arXiv:2204.04347
On the Importance of Karaka Framework in Multi-modal Grounding
원문 초록
Computational Paninian Grammar model helps in decoding a natural language expression as a series of modifier-modified relations and therefore facilitates in identifying dependency relations closer to language (context) semantics compared to the usual Stanford dependency relations. However, the importance of this CPG dependency scheme has not been studied in the context of multi-modal vision and language applications. At IIIT Hyderabad, we plan to perform a novel study to explore the potential advantages and disadvantages of CPG framework in a vision-language navigation task setting, a popular and challenging multi-modal grounding task.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation
Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation
doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language Navigation
DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control
Correctable Landmark Discovery via Large Models for Vision-Language Navigation
Open-Set 3D Semantic Instance Maps for Vision Language Navigation -- O3D-SIM
토론
이 논문과 연결된 포럼 글이 아직 없습니다.