원문정보
초록
영어
A novel multimodal approach of highlight ranking for sports video summaries in affective context was proposed based on player behavior information and audio keywords of sports game. The mid-level representation trajectory-action-audio is constructed for the video content by fusing the information of player trajectory, action and audio keywords. Based on trajectory-action-audio, the computational affective features are extracted to describe the objective process of highlight ranking of sports video summaries from user subjective perception. A kernel based nonlinear probabilistic ranking model construction method is proposed, which is robust for the noisy data and provided with good expansibility. In addition, a new subjective evaluation criterion is proposed to guide model construction and feature extraction with the assistance of forward search algorithm.
목차
1. Introduction
2. Emotional Experience Theory and Highlight Ranking Guidance
3. Construct of Video Semantic Middle Expression
4. Emotional Feature Extraction
4.1. Emotional Feature based on Player Trajectory
4.2. Emotional Characteristics based on the Player Actions
4.3. Establishment of Highlight Ranking Model
4. Experimental Analysis And Results
4.1. Round Fragment of Highlight Degree Truth Evaluation based on user Learning
4.2. Evaluation of Effectiveness of Highlight Ranking Method
4.3. General Evaluation of Highlight Ranking Method
4.4. Effectiveness Analysis of Emotional Characteristics
5. Conclusion
References