DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization

TL;DR

DeepQAMVS introduces a hierarchical pointer network trained with reinforcement learning to generate concise, representative, and chronologically coherent summaries for multiple videos based on user queries.

Contribution

It presents a novel query-aware hierarchical pointer network that jointly optimizes multiple summarization criteria using reinforcement learning.

Findings

Achieves state-of-the-art results on MVS1K dataset.

Inference time scales linearly with input video frames.

Effectively balances conciseness, relevance, and temporal coherence.

Abstract

The recent growth of web video sharing platforms has increased the demand for systems that can efficiently browse, retrieve and summarize video content. Query-aware multi-video summarization is a promising technique that caters to this demand. In this work, we introduce a novel Query-Aware Hierarchical Pointer Network for Multi-Video Summarization, termed DeepQAMVS, that jointly optimizes multiple criteria: (1) conciseness, (2) representativeness of important query-relevant events and (3) chronological soundness. We design a hierarchical attention model that factorizes over three distributions, each collecting evidence from a different modality, followed by a pointer network that selects frames to include in the summary. DeepQAMVS is trained with reinforcement learning, incorporating rewards that capture representativeness, diversity, query-adaptability and temporal coherence. We achieve state-of-the-art results on the MVS1K dataset, with inference time scaling linearly with the number of input video frames.