@other{https://authors.library.caltech.edu/records/47sqx-33w78,
    title = "A Foundation Model for Cell Segmentation",
    journal = "bioRvix",
    url = "https://authors.library.caltech.edu/records/47sqx-33w78",
    id = "record",
    issn = "2692-8205",
    doi = "10.1101/2023.11.17.567630",
    pmcid = "PMC10690226"
}


@other{https://authors.library.caltech.edu/records/ggr3q-q1d05,
    title = "Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection",
    url = "https://authors.library.caltech.edu/records/ggr3q-q1d05",
    id = "record",
    isbn = "979-8-3503-0718-4",
    doi = "10.1109/iccv51070.2023.01684"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20230316-204045919,
    title = "Multiview Compressive Coding for 3D Reconstruction",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20230316-204045919",
    id = "record"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204809456,
    title = "SynSin: End-to-end View Synthesis from a Single Image",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204809456",
    id = "record",
    doi = "10.48550/arXiv.1912.08804"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204749212,
    title = "Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204749212",
    id = "record",
    doi = "10.48550/arXiv.2207.10660"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204843170,
    title = "Mask R-CNN",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204843170",
    id = "record",
    doi = "10.48550/arXiv.1703.06870"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204846541,
    title = "Chained Predictions Using Convolutional Neural Networks",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204846541",
    id = "record",
    doi = "10.48550/arXiv.1605.02346"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204829682,
    title = "Detecting and Recognizing Human-Object Interactions",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204829682",
    id = "record"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204816196,
    title = "Embodied Question Answering in Photorealistic Environments with Point Cloud Perception",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204816196",
    id = "record",
    doi = "10.48550/arXiv.1904.03461"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204759329,
    title = "Recognizing Scenes from Novel Viewpoints",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204759329",
    id = "record",
    doi = "10.48550/arXiv.2112.01520"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204833051,
    title = "Embodied Question Answering",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204833051",
    id = "record",
    doi = "10.48550/arXiv.1711.11543"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-223825499,
    title = "Mesh R-CNN",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-223825499",
    id = "record",
    doi = "10.48550/arXiv.1906.02739"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204859995,
    title = "R-CNNs for Pose Estimation and Action Detection",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204859995",
    id = "record",
    doi = "10.48550/arXiv.1406.5212"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204853268,
    title = "Actions and Attributes from Wholes and Parts",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204853268",
    id = "record",
    doi = "10.48550/arXiv.1412.2604"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204802712,
    title = "Accelerating 3D Deep Learning with PyTorch3D",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204802712",
    id = "record",
    doi = "10.48550/arXiv.2007.08501"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204755957,
    title = "Differentiable Stereopsis: Meshes from multiple views using differentiable rendering",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204755957",
    id = "record",
    doi = "10.48550/arXiv.2110.05472"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204752587,
    title = "Learning 3D Object Shape and Layout without 3D Supervision",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204752587",
    id = "record",
    doi = "10.48550/arXiv.2206.07028"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204856628,
    title = "Finding Action Tubes",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204856628",
    id = "record",
    doi = "10.48550/arXiv.1411.6031"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204826312,
    title = "Building Generalizable Agents with a Realistic and Rich 3D Environment",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204826312",
    id = "record",
    doi = "10.48550/arXiv.1801.02209"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204745839,
    title = "BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204745839",
    id = "record",
    doi = "10.48550/arXiv.2212.07401"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204849905,
    title = "Contextual Action Recognition with R*CNN",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204849905",
    id = "record",
    doi = "10.48550/arXiv.1505.01197"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204806086,
    title = "3D Shape Reconstruction from Vision and Touch",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204806086",
    id = "record",
    doi = "10.48550/arXiv.2007.03778"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204839800,
    title = "Data Distillation: Towards Omni-Supervised Learning",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204839800",
    id = "record",
    doi = "10.48550/arXiv.1712.04440"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204822934,
    title = "Neural Modular Control for Embodied Question Answering",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204822934",
    id = "record",
    doi = "10.48550/arXiv.1810.11181"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204819572,
    title = "Multi-Target Embodied Question Answering",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204819572",
    id = "record",
    doi = "10.48550/arXiv.1904.04686"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204836433,
    title = "Detect-and-Track: Efficient Pose Estimation in Videos",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204836433",
    id = "record",
    doi = "10.48550/arXiv.1712.09184"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-215117759,
    title = "Building Generalizable Agents with a Realistic and Rich 3D Environment",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-215117759",
    id = "record"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789792000.24,
    title = "2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
    chapter = "Differentiable Stereopsis: Meshes from multiple views using differentiable rendering",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789792000.24",
    id = "record",
    isbn = "978-1-6654-6946-3",
    doi = "10.1109/cvpr52688.2022.00844"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789795000.26,
    title = "2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
    chapter = "Learning 3D Object Shape and Layout without 3D Supervision",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789795000.26",
    id = "record",
    isbn = "978-1-6654-6946-3",
    doi = "10.1109/cvpr52688.2022.00174"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221219-224850812,
    title = "Advances in Neural Information Processing Systems 33 (NeurIPS 2020)",
    chapter = "3D Shape Reconstruction from Vision and Touch",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-224850812",
    id = "record",
    isbn = "9781713829546"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789782000.20,
    title = "2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
    chapter = "SynSin: End-to-End View Synthesis From a Single Image",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789782000.20",
    id = "record",
    isbn = "978-1-7281-7168-5",
    doi = "10.1109/cvpr42600.2020.00749"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789777000.18,
    title = "2019 IEEE/CVF International Conference on Computer Vision (ICCV)",
    chapter = "Mesh R-CNN",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789777000.18",
    id = "record",
    isbn = "978-1-7281-4803-8",
    doi = "10.1109/iccv.2019.00988"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789767000.16,
    title = "2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
    chapter = "Multi-Target Embodied Question Answering",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789767000.16",
    id = "record",
    isbn = "978-1-7281-3293-8",
    doi = "10.1109/cvpr.2019.00647"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789772000.17,
    title = "2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
    chapter = "Embodied Question Answering in Photorealistic Environments With Point Cloud Perception",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789772000.17",
    id = "record",
    isbn = "978-1-7281-3293-8",
    doi = "10.1109/cvpr.2019.00682"
}


@article{https://resolver.caltech.edu/CaltechAUTHORS:20221219-204809634,
    title = "Neural Modular Control for Embodied Question Answering",
    journal = "Proceedings of Machine Learning Research",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-204809634",
    id = "record",
    issn = "2640-3498",
    volume = "87"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789751000.12,
    title = "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition",
    chapter = "Data Distillation: Towards Omni-Supervised Learning",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789751000.12",
    id = "record",
    isbn = "978-1-5386-6420-9",
    doi = "10.1109/cvpr.2018.00433"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789753000.13,
    title = "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition",
    chapter = "Detect-and-Track: Efficient Pose Estimation in Videos",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789753000.13",
    id = "record",
    isbn = "978-1-5386-6420-9",
    doi = "10.1109/cvpr.2018.00044"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789762000.15,
    title = "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition",
    chapter = "Detecting and Recognizing Human-Object Interactions",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789762000.15",
    id = "record",
    isbn = "978-1-5386-6420-9",
    doi = "10.1109/cvpr.2018.00872"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789757000.14,
    title = "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition",
    chapter = "Embodied Question Answering",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789757000.14",
    id = "record",
    isbn = "978-1-5386-6420-9",
    doi = "10.1109/cvpr.2018.00008"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789744000.10,
    title = "2017 IEEE International Conference on Computer Vision (ICCV)",
    chapter = "Mask R-CNN",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789744000.10",
    id = "record",
    isbn = "978-1-5386-1032-9",
    doi = "10.1109/iccv.2017.322"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789739000.9,
    title = "2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
    chapter = "Learn2Smile: Learning non-verbal interaction through observation",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789739000.9",
    id = "record",
    isbn = "978-1-5386-2682-5",
    doi = "10.1109/iros.2017.8206272"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789734000.8,
    title = "Computer Vision – ECCV 2016",
    chapter = "Chained Predictions Using Convolutional Neural Networks",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789734000.8",
    id = "record",
    isbn = "9783319464923",
    doi = "10.1007/978-3-319-46493-0\_44"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789729000.6,
    title = "2015 IEEE International Conference on Computer Vision (ICCV)",
    chapter = "Contextual Action Recognition with R*CNN",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789729000.6",
    id = "record",
    isbn = "978-1-4673-8391-2",
    doi = "10.1109/iccv.2015.129"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789725000.5,
    title = "2015 IEEE International Conference on Computer Vision (ICCV)",
    chapter = "Actions and Attributes from Wholes and Parts",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789725000.5",
    id = "record",
    isbn = "978-1-4673-8391-2",
    doi = "10.1109/iccv.2015.284"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789721000.4,
    title = "2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
    chapter = "Finding action tubes",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789721000.4",
    id = "record",
    isbn = "978-1-4673-6964-0",
    doi = "10.1109/cvpr.2015.7298676"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789716000.3,
    title = "2014 IEEE Conference on Computer Vision and Pattern Recognition",
    chapter = "Using k-Poselets for Detecting People and Localizing Their Keypoints",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789716000.3",
    id = "record",
    isbn = "978-1-4799-5118-5",
    doi = "10.1109/cvpr.2014.458"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20221215-789688000.2,
    title = "2013 IEEE Conference on Computer Vision and Pattern Recognition",
    chapter = "Articulated Pose Estimation Using Discriminative Armlet Classifiers",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221215-789688000.2",
    id = "record",
    isbn = "978-1-5386-5672-3",
    doi = "10.1109/cvpr.2013.429"
}