A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval
This work addresses the need for more robust evaluation in video retrieval for researchers and practitioners, though it is incremental as it builds on existing methods with new data generation.
The paper tackles the problem of long video retrieval by addressing the lack of diverse captions in training and evaluation, showing that models struggle with shorter captions and that finetuning on synthetic diverse captions improves performance, achieving gains such as +2.8% R@1 on ActivityNet.
Existing long video retrieval systems are trained and tested in the paragraph-to-video retrieval regime, where every long video is described by a single long paragraph. This neglects the richness and variety of possible valid descriptions of a video, which could range anywhere from moment-by-moment detail to a single phrase summary. To provide a more thorough evaluation of the capabilities of long video retrieval systems, we propose a pipeline that leverages state-of-the-art large language models to carefully generate a diverse set of synthetic captions for long videos. We validate this pipeline's fidelity via rigorous human inspection. We use synthetic captions from this pipeline to perform a benchmark of a representative set of video language models using long video datasets, and show that the models struggle on shorter captions. We show that finetuning on this data can both mitigate these issues (+2.8% R@1 over SOTA on ActivityNet with diverse captions), and even improve performance on standard paragraph-to-video retrieval (+1.0% R@1 on ActivityNet). We also use synthetic data from our pipeline as query expansion in the zero-shot setting (+3.4% R@1 on ActivityNet). We derive insights by analyzing failure cases for retrieval with short captions. For data access and other details, please refer to our project website at https://mgwillia.github.io/10k-words.