5 papers · 1 filter
VGLD: Visually-Guided Linguistic Disambiguation for Monocular Depth Scale Recovery
Bojin Wu, Jing Chen
Monocular depth estimation can be broadly categorized into two directions: relative depth estimation, which predicts normalized or inverse depth without absolute scale, and metric…
R^3-VQA: "Read the Room" by Video Social Reasoning
Lixing Niu, Jiapeng Li, Xingping Yu +6
"Read the room" is a significant social reasoning capability in human daily life. Humans can infer others' mental states from subtle social cues. Previous social reasoning tasks an…
SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
Hao Du, Bo Wu, Yan Lu +1
Vision-language temporal alignment is a crucial capability for human dynamic recognition and cognition in real-world scenarios. While existing research focuses on capturing vision-…
Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
Granite Vision Team, Leonid Karlinsky, Assaf Arbelle +60
We introduce Granite Vision, a lightweight large language model with vision capabilities, specifically designed to excel in enterprise use cases, particularly in visual document un…
SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge
Andong Wang, Bo Wu, Sunli Chen +5
Learning commonsense reasoning from visual contexts and scenes in real-world is a crucial step toward advanced artificial intelligence. However, existing video reasoning benchmarks…