Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
- Sonia Raychaudhuri, Saim Wani, Shivansh Patel, Unnat Jain, Angel X. Chang
- Computer ScienceConference on Empirical Methods in Natural…
- 30 September 2021
This work proposes a simple and effective language-aligned supervision scheme, and a new metric that measures the number of sub-instructions the agent has completed during navigation.
Motion Annotation Programs: A Scalable Approach to Annotating Kinematic Articulations in Large 3D Shape Collections
- Xianghao Xu, David Charatan, Daniel Ritchie
- Computer ScienceInternational Conference on 3D Vision
- 1 November 2020
This paper presents a system that helps individual expert users rapidly annotate kinematic motions in large 3D shape collections with simple, re-usable procedural rules that generate motion for a given input shape.
Retrospectives on the Embodied AI Workshop
A retrospective on the state of Embodied AI research is presented and 13 challenges presented at the EmbodiedAI Workshop at CVPR are grouped into three themes: visual navigation, rearrangement and integration.
Video Moment Localization using Object Evidence and Reverse Captioning
- Madhawa Vidanapathirana, Supriya Pandhre, Sonia Raychaudhuri, Anjali Khurana
- Computer ScienceArXiv
- 18 June 2020
This work proposes "Multi-faceted VideoMoment Localizer" (MML), an extension of MAC model by the introduction of visual object evidence via object segmentation masks and video understanding features via video captioning that outperforms MAC baseline and improves language modelling in sentence embedding.