HAMMR: HierArchical MultiModal React agents for generic VQA.

Lluís Castrejón

Lluís Castrejón Thomas Mensink Howard Zhou Vittorio Ferrari André Araújo 0001 Jasper R. R. Uijlings HAMMR: HierArchical MultiModal React agents for generic VQA. 2024 abs/2404.05465 CoRR https://doi.org/10.48550/arXiv.2404.05465 db/journals/corr/corr2404.html#abs-2404-05465

Lisa Alazraki Lluís Castrejón Mostafa Dehghani 0001 Fantine Huot Jasper R. R. Uijlings Thomas Mensink How (not) to ensemble LVLMs for VQA. 1-20 2023 ICBINB https://proceedings.mlr.press/v239/alazraki23a.html conf/icbinb/2023 db/conf/icbinb/icbinb2023.html#AlazrakiCDHUM23 Thomas Mensink Jasper R. R. Uijlings Lluís Castrejón Arushi Goel Felipe Cadar Howard Zhou Fei Sha André Araújo 0001 Vittorio Ferrari Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories. 3090-3101 2023 ICCV https://doi.org/10.1109/ICCV51070.2023.00289 conf/iccv/2023 db/conf/iccv/iccv2023.html#MensinkUCGCZSAF23

Thomas Mensink Jasper R. R. Uijlings Lluís Castrejón Arushi Goel Felipe Cadar Howard Zhou Fei Sha André Araújo 0001 Vittorio Ferrari Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories. 2023 abs/2306.09224 CoRR https://doi.org/10.48550/arXiv.2306.09224 db/journals/corr/corr2306.html#abs-2306-09224

Lisa Alazraki Lluís Castrejón Mostafa Dehghani 0001 Fantine Huot Jasper R. R. Uijlings Thomas Mensink How (not) to ensemble LVLMs for VQA. 2023 abs/2310.06641 CoRR https://doi.org/10.48550/arXiv.2310.06641 db/journals/corr/corr2310.html#abs-2310-06641

Rim Assouel Lluís Castrejón Aaron C. Courville Nicolas Ballas Yoshua Bengio VIM: Variational Independent Modules for Video Prediction. 70-89 2022 CLeaR https://proceedings.mlr.press/v177/assouel22a.html conf/clear2/2022 db/conf/clear2/clear2022.html#AssouelCCBB22 Lluís Castrejón Nicolas Ballas Aaron C. Courville Cascaded Video Generation for Videos In-the-Wild. 2385-2392 2022 ICPR https://doi.org/10.1109/ICPR56361.2022.9956228 conf/icpr/2022 db/conf/icpr/icpr2022.html#CastrejonBC22

Lluís Castrejón Nicolas Ballas Aaron C. Courville Cascaded Video Generation for Videos In-the-Wild. 2022 abs/2206.00735 CoRR https://doi.org/10.48550/arXiv.2206.00735 db/journals/corr/corr2206.html#abs-2206-00735

Lluís Castrejón Nicolas Ballas Aaron C. Courville Hierarchical Video Generation for Complex Data. 2021 abs/2106.02719 CoRR https://arxiv.org/abs/2106.02719 db/journals/corr/corr2106.html#abs-2106-02719

Mahmoud Assran Nicolas Ballas Lluís Castrejón Michael G. Rabbat Recovering Petaflops in Contrastive Semi-Supervised Learning of Visual Representations. 2020 abs/2006.10803 CoRR https://arxiv.org/abs/2006.10803 db/journals/corr/corr2006.html#abs-2006-10803

Lluís Castrejón Nicolas Ballas Aaron C. Courville Improved Conditional VRNNs for Video Prediction. 7607-7616 2019 ICCV https://doi.org/10.1109/ICCV.2019.00770 conf/iccv/2019 db/conf/iccv/iccv2019.html#CastrejonBC19

Lluís Castrejón Nicolas Ballas Aaron C. Courville Improved Conditional VRNNs for Video Prediction. 2019 abs/1904.12165 CoRR http://arxiv.org/abs/1904.12165 db/journals/corr/corr1904.html#abs-1904-12165

Yusuf Aytar Lluís Castrejón Carl Vondrick Hamed Pirsiavash Antonio Torralba 0001 Cross-Modal Scene Networks. 2303-2314 2018 40 IEEE Trans. Pattern Anal. Mach. Intell. 10 https://doi.org/10.1109/TPAMI.2017.2753232 http://doi.ieeecomputersociety.org/10.1109/TPAMI.2017.2753232 https://www.wikidata.org/entity/Q50044177 db/journals/pami/pami40.html#AytarCVP018

Paul Vicol Makarand Tapaswi Lluís Castrejón Sanja Fidler MovieGraphs: Towards Understanding Human-Centric Situations From Videos. 8581-8590 2018 CVPR http://openaccess.thecvf.com/content_cvpr_2018/html/Vicol_MovieGraphs_Towards_Understanding_CVPR_2018_paper.html https://doi.org/10.1109/CVPR.2018.00895 https://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00895 conf/cvpr/2018 db/conf/cvpr/cvpr2018.html#VicolTCF18 Lluís Castrejón Kaustav Kundu Raquel Urtasun Sanja Fidler Annotating Object Instances with a Polygon-RNN. 4485-4493 2017 CVPR https://doi.org/10.1109/CVPR.2017.477 https://doi.ieeecomputersociety.org/10.1109/CVPR.2017.477 conf/cvpr/2017 db/conf/cvpr/cvpr2017.html#CastrejonKUF17

Lluís Castrejón Kaustav Kundu Raquel Urtasun Sanja Fidler Annotating Object Instances with a Polygon-RNN. 2017 abs/1704.05548 CoRR http://arxiv.org/abs/1704.05548 db/journals/corr/corr1704.html#CastrejonKUF17

Paul Vicol Makarand Tapaswi Lluís Castrejón Sanja Fidler MovieGraphs: Towards Understanding Human-Centric Situations from Videos. 2017 abs/1712.06761 CoRR http://arxiv.org/abs/1712.06761 db/journals/corr/corr1712.html#abs-1712-06761

Lluís Castrejón Yusuf Aytar Carl Vondrick Hamed Pirsiavash Antonio Torralba 0001 Learning Aligned Cross-Modal Representations from Weakly Aligned Data. 2940-2949 2016 CVPR https://doi.org/10.1109/CVPR.2016.321 https://doi.ieeecomputersociety.org/10.1109/CVPR.2016.321 conf/cvpr/2016 db/conf/cvpr/cvpr2016.html#CastrejonAVPT16

Lluís Castrejón Yusuf Aytar Carl Vondrick Hamed Pirsiavash Antonio Torralba 0001 Learning Aligned Cross-Modal Representations from Weakly Aligned Data. 2016 abs/1607.07295 CoRR http://arxiv.org/abs/1607.07295 db/journals/corr/corr1607.html#CastrejonAVPT16

Yusuf Aytar Lluís Castrejón Carl Vondrick Hamed Pirsiavash Antonio Torralba 0001 Cross-Modal Scene Networks. 2016 abs/1610.09003 CoRR http://arxiv.org/abs/1610.09003 db/journals/corr/corr1610.html#AytarCVPT16

Lisa Alazraki André Araújo 0001 Rim Assouel Mido AssranMahmoud Assran Yusuf Aytar Nicolas Ballas Yoshua Bengio Felipe C. ChamoneFelipe Cadar Aaron C. Courville Mostafa Dehghani 0001 Vittorio Ferrari Sanja Fidler Arushi Goel Fantine Huot Kaustav Kundu Thomas Mensink Hamed Pirsiavash Michael G. Rabbat Fei Sha Makarand Tapaswi Antonio Torralba 0001 Jasper R. R. Uijlings Raquel Urtasun Paul Vicol Carl Vondrick Howard Zhou