We use the F-score as the evaluation metric, comparing the machine-generated summaries against human-annotated ground truth.
Helping distributors and collectors organize massive libraries of digital media. icdv-30037
could appear as:
We presented TSAN, a deep unsupervised framework for video summarization. By integrating adversarial learning with a reconstruction objective, we achieve state-of-the-art results on benchmark datasets. This approach significantly reduces the dependency on manual annotations, paving the way for scalable video understanding systems. We use the F-score as the evaluation metric,
We use the F-score as the evaluation metric, comparing the machine-generated summaries against human-annotated ground truth.
Helping distributors and collectors organize massive libraries of digital media.
could appear as:
We presented TSAN, a deep unsupervised framework for video summarization. By integrating adversarial learning with a reconstruction objective, we achieve state-of-the-art results on benchmark datasets. This approach significantly reduces the dependency on manual annotations, paving the way for scalable video understanding systems.