Does Video Summarization Require Videos? Quantifying the Effectiveness of Language in Video Summarization
This work addresses video summarization for computer vision applications, offering an incremental improvement in efficiency and explainability.
The paper tackles the challenge of video summarization by proposing a language-only approach that uses textual captions to achieve competitive accuracy with high data efficiency, reducing input data processing while retaining comparable results.
Video summarization remains a huge challenge in computer vision due to the size of the input videos to be summarized. We propose an efficient, language-only video summarizer that achieves competitive accuracy with high data efficiency. Using only textual captions obtained via a zero-shot approach, we train a language transformer model and forego image representations. This method allows us to perform filtration amongst the representative text vectors and condense the sequence. With our approach, we gain explainability with natural language that comes easily for human interpretation and textual summaries of the videos. An ablation study that focuses on modality and data compression shows that leveraging text modality only effectively reduces input data processing while retaining comparable results.