Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint
Zhiyun Jiang, Hanyong Wang, Binbin Liang +3
Traditional scene understanding focuses on affirmative information objectively present in images. However, in safety-critical domains, comprehending key information that should exi…
cs.CV2026
Benchmarking MLLMs via Cognitive Expected Scene Graph for Safety-Critical Visual Negation Understanding
Zhiyun Jiang, Hanyong Wang, Binbin Liang +3
True machine intelligence requires transcending passive pixel registration to master top-down functional reasoning over absent information via visual negation understanding. Howeve…
cs.CV2020
Exploring the Impacts from Datasets to Monocular Depth Estimation (MDE) Models with MineNavi
Xiangtong Wang, Binbin Liang, Menglong Yang +1
Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such a…