| Mad: A scalable dataset for language grounding in videos from movie audio descriptions M Soldan, A Pardo, JL Alcázar, F Caba, C Zhao, S Giancola, B Ghanem Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 109 | 2022 |
| Active speakers in context JL Alcázar, F Caba, L Mai, F Perazzi, JY Lee, P Arbeláez, B Ghanem Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2020 | 98 | 2020 |
| Maas: Multi-modal assignation for active speaker detection JL Alcázar, F Caba, AK Thabet, B Ghanem Proceedings of the IEEE/CVF International Conference on Computer Vision, 265-274, 2021 | 61 | 2021 |
| Pivot: Prompting for video continual learning A Villa, JL Alcázar, M Alfarra, K Alhamoud, J Hurtado, FC Heilbron, A Soto, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 51 | 2023 |
| Multi-view dynamic facial action unit detection A Romero, J León, P Arbeláez Image and Vision Computing 122, 103723, 2022 | 43 | 2022 |
| vclimb: A novel video class incremental learning benchmark A Villa, K Alhamoud, V Escorcia, F Caba, JL Alcázar, B Ghanem Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 41 | 2022 |
| End-to-end active speaker detection JL Alcazar, M Cordes, C Zhao, B Ghanem European Conference on Computer Vision, 126-143, 2022 | 32 | 2022 |
| Moviecuts: A new dataset and benchmark for cut type recognition A Pardo, FC Heilbron, JL Alcázar, A Thabet, B Ghanem European Conference on Computer Vision, 668-685, 2022 | 31 | 2022 |
| Learning to cut by watching movies A Pardo, F Caba, JL Alcázar, AK Thabet, B Ghanem Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 26 | 2021 |
| Behind the magic, merlim: Multi-modal evaluation benchmark for large image-language models A Villa, JCL Alcázar, A Soto, B Ghanem arXiv preprint arXiv:2312.02219, 2023 | 10 | 2023 |
| Just a glimpse: Rethinking temporal information for video continual learning L Alssum, JL Alcazar, M Ramazanova, C Zhao, B Ghanem Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 7 | 2023 |
| APES: Audiovisual person search in untrimmed video JL Alcazar, F Caba, L Mai, F Perazzi, JY Lee, P Arbelaez, B Ghanem Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021 | 6 | 2021 |
| Learning to read analog gauges from synthetic data J Leon-Alcazar, Y Alnumay, C Zheng, H Trigui, S Patel, B Ghanem Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024 | 4 | 2024 |
| MAIN: Multi-Attention Instance Network for Video Segmentation JL Alcazar, MA Bravo, AK Thabet, G Jeanneret, T Brox, P Arbelaez, ... arXiv preprint arXiv:1904.05847, 2019 | 4 | 2019 |
| Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration JC Pérez, A Pardo, M Soldan, H Itani, J Leon-Alcazar, B Ghanem arXiv preprint arXiv:2405.17146, 2024 | 2 | 2024 |
| Usability evaluation of a mobile tool to support prenatal examination JC Leon, A Aponte, S Vega, E Romero IX International Seminar On Medical Information Processing And Analysis 8922 …, 2013 | 2 | 2013 |
| Markerless Analysis of Gait Patterns in the Parkinson's Disease L Alcázar, J Carlos Universidad Nacional de Colombia, 2012 | 2 | 2012 |
| Universidad de los Andes at ActivityNet Challenge 2020-Task B Active Speaker Detection (AVA) JL Alcázar, P Arbeláez The ActivityNet Large-Scale Activity Recognition Challenge 2020, 4, 2020 | 1 | 2020 |
| EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models A Villa, JL Alcázar, M Alfarra, V Araujo, A Soto, B Ghanem arXiv preprint arXiv:2501.02699, 2025 | | 2025 |
| fuankarion/automatic-gauge-reading J Leon-Alcazar, Y Alnumay, C Zheng, HA Trigui, S Patel, B Ghanem Github, 2023 | | 2023 |
Bernard GhanemProfessor, King Abdullah University of Science and TechnologyPatvirtintas el. paštas kaust.edu.sa