UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection
European Conference on Computer Vision(2023)
摘要
Recent advances in deep neural networks have achieved significant progress in
detecting individual objects from an image. However, object detection is not
sufficient to fully understand a visual scene. Towards a deeper visual
understanding, the interactions between objects, especially humans and objects
are essential. Most prior works have obtained this information with a bottom-up
approach, where the objects are first detected and the interactions are
predicted sequentially by pairing the objects. This is a major bottleneck in
HOI detection inference time. To tackle this problem, we propose UnionDet, a
one-stage meta-architecture for HOI detection powered by a novel union-level
detector that eliminates this additional inference stage by directly capturing
the region of interaction. Our one-stage detector for human-object interaction
shows a significant reduction in interaction prediction time 4x~14x while
outperforming state-of-the-art methods on two public datasets: V-COCO and
HICO-DET.
更多查看译文
关键词
Visual relationships,Real-time detection,Human-object interaction detection,Object detection
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要