標題: Deep 360 Pilot: Learning a Deep Agent for Piloting through 360 degrees Sports Videos
作者: Hu, Hou-Ning
Lin, Yen-Chen
Liu, Ming-Yu
Cheng, Hsien-Tzu
Chang, Yung-Ju
Sun, Min
交大名義發表
National Chiao Tung University
公開日期: 1-一月-2017
摘要: Watching a 360 degrees sports video requires a viewer to continuously select a viewing angle, either through a sequence of mouse clicks or head movements. To relieve the viewer from this "360 piloting" task, we propose "deep 360 pilot" - a deep learning-based agent for piloting through 360 degrees sports videos automatically. At each frame, the agent observes a panoramic image and has the knowledge of previously selected viewing angles. The task of the agent is to shift the current viewing angle (i.e. action) to the next preferred one (i.e., goal). We propose to directly learn an online policy of the agent from data. Specifically, we leverage a state-of-the-art object detector to propose a few candidate objects of interest (yellow boxes in Fig. 1). Then, a recurrent neural network is used to select the main object (green dash boxes in Fig. 1). Given the main object and previously selected viewing angles, our method regresses a shift in viewing angle to move to the next one. We use the policy gradient technique to jointly train our pipeline, by minimizing: (1) a regression loss measuring the distance between the selected and ground truth viewing angles, (2) a smoothness loss encouraging smooth transition in viewing angle, and (3) maximizing an expected reward of focusing on a foreground object. To evaluate our method, we built a new 360-Sports video dataset consisting of five sports domains. We trained domain-specific agents and achieved the best performance on viewing angle selection accuracy and users' preference compared to [53] and other baselines.
URI: http://dx.doi.org/10.1109/CVPR.2017.153
http://hdl.handle.net/11536/146873
ISSN: 1063-6919
DOI: 10.1109/CVPR.2017.153
期刊: 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
起始頁: 1396
結束頁: 1405
顯示於類別:會議論文