A CLIP-Hitchhiker's Guide to Long Video Retrieval
This addresses the challenge of effective video retrieval for researchers and practitioners, though it is incremental as it builds on existing CLIP-based approaches.
The paper tackles the problem of adapting image-text models like CLIP for long video retrieval by improving temporal aggregation, finding that a weighted-mean baseline via query-scoring outperforms prior methods and mean-pooling, achieving state-of-the-art results on benchmarks.
Our goal in this paper is the adaptation of image-text models for long video retrieval. Recent works have demonstrated state-of-the-art performance in video retrieval by adopting CLIP, effectively hitchhiking on the image-text representation for video tasks. However, there has been limited success in learning temporal aggregation that outperform mean-pooling the image-level representations extracted per frame by CLIP. We find that the simple yet effective baseline of weighted-mean of frame embeddings via query-scoring is a significant improvement above all prior temporal modelling attempts and mean-pooling. In doing so, we provide an improved baseline for others to compare to and demonstrate state-of-the-art performance of this simple baseline on a suite of long video retrieval benchmarks.