Multimodal Video-to-Music Recommendation via Semantic Retrieval and Temporal Reranking
For video-to-music recommendation, this two-stage approach achieves state-of-the-art results by addressing both semantic and temporal alignment.
VTMR improves video-to-music recommendation by combining semantic retrieval (R@10 from 14.2 to 15.9) with temporal reranking (R@10 to 18.3), outperforming baselines and matching a commercial system in human preference.
We present VTMR, a two-stage framework for Video-To-Music Recommendation. In Stage~1, VTMR aligns comprehensive video and music signals in a joint audio-visual-text representation space and efficiently retrieves semantically compatible candidates using coarse global embeddings. In Stage~2, it reranks the retrieved candidates by attending to the temporal sequences of both video and music, thereby capturing fine-grained temporal correspondence. Evaluated on the video-to-music recommendation task, the multimodal retrieval stage improves R@10 from 14.2 to 15.9 and Median Rank from 75 to 58 over the strongest baseline; the temporal reranker further boosts R@10 to 18.3 and Median Rank to 46, demonstrating complementary gains from richer query encoding and temporal alignment. A human preference study confirms that VTMR is on par with a commercial baseline in overall preference, while outperforming a generative baseline in music quality.