Glance, David; Liu, Wei; Owens, Robyn A; Mian, Ajmal | |  | | Pestana, C. A. P. et al., (2021). Assistive Signals for Deep Neural Network Classifiers [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106251 |
| 8 | I Only Have Eyes for You: The Impact of Masks On Convolutional-Based Facial Expression Recognition Biometrics Full Paper Poster | Barros, Pablo; Sciutti, Alessandra | |  | | Barros, P. et al., (2021). I Only Have Eyes for You: The Impact of Masks On Convolutional-Based Facial Expression Recognition [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/8_CameraReady_08.pdf |
| 10 | Generalizable Multi-Camera 3D Pedestrian Detection 3D Vision Full Paper Oral | Lima, Joao Lima; Roberto, Rafael A; Figueiredo, Lucas; Magalhães Simões, Francisco Paulo; Teichrieb, Veronica | |  | | Lima, J. et al., (2021). Generalizable Multi-Camera 3D Pedestrian Detection [Oral Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106252 |
| 19 | Filter Distribution Templates in Convolutional Networks for Image Classification Tasks Deep Learning Full Paper Oral | Izquierdo Cordova, Ramon; Mayol-Cuevas, Walterio | |  | | Izquierdo Cordova, R. et al., (2021). Filter Distribution Templates in Convolutional Networks for Image Classification Tasks [Oral Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106253 |
| 22 | BAOD: Budget-Aware Object Detection Object Detection Full Paper Oral | Pardo, Alejandro; Xu, Mengmeng Frost; Thabet, Ali K; Arbeláez, Pablo; Ghanem, Bernard | |  | | Mengmeng Frost, X. et al., (2021). BAOD: Budget-Aware Object Detection [Oral Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106254 |
| 27 | On Disentanglement and Mutual Information in Semi-Supervised Variational Auto-Encoders Deep Learning Full Paper Poster | Gordon-Rodriguez, Elliott | |  | | Gordon-Rodriguez, E., (2021). On Disentanglement and Mutual Information in Semi-Supervised Variational Auto-Encoders [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai2021062517 |
| 47 | A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks Efficient Training Full Paper Poster | Suarez-Ramirez, Cuauhtemoc D; Gonzalez-Mendoza, Miguel; Chang Leonardo; Ochoa-Ruiz Gilberto; Duran-Vega, Mario A | |  | | Suarez-Ramirez, C. D. et al., (2021). A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106255 |
| 50 | MarkerPose: Robust Real-time Planar Target Tracking for Accurate Stereo Pose Estimation Pose Estimation Full Paper Oral | Meza, Jhacson; Romero, Lenny; Marrugo, Andrés | |  | | Meza, J. et al., (2021). MarkerPose: Robust Real-time Planar Target Tracking for Accurate Stereo Pose Estimation [Oral Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106256 |
| 40 | I Find Your Lack of Uncertainty in Computer Vision Disturbing Explainable AI Full Paper Oral | Valdenegro-Toro, Matias | |  | | Valdenegro-Toro, M., (2021). I Find Your Lack of Uncertainty in Computer Vision Disturbing [Oral Presentation]. International Conference on Machine Learning: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/40_CameraReady_40.pdf |
Extended Abstracts
ID | Paper Title | Author Names | | Poster | Pitch | Citation |
|---|---|---|---|---|---|---|
| 6 | Assessing deep learning methods for the identification of kidney stones composition in endoscopic images Medical Extended Abstract Poster | Lopez-Tiro, Francisco; Varelo-Silgado, Andres; Mendez Ruiz, Mauricio; Hinojosa-Alcaraz, Oscar; Gonzalez-Mendoza, Miguel; Vincent Estrade; Ochoa-Ruiz Gilberto; Daul Christian | |  | | Lopez-Tiro F. et al., (2021). Assessing deep learning methods for the identification of kidney stones composition in endoscopic images [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/6_CameraReady_06.pdf |
| 9 | Mobile Convolutional Neural Network for Neonatal Pain Assessment Image Classification Extended Abstract Oral | Carlini, Lucas P; Ferreira, Leonardo; Coutrin, Gabriel ; Varoto, Victor ; Marcondes Heiderich, Tatiany ; Balda, Rita ; Barros, Marina ; Guinsburg, Ruth ; Thomaz, Carlos E | |  | | Carlini, L. P. et al., (2021). Mobile Convolutional Neural Network for Neonatal Pain Assessment [Oral Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106258 |
| 13 | Visual-Syntactic Embedding for Video Captioning Video + Language Extended Abstract Oral | Perez-Martin, Jesus; Pérez, Jorge; Bustos, Benjamin | |  | | Perez-Martin, J. et al., (2021). Visual-Syntactic Embedding for Video Captioning [Oral Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106259 |
| 20 | Explainable, Automated Urban Interventions to Improve Pedestrian and Vehicle Safety Scene Analysis Extended Abstract Poster | Bustos, Cristina; Rhoads, Daniel; Solé-Ribalta, Albert; Masip, David; Arenas, Alex; Lapedriza, Agata; Borge-Holthoefer, Javier | |  | | Bustos, C. et al., (2021). Explainable, Automated Urban Interventions to Improve Pedestrian and Vehicle Safety [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/20_CameraReady_20.pdf |
| 21 | High-level camera-LiDAR fusion for 3D object detection with machine learning 3D Vision Extended Abstract Poster | Salazar, Gustavo A; Saavedra, Miguel Angel; Romero Cano, Victor A | |  | | Salazar, G. A. et al., (2021). High-level camera-LiDAR fusion for 3D object detection with machine learning [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai2021062510 |
| 28 | Improving Domain Generalization using Style Regularization Deep Learning Extended Abstract Poster | Pérez, Gustavo | |  | | Pérez, G., (2021). Improving Domain Generalization using Style Regularization [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai2021062512 |
| 29 | ProjectionNet and LRNet: Light and Fast ConvNets for Mammography Screening Projections Classification Medical Extended Abstract Poster | Ramirez, Radames r ; Sanchez, Abraham ; Iñiguez, Marco ; Moya, Eduardo Ulises; Cabrera Sanchez, Miguel Angel; Salas Aguirre, Sofia; Haro Morales, Claudia Eunice; Sanchez Montes, Alejandro | |  | | Ramirez, R. R. et al., (2021). ProjectionNet and LRNet: Light and Fast ConvNets for Mammography Screening Projections Classification [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/29_CameraReady_29.pdf |
| 34 | Attention YOLACT++ for real-time instance segmentation of medical instruments in endoscopic procedures Medical Extended Abstract Oral | Ángeles-Cerón, Juan Carlos; Ochoa-Ruiz, Gilberto; Chang, Leonardo; Ali, Sharib | |  | | Ángeles-Cerón, J. C. et al., (2021). Attention YOLACT++ for real-time instance segmentation of medical instruments in endoscopic procedures [Oral Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai2021062511 |
| 39 | Assessing the impact of the loss function, architecture and image type for Deep Learning-based wildfire segmentation Medical Extended Abstract Poster | Ciprián-Sánchez, Jorge F; Ochoa-Ruiz, Gilberto; Rossi, Lucile | |  | | , (2021). Assessing the impact of the loss function, architecture and image type for Deep Learning-based wildfire segmentation [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/39_CameraReady_39.pdf |
| 43 | Machine learning image classification for urban land use using GEOBIA, texture and landscape metrics Image Classification Extended Abstract Oral | Ruiz, Ivan E; Munoz, Jorge | |  | | Ruiz, I. E. et al., (2021). Machine learning image classification for urban land use using GEOBIA, texture and landscape metrics [Oral Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/43_CameraReady_43.pdf |
| 49 | Scalable Visual Attribute Extraction through Hidden Layers of a Residual ConvNet Image Classification Extended Abstract Poster | Baloian, Andrés ; Murrugarra-Llerena, Nils ; Saavedra, Jose M M | |  | | Baloian, A. et al., (2021). Scalable Visual Attribute Extraction through Hidden Layers of a Residual ConvNet [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/49_CameraReady_49.pdf |
| 51 | OSCAR and ActivityNet: an Image Captioning model can effectively learn a Video Captioning dataset Vision + Language Extended Abstract Poster | Byrd, Emmanuel; Gonzalez-Mendoza, Miguel | |  | | Byrd, E. et al., (2021). OSCAR and ActivityNet: an Image Captioning model can effectively learn a Video Captioning dataset [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai202106257 |
| 53 | Finding Significant Features for Few-Shot Learning using Dimensionality Reduction Techniques Image Classification Extended Abstract Poster | Mendez Ruiz, Mauricio; Ochoa-Ruiz, Gilberto; Garcia, Ivan; Méndez-Vázquez Andrés | |  | | Mendez Ruiz, M. et al., (2021). Finding Significant Features for Few-Shot Learning using Dimensionality Reduction Techniques [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai2021062513 |
| 55 | Pedestrian Intention Prediction with Multi-Input Concatenation Action Recognition Extended Abstract Poster | Singh, Ankur; Suddamalla, Upendra | |  | | Singh, A. et al., (2021). Pedestrian Intention Prediction with Multi-Input Concatenation [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai2021062514 |
| 58 | Absolute Scale Estimation Approach for Monocular Visual Odometry Pose Estimation Extended Abstract Poster | Díaz, Aldo A; Kurka, Paulo Kurka | |  | | Díaz, A. A. et al., (2021). Absolute Scale Estimation Approach for Monocular Visual Odometry [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai2021062515 |
| 59 | Relative scale estimation approach for monocular visual odometry Pose Estimation Extended Abstract Poster | Díaz, Aldo A Díaz; Kurka, Paulo Kurka | |  | | Díaz, A. A. et al., (2021). Relative scale estimation approach for monocular visual odometry [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://doi.org/10.52591/lxai2021062516 |
| 57 | Underwater Vision-Based Gesture Recognition: Robustness Validation for Safe Human-Robot Interaction Applications Extended Abstract Poster | Chavez, Arturo Gomez | | | | Gomez Chavez, A. et al., (2021). Underwater Vision-Based Gesture Recognition: Robustness Validation for Safe Human-Robot Interaction [Poster Presentation]. Computer Vision and Pattern Recognition Conference: LatinX in AI (LXAI) Research Workshop 2021, Virtual. https://research.latinxinai.org/papers/cvpr/2021/pdf/57_CameraReady_57.pdf |