2 papers
cs.MM2026
AdShot: Benchmarking Multimodal Large Language Models for Video Advertisement Clipping
Wen Xie, Om Rastogi, Sai Siddhartha Vivek Dhir Rangoju +3
Advertisers routinely create multiple duration variants of ads to meet marketing budgets and viewer preferences, a labor-intensive and costly process. While multimodal large langua…
cs.CV2025
AdSum: Two-stream Audio-visual Summarization for Automated Video Advertisement Clipping
Wen Xie, Yanjun Zhu, Gijs Overgoor +3
Advertisers commonly need multiple versions of the same advertisement (ad) at varying durations for a single campaign. The traditional approach involves manually selecting and re-e…