Paying Attention to Video Object Pattern Understanding

Authors:
Publisher website
Google Scholar
Abstract
This paper conducts a systematic study on the role of visual attention in video object pattern understanding. By elaborately annotating three popular video segmentation datasets (DAVIS16, Youtube-Objects and SegTrackV2) with dynamic eye-tracking data in the unsupervised video object segmentation (UVOS) setting, for the first time, we quantitatively verified the high consistency of visual attention behavior among human observers, and found strong correlation between human attention and explicit primary object judgments during dynamic, task-driven viewing. Such novel observations provide an in-depth insight of the underlying rationale behind video object pattens. Inspired by these findings, we decouple UVOS into two sub-tasks: UVOS-driven Dynamic Visual Attention Prediction (DVAP) in spatiotemporal domain, and Attention-Guided Object Segmentation (AGOS) in spatial domain. Our UVOS solution enjoys three major advantages: 1) modular training without using expensive video segmentation annotations, instead, using more affordable dynamic fixation data to train the initial video attention module and using existing fixation-segmentation paired static/image data to train the subsequent segmentation module; 2) comprehensive foreground understanding through multi-source learning; and 3) additional interpretability from the biologically-inspired and assessable attention. Experiments on four popular benchmarks show that, even without using expensive video object mask annotations, our model achieves compelling performance compared with state-of-the-arts and enjoys fast processing speed (10 fps on a single GPU). Our collected eye-tracking data and algorithm implementations have been made publicly available at https://github.com/wenguanwang/AGS.
Funding Information
  • Beijing Natural Science Foundation (4182056)
  • CCF-Tencent Open Fund
  • Tencent AI Lab Rhino-Bird Focused Research Program
  • Zhijiang Lab's International Talent Fund for Young Professionals
  • Beijing Municipal Education Commission.
  • Yahoo Faculty Research and Engagement Program award
  • Amazon AWS Machine Learning Research Award

This publication has 105 references indexed in Scilit: