Video abstract generation method and system based on graph-guided adaptive key frame sampling

By using a graph-guided adaptive keyframe sampling method, a coherent video summary is generated, which solves the problem that existing video summarization technologies cannot adapt to videos of different durations. It achieves a stable balance between coverage, diversity and coherence, and adapts to the resource constraints of different application scenarios.

CN121815045APending Publication Date: 2026-04-07SHANDONG JIAOTONG UNIV
0 Cites 1 Cited by

Patent Information

Application Number
CN202610038976.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-13
Publication Date
2026-04-07

AI Technical Summary

Technical Problem

Existing video summarization technologies cannot adapt to videos of different durations during keyframe selection. Insufficient inter-frame correlation modeling leads to fragmented or repetitive keyframe selection. Furthermore, the sampling budget and selection process are independent of each other, making it difficult to achieve a stable balance between coverage, diversity, and coherence.

Method used

A graph-guided adaptive keyframe sampling method is adopted, which generates a coherent importance distribution through global content and semantic relationships. Combined with a sampling rate function that varies with the video length and a controllable distribution focusing mechanism, the budget and selection process are unified, and video summaries are generated using graph-guided weights and adaptive sampling weights.

Benefits of technology

It achieves stable and adjustable video summarization under different video lengths and content complexities, avoiding over-sampling of short videos and under-sampling of long videos, maintaining the coverage, diversity and coherence of the summaries, and adapting to the resource constraints of different application scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a video abstract generation method and system based on graph-guided adaptive key frame sampling, and relates to the technical field of video abstract generation, and the method comprises the steps: obtaining and extracting different scale features of each video frame, and generating multi-scale fusion features through the weighted fusion of scale attention weights; calculating inter-frame similarity to construct a weighted undirected graph, obtaining global structured frame features of each video frame through multi-layer feature propagation, and calculating graph guide weight of each frame; introducing a learnable distribution focusing parameter to perform power scaling on the graph guide weight to obtain an adaptive sampling weight, and calculating a final comprehensive weight; and according to the video frame length of the original video, calculating the number of sampling frames through a video length adaptive function, and according to the comprehensive weight and the number of sampling frames, sampling key frames by adopting a frame screening strategy based on sorting to generate a video abstract. According to the method, the video abstract with better coverage, diversity and stability balance can be generated.
Need to check novelty before this filing date? Find Prior Art