3D Visual Question Answering (VQA)

3D Visual Question Answering (VQA) is a benchmark that evaluates the ability of models to understand and reason about 3D scenes by answering questions based on visual inputs, typically involving spatial and contextual information.

Papers using 3D Visual Question Answering (VQA) (6)

Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding2026Do Large Vision-language Models Distinguish Between The Actual And Apparent Features Of Illusions?2025CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks2022 · 19 citesLarge Language Models are Visual Reasoning Coordinators2023 · 14 citesMultimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks2022 · 8 citesCAVL: Learning Contrastive and Adaptive Representations of Vision and Language2023 · 1 cites