Preprint
Sep 2026
Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval
Results show that adaptively orchestrating foundation-model capabilities can combine scalable retrieval with fine-grained reasoning without task-specific training, and are shown to be state-of-the-art among training-free approaches.
Dmitry Demidov, Muhammad Zaigham Zaheer, Omkar Thawakar et al.
· 0 citations