datasets

@inproceedings{ArtemisECCV2024,
  author = {Panagopoulou, Artemis and Xue, Le and Yu, Ning and Li, Junnan and Li, Dongxu and Joty, Shafiq and Xu, Ran and Savarese, Silvio and Xiong, Caiming and Niebles, Juan Carlos},
  title = {{X-InstructBLIP}: A Framework for Aligning Image, 3D, Audio, Video to {LLM}s and its Emergent Cross-modal Reasoning},
  booktitle = {European Conference on Computer Vision (ECCV)},
  address = {Milan, Italy},
  month = oct,
  year = {2024},
}

@inproceedings{YuECCV2024,
  author = {Yu, Ning and Chen, Chia-Chih and Chen, Zeyuan and Meng, Rui and Wu, Gang and Josel, Paul and Niebles, Juan Carlos and Xiong, Caiming and Xu, Ran},
  title = {{LayoutDETR}: Detection Transformer Is a Good Multimodal Layout Designer},
  booktitle = {European Conference on Computer Vision (ECCV)},
  address = {Milan, Italy},
  month = oct,
  year = {2024},
}

@inproceedings{Xue_CVPR_2024,
  author = {Xue, Le and Yu, Ning and Zhang, Shu and Panagopoulou, Artemis and Li, Junnan and Martín-Martín, Roberto and Wu, Jiajun and Xiong, Caiming and Xu, Ran and Niebles, Juan Carlos and Savarese, Silvio},
  title = {{ULIP-2}: Towards Scalable Multimodal Pre-training for {3D} Understanding},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  address = {Seattle, Washington},
  month = jun,
  year = {2024},
}

@inproceedings{Xue_CVPR_2023,
  author = {Xue, Le and Gao, Mingfei and Xing, Chen and Martín-Martín, Roberto and Wu, Jiajun and Xiong, Caiming and Xu, Ran and Niebles, Juan Carlos and Savarese, Silvio},
  title = {{ULIP}: Learning Unified Representation of Language, Image and Point Cloud for 3D Understanding},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  address = {Vancouver, Canada},
  month = jun,
  year = {2023},
  doi = {10.1109/CVPR52729.2023.00120}
}

@inproceedings{Luo_NeurIPS_2022,
  author = {Luo, Zelun and Durante, Zane and Li, Linden and Xie, Wanze and Liu, Ruochen and Jin, Emily and Huang, Zhuoyi and Li, Lun Yu and Wu, Jiajun and Niebles, Juan Carlos and Adeli, Ehsan and Fei-Fei, Li},
  title = {{MOMA-LRG}: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},
  address = {New Orleans, USA},
  month = dec,
  year = {2022},
}

@inproceedings{Ji_CVPR_2020,
  author = {Ji, Jingwei and Krishna, Ranjay and Fei-Fei, Li and Niebles, Juan Carlos},
  title = {Action Genome: Actions as Compositions of Spatio-temporal Scene Graphs},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  address = {Seattle, Washington, USA},
  month = jun,
  year = {2020},
  doi = {10.1109/CVPR42600.2020.01025}
}

@inproceedings{Cao_CVPR_2020,
  author = {Cao, Kaidi and Ji, Jingwei and Cao, Zhangjie and Chang, Chien-Yi and Niebles, Juan Carlos},
  title = {Few-Shot Video Classification via Temporal Alignment},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  address = {Seattle, Washington, USA},
  month = jun,
  year = {2020},
  doi = {10.1109/CVPR42600.2020.01063},
}

@article{Liu_RAL_2020,
  author = {Liu, Bingbin and Adeli, Ehsan and Cao, Zhangjie and Lee, Kuan-Hui and Shenoi, Abhijeet and Gaidon, Adrien and Niebles, Juan Carlos},
  title = {Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction},
  journal = {IEEE Robotics and Automation Letters (RA-L) and IEEE International Conference on Robotics and Automation (ICRA)},
  volume = {5},
  number = {2},
  address = {Paris, France},
  month = may,
  year = {2020},
  doi = {10.1109/LRA.2020.2976305},
}

@inproceedings{Zang_EMNLP_2018,
  author = {Zang, Xiaoxue and Pokle, Ashwini and Vázquez, Marynel and Chen, Kevin and Niebles, Juan Carlos and Soto, Alvaro and Savarese, Silvio},
  title = {Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation},
  booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  address = {Brussels, Belgium},
  month = nov,
  year = {2018},
  doi = {10.18653/v1/D18-1286}
}

@inproceedings{Krishna_ICCV_2017,
  author = {Krishna, Ranjay and Hata, Kenji and Ren, Frederic and Fei-Fei, Li and Niebles, Juan Carlos},
  title = {Dense-Captioning Events in Videos},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  address = {Venice, Italy},
  month = oct,
  year = {2017},
  doi = {10.1109/ICCV.2017.83},
}

@inproceedings{Zeng_CVPR_2017,
  author = {Zeng, Kuo-Hao and Chou, Shih-Han and Chan, Fu-Hsiang and Niebles, Juan Carlos and Sun, Min},
  title = {Agent-centric Risk Assessment: Accident Anticipation and Risky Region Localization},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  address = {Honolulu, Hawaii, USA},
  month = jun,
  year = {2017},
  doi = {10.1109/CVPR.2017.146},
}

@article{Lillo_IVC_2017,
  author = {Lillo, Ivan and Niebles, Juan Carlos and Soto, Alvaro},
  journal = {Image and Vision Computing},
  volume = {59},
  month = mar,
  year = {2017},
  doi = {10.1016/j.imavis.2016.11.004},
}

@inproceedings{Zeng_AAAI_2017,
  author = {Zeng, Kuo-Hao and Chen, Tseng-Hung and Chuang, Ching-Yao and Liao, Yuan-Hong and Sun, Juan Carlos Niebles and Min},
  title = {Leveraging Video Descriptions to Learn Video Question Answering},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  address = {San Francisco, USA},
  month = feb,
  year = {2017},
  doi = {10.1609/aaai.v31i1.11238}
}

@inproceedings{Zeng_ECCV_2016,
  author = {Zeng, Kuo-Hao and Chen, Tseng-Hung and Niebles, Juan Carlos and Sun, Min},
  title = {Title Generation for User Generated Videos},
  booktitle = {European Conference on Computer Vision (ECCV)},
  address = {Amsterdam, Netherlands},
  month = oct,
  year = {2016},
  doi = {10.1007/978-3-319-46475-6_38},
}

@inproceedings{Lillo_CVPR_2016,
  author = {Lillo, Ivan and Niebles, Juan Carlos and Soto, Alvaro},
  title = {A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  address = {Las Vegas, USA},
  month = jun,
  year = {2016},
  doi = {10.1109/CVPR.2016.218},
}

@inproceedings{Caba_CVPR_2015,
  author = {Caba Heilbron, Fabian and Escorcia, Victor and Ghanem, Bernard and Niebles, Juan Carlos},
  title = {{ActivityNet}: A Large-Scale Video Benchmark for Human Activity Understanding},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  address = {Boston, USA},
  month = jun,
  year = {2015},
  doi = {10.1109/CVPR.2015.7298698},
}

@inproceedings{Lillo_CVPR_2014,
  author = {Lillo, Ivan and Soto, Alvaro and Niebles, Juan Carlos},
  title = {Discriminative Hierarchical Modeling of Spatio-Temporally Composable Human Activities},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  address = {Colombus, USA},
  month = jun,
  year = {2014},
  doi = {10.1109/CVPR.2014.109},
}

@inproceedings{Niebles_ECCV_2010,
  author = {Niebles, Juan Carlos and Chen, Chih-Wei and Fei-Fei, Li},
  title = {Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification},
  booktitle = {European Conference on Computer Vision (ECCV)},
  address = {Hersonissos, Crete, Greece},
  month = sep,
  year = {2010},
  doi = {10.1007/978-3-642-15552-9_29},
}

@inproceedings{Niebles_ECCV_2008,
  author = {Niebles, Juan Carlos and Han, Bohyung and Ferencz, Andras and Fei-Fei, Li},
  title = {Extracting Moving People from Internet Videos},
  booktitle = {European Conference on Computer Vision (ECCV)},
  address = {Marseilles, France},
  month = oct,
  year = {2008},
  doi = {10.1007/978-3-540-88693-8_39},
}