352 citations · 568 across the 21 of their papers we have counts for
6 papers · 1 filter
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment
Ziyu Zhu, Xiaojian Ma, Yixin Chen +3
3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence. Cu…
Perceive, Ground, Reason, and Act: A Benchmark for General-purpose Visual Representation
Jiangyong Huang, William Yicheng Zhu, Baoxiong Jia +4
Current computer vision models, unlike the human visual system, cannot yet achieve general-purpose visual understanding. Existing efforts to create a general vision model are limit…
SQA3D: Situated Question Answering in 3D Scenes
Xiaojian Ma, Silong Yong, Zilong Zheng +4
We propose a new task to benchmark scene understanding of embodied agents: Situated Question Answering in 3D Scenes (SQA3D). Given a scene context (e.g., 3D scan), SQA3D requires t…
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
Huaizu Jiang, Xiaojian Ma, Weili Nie +4
A significant gap remains between today's visual pattern recognition models and human-level visual cognition especially when it comes to few-shot learning and compositional reasoni…
RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning
Xiaojian Ma, Weili Nie, Zhiding Yu +5
Reasoning about visual relationships is central to how humans interpret the visual world. This task remains challenging for current deep learning algorithms since it requires addre…
Unsupervised Foreground Extraction via Deep Region Competition
Peiyu Yu, Sirui Xie, Xiaojian Ma +3
We present Deep Region Competition (DRC), an algorithm designed to extract foreground objects from images in a fully unsupervised manner. Foreground extraction can be viewed as a s…