… pedestrian detection with the following contributions. First, we introduce a novel maskguided
attention network that fits naturally into popular pedestrian detection pipelines. Our …

… Multispectral pedestrian detection is an emerging solution … cross-modality interactive
attention network that takes full … two modalities are encoded in the attention module. Next, the …

… attention net that uses global pooling instead. We refer to the FasterRCNN detector using part
attention net … Motivated by these findings, we design an attention net to generate attention …

… attention network for the occlusion handling are explored. Self-attention network learns the
features of a pedestrian’… CAM-based attention network is trained separately from the detectors …

… dual attention network to extenuate the limitations mentioned above for pedestrian detection…
We constructed a single-stage pedestrian detector based on the dual attention network and …

… pedestrian detectors, we use soft-cascaded decision trees instead of cascaded deep neural
networks to achieve high accuracy and fast detection … several pedestrian detection datasets …

… Since we use CNNs as our basic structure, and an attention network as an add-on … pedestrian
detectors and re-identification methods, occlusion handling for pedestrians and attention …

… for occluded pedestrian detection with the following contributions. First, we introduce a novel
mask-guided attention network that fits naturally into popular pedestrian detection pipelines…

… -scale convolution module-attention network (MSCM-ANet), … a pedestrian detection method
for multi-scale attention … scale convolution module and attention module for feature extraction …

… 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 …