In this paper, we propose a novel encoder-decoder network, called extit {Scale Aggregation
Network (SANet)}, for accurate and efficient crowd counting. The encoder extracts multi …

Nearly all existing counting methods are designed for a specific object class. Our work,
however, aims to create a counting model able to count any class of object. To achieve this …

Most of the recent advances in crowd counting have evolved from hand-designed density
estimation networks, where multi-scale features are leveraged to address the scale variation …