Yongqiang Yao

TL;DR: Zhang et al. as discussed by the authors proposed Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object, which significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them.

TL;DR: An Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them.

TL;DR: The Equalized Focal Loss (EFL) is proposed that rebalances the loss contribution of positive and negative samples of different categories independently according to their imbalance degrees and achieves significant performance improvements on rare categories, surpassing all existing state-of-the-art methods.

TL;DR: Wang et al. as mentioned in this paper proposed an attention mechanism based on the improved spatial-temporal convolutional neural network (AMSTCNN) for traffic police gesture recognition, which integrates spatial and temporal information, uses weight matching to pay more attention to the region where human action occurs, and extracts region proposals of the image.

TL;DR: The PicassoNet is proposed, a lightweight cascaded facial landmark detector with adaptive computation for individual facial part and a boundary-aware loss to optimize along tangent and normal of facial boundaries, instead of optimizing along horizontal and vertical as the conventional loss do.