Accepted Papers
Full Papers
Paper ID | Paper Title | Author Names | | Poster | Pitch | Citation |
|---|---|---|---|---|---|---|
| 4 | An End-to-End Approach for Handwriting Recognition: From Handwritten Text Lines to Complete Manuscripts Representation Learning Vision applications and systems Poster | Dayvid Castro; Cleber Zanchettin; Byron L D Bezerra |  |  |  | Castro, D. et al., (2024). An End-to-End Approach for Handwriting Recognition: From Handwritten Text Lines to Complete Manuscripts [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Dayvid_Castro.pdf |
| 19 | ST-Gait++: Leveraging spatio-temporal convolutions for gait-based emotion recognition on videos Video: Action and event understanding Biometrics Poster | Maria Luisa Lima; Willams Costa; Estefania Talavera; Veronica Teichrieb | | | | Costa, W. et al., (2024). ST-Gait++: Leveraging spatio-temporal convolutions for gait-based emotion recognition on videos [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Willams_Costa.pdf |
| 21 | High-Resolution Detection of Earth Structural Heterogeneities from Seismic Amplitudes using Convolutional Neural Networks with Attention layers Transfer/ low-shot/ continual/ long-tail learning Vision applications and systems Poster | Luiz Schirmer; Guilherme G Schardong; Vinícius D da Silva; Hélio Lopes; Rogerio de Araujo Santos | | | | Schirmer, L. et al., (2024). High-Resolution Detection of Earth Structural Heterogeneities from Seismic Amplitudes using Convolutional Neural Networks with Attention layers [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Luiz_Schirmer.pdf |
| 23 | The Myth of the Pyramid Transfer/ low-shot/ continual/ long-tail learning Vision applications and systems Poster | Ramon Izquierdo Cordova; Walterio Mayol-Cuevas | | | | Izquierdo Cordova, R. et al., (2024). The Myth of the Pyramid [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Ramon_Izquierdo-Cordova.pdf |
| 24 | Beyond Appearances: Material Segmentation with Embedded Spectral Information from RGB-D imagery Image and video synthesis and generation Scene analysis and understanding Poster | Fabian Perez; Hoover Rueda-Chacón | | | | Perez, F. et al., (2024). Beyond Appearances: Material Segmentation with Embedded Spectral Information from RGB-D imagery [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Fabian_Perez.pdf |
Extended Abstracts
Paper ID | Paper Title | Author Names | | Poster | Citation |
|---|---|---|---|---|---|
| 27 | Attention Modules Improve Efficient Anomaly Localization for Industrial Inspection in the Wild Transfer/ low-shot/ continual/ long-tail learning Datasets and evaluation Poster | André Luiz B Vieira e Silva; Felipe M Battisti; Veronica Teichrieb; Francisco Paulo Magalhães Simões | | | Vieira e Silva, A. L. B. et al., (2024). Attention Modules Improve Efficient Anomaly Localization for Industrial Inspection in the Wild [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Andre_Vieira.pdf |
| 30 | DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling 3D from single images Representation learning Poster | Miguel Fainstein; Viviana Siless; Emmanuel Iarussi | | | Fainstein, M. et al., (2024). DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Miguel_Fainstein.pdf |
| 41 | Enhancing Continual Learning in Diabetic Retinopathy: Multimodal Zero-shot Clustering and Strategic Experience Replay Machine Learning Medical and biological vision, cell microscopy Poster | Gusseppe Bravo-Rocca; Peini Liu; Jordi Guitart; Ajay Dholakia; David D Ellison; Rodrigo M Carrillo-Larco | | | Bravo-Rocca, G. et al., (2024). Enhancing Continual Learning in Diabetic Retinopathy: Multimodal Zero-shot Clustering and Strategic Experience Replay [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Gusseppe_Bravo-Rocca.pdf |
| 43 | RetryTRACK: Recovering Misses in Multi-camera Pedestrian Tracking 3D from multi-view and sensors Video: Action and event understanding Poster | Isabella F de Andrade; Joao Lima; Veronica Teichrieb | | | de Andrade, I. F. et al., (2024). RetryTRACK: Recovering Misses in Multi-camera Pedestrian Tracking [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Isabella_deAndrade.pdf |
| 46 | Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning Image and video synthesis and generation Representation learning Poster | Rafael T Elberg; Denis Parra; Mircea Petrache | | | Elberg, R. T. et al., (2024). Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Rafael_Elberg.pdf |
| 55 | On the Robustness of Large Multimodal Models Against Image Adversarial Attacks Adversarial attack and defense Vision, language, and reasoning Poster | Alejandro Aparcedo | | | Aparcedo, A., (2024). On the Robustness of Large Multimodal Models Against Image Adversarial Attacks [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Alejandro_Aparcedo.pdf |
| 56 | Triplanar CNN Approach for Hippocampus Segmentation and Depression Classification Vision applications and systems Datasets and evaluation Poster | Andrea C Salazar Zozaya; Jose A. Cantoral-Ceballos; Ricardo Caraza | | | Salazar Zozaya, A. C. et al., (2024). Triplanar CNN Approach for Hippocampus Segmentation and Depression Classification [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Andrea_Salazar.pdf |
| 63 | Convolutional neural network architectures and aggregation information models for pulmonary X-ray segmentation Representation learning Medical and biological vision, cell microscopy Poster | Antonio Nadal-Martinez; Lidia Talavera-Martínez; Marc Munar; Manuel González-Hidalgo | | | Talavera-Martínez, L. et al., (2024). Convolutional neural network architectures and aggregation information models for pulmonary X-ray segmentation [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Lidia_TalaveraMartinez.pdf |
| 65 | MaSA-UNet: Manhattan Self-Attention UNet with Weighted Composed Loss for Skin Lesion Segmentation Medical and biological vision, cell microscopy Machine learning Poster | Abel A Reyes-Angulo; Sidike Paheding | | | Reyes-Angulo, A. A. et al., (2024). MaSA-UNet: Manhattan Self-Attention UNet with Weighted Composed Loss for Skin Lesion Segmentation [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Abel_Reyes-Angulo.pdf |
| 68 | VWise: A novel benchmark for evaluating scene classification for vehicular applications Datasets and evaluation Vision applications and systems Poster | Pedro A Oliveira; Emanuella Freitas; Gabriel Coelho; Willams Costa; João Teixeira; Valter Ferreira; Roberto Jones; Veronica Teichrieb | | | Costa, W. et al., (2024). VWise: A novel benchmark for evaluating scene classification for vehicular applications [Poster Presentation]. International Conference on Computer Vision: LatinX in AI (LXAI) Research Workshop 2024, Seattle WA, USA. https://research.latinxinai.org/papers/cvpr/2024/pdf/Willams_Costa.pdf |