2 papers
cs.CV2026
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen +3
The dense, temporal nature of video presents a profound challenge for automated analysis. Despite the use of powerful Vision-Language Models, prevailing methods for video understan…
cs.AI2025
HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes
Xuanyu Su, Yansong Li, Diana Inkpen +1
Amidst the rise of Large Multimodal Models (LMMs) and their widespread application in generating and interpreting complex content, the risk of propagating biased and harmful memes…