3 papers
cs.CV2026
CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
Mingfang Zhang, Jingjing Pan, Ashutosh Kumar +7
Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of…
cs.CV2026
InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
Ashutosh Kumar, Rajat Saini, Jingjing Pan +5
Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only supervision. We introduce Ins…
cs.CV2026
Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos
Ziqi Gao, Jieyu Zhang, Wisdom Oluchi Ikezogwo +10
We introduce Synthetic Visual Genome 2 (SVG2), a large-scale panoptic video scene graph dataset. SVG2 contains over 636K videos with 6.6M objects, 52.0M attributes, and 6.7M relati…