“…Recent approaches like [31,59,60,61,62,63] have aimed at incorporating various forms of related information like attention [59], semantic priors [60], segmentation [61], inverse attention [62], and hierarchical attention [31] respectively into the network. Other techniques such as [64,65,66,67,68] leverage features from different layers of the network using different techniques like trellis style encoder decoder [64], explicitly considering perspective [65], context information [66], adaptive density map generation [68] and multiple views [67].…”