Angel Chang
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2019
Angel Chang is a Canada CIFAR AI Chair with Amii, an assistant professor at Simon Fraser University, and a recipient of the Hans Fischer Fellowship from the Technical University of Munich Institute for Advanced Study. She is also a faculty member of the GrUVi Lab and Nat Lang Lab at Simon Fraser University.
Chang works at the intersection of language and vision to create computer models with knowledge and understanding of the world. Her research connects language to 3D representations of shapes, scenes, and ground language for embodied agents in indoor environments. Through her collaborative research, Chang has developed methods for generating coloured 3D shapes from natural language and for turning input text into computer-generated scenes that can then be further refined through textual interaction by the user.
Awards
- SGP 2018 and SGP 2020 Dataset Awards from the Symposium on Geometry Processing for her work on the ShapeNet and ScanNet datasets.
Relevant Publications
- Zhang, Y. Gong, Z., Chang, A.X. (2023). Multi3drefer: Grounding text description to multiple 3d objects. Proceedings of the IEEE/CVF International Conference on Computer Vision. (pp. 15225-15236)
- Zhenyu Chen, D., Wu, Q., Nießner, M.. Chang, A. X. (2022). D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding. European Conference on Computer Vision (pp. 487-505).
- Mao, Y., Zhang, Y., Jiang, H., Chang, A. X., Savva, M. (2022). MultiScan: Scalable RGBD scanning for 3D environments with articulated objects. Advances in Neural Information Processing Systems 35 (pp. 9058-9071).
Szot, A., Clegg, A., Undersander, E., Wijmans, E., Zhao, Y., Turner, J., … & Batra, D. (2021). Habitat 2.0: Training Home Assistants to Rearrange their Habitat.
Chen, Z., Gholami, A., Nießner, M., & Chang, A. X. (2021). Scan2Cap: Context-aware Dense Captioning in RGB-D Scans. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3193-3203).