… and small-scale pedestrian detection remain inherently hard … -scale pedestrian detection
method with global–local attention … small-scale pedestrians, we add a high-resolution detection …

… attention mechanisms are motivated by the fact that different channels of CNN-based detectors,
in our case a FasterRCNN pedestrian detector… channel features are localizable and often …

… local areas that distinguish subordinate categories by cascading … detection design, we
constructed a pedestrian detection algorithm based on multi-scale feature extraction and attention …

… Convolution is a local operation, which obtains local information of an image by … detector,
we designed an anchor-free pedestrian detector called CSANet based on the dual attention …

… pedestrian detector, and we find that different channels activate responses for different body
parts respectively. These findings motivate us to employ an attention … Therefore, an attention …

… In this paper, a multi-scale pedestrian detector based on self-attention mechanism and …
global information, the spatial attention mechanism asymmetric pyramid non-local block (APNB) …

… Fusion with Local Attention In this section, we will discuss different options of using local
attention with CBAM module. CBAM is composed of channel attention and spatial attention. …

… of attention guidance on the detector for the detections. Compared with the state-of-the-art
methods on two standard pedestrian … network, the core of our model, implements the local …

… PiCANet [33] is a pixel-level contextual attention network that can selectively attend to local
or global contexts and produce informative contextual features for each pixel. We incorporate …

… Pedestrian detection is one of the most challenging tasks in computer vision, and has received
a lot of attention in the last years. Recently, some authors have shown the advantages of …