.png){kind=icon}
返回
Hierarchical Graph Pattern Understanding for Zero-Shot Video Object Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2023.3326395.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene. The temporal consistency provided by the optical flow could be effectively supplemented by modeling in a structural form. This paper proposes a new hierarchical graph neural network (GNN) architecture, dubbed hierarchical graph pattern understanding (HGPU), for zero-shot video object segmentation (ZS-VOS). Inspired by the strong ability of GNNs in capturing structural relations, HGPU innovatively leverages motion cues (i.e., optical flow) to enhance the high-order representations from the neighbors of target frames. Specifically, a hierarchical graph pattern encoder with message aggregation is introduced to acquire different levels of motion and appearance features in a sequential manner. Furthermore, a decoder is designed for hierarchically parsing and understanding the transformed multi-modal contexts to achieve more accurate and robust results. HGPU achieves state-of-the-art performance on four publicly available benchmarks (DAVIS-16, YouTube-Objects, Long-Videos and DAVIS-17). Code and pre-trained model can be found at https://github.com/NUST-Machine-Intelligence-Laboratory/HGPU.
Keyword:
Video object segmentation
graph neural network
zero-shot
encoder-decoder
optical flow
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
Forced acoustical response of a cavity coupled with a semi-infinite space using coupled mode theory.png)
Wave Motion
Wave MotionIF0
PREAI
分享收藏Chiral cage molecules generated by regioselective O-alkylation of a doubly-bridged calix[8]arene
PREAI
分享收藏
查看更多内容