Context Refinement for Object Detection

105 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, methodology): “8% AP), C-Mask RCNN [7] ( 42 .”
Deep High-Resolution Representation Learning for Visual Recognition (2019, neutral): “C-FRCNN [25] ResNet-101 800 1× 39.”
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (2019, background): “We observe that 2D object detection performs reasonably and continues to make rapid advances [5, 6, 11, 14, 19, 33].”
Recent Advances in Deep Learning for Object Detection (2019, background): “code contextual information is to implicitly encode region features by adding image features surrounding region proposals and a large number of approaches have been proposed based on this idea [131, 106, 140, 141, 142, 143].”
High-Resolution Representations for Labeling Pixels and Regions (2019, unknown): “C-FRCNN [18] ResNet-101 800 1× 39.”
Multi-task incremental learning for object detection (2020, background): “Also, it has been shown in [6, 46] that context information is very important for object detection.”