Object detection, including objectness detection (OD), salient object detection (SOD), and category-specific object detection (COD), is one of the most fundamental yet challenging …
B Jiang, R Luo, J Mao, T Xiao… - Proceedings of the …, 2018 - openaccess.thecvf.com
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect …
The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in …
JR Chang, YS Chen - … of the IEEE conference on computer …, 2018 - openaccess.thecvf.com
Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks …
S Chen, X Tan, B Wang, X Hu - Proceedings of the …, 2018 - openaccess.thecvf.com
Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently. However, there still exists following two major …
For object detection, the two-stage approach (eg, Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (eg, SSD) has the advantage of high …
We present a box-free bottom-up approach for the tasks of pose estimation and instance segmentation of people in multi-person images using an efficient single-shot model. The …
B Singh, LS Davis - Proceedings of the IEEE conference on …, 2018 - openaccess.thecvf.com
An analysis of different techniques for recognizing and detecting objects under extreme scale variation is presented. Scale specific and scale invariant design of detectors are …
W Wang, R Yu, Q Huang… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Abstract We introduce Similarity Group Proposal Network (SGPN), a simple and intuitive deep learning framework for 3D object instance segmentation on point clouds. SGPN uses a …