A large body of work in both the theoretical and experimental literature suggests that upper bound implications in simple sentences with bare numerals are entailments arising from the semantics of the numeral, rather than scalar implicatures of the sort seen with other scalar terms. However, not all semantic analyses of numerals designed to introduce upper bounding entailments in simple sentenc...

Loss functions, such as the IoU function and GIoU (Generalized Intersection over Union) have been put forward to replace regression loss functions commonly used in calculation. alleviates vanishing gradient case of non-overlapping, but it will completely degenerate into when bounding boxes overlap totally, which fails achieve optimization effect. To solve this problem, some improvements are pro...

Existing person re-identification (re-id) methods assume the provision of accurately cropped person bounding boxes with minimum background noise, mostly by manually cropping. This is significantly breached in practice when person bounding boxes must be detected automatically given a very large number of images and/or videos processed. Compared to carefully cropped manually, auto-detected boundi...

We discuss a comparison of the entropy of pseudo-Anosov maps and the volume of their mapping tori. Recent study of Weil-Petersson geometry of the Teichmüller space tells us that they admit linear inequalities for both directions under some bounded geometry condition. Based on the experiments, we present various observations on the relation between minimal entropies and volumes, and on bounding ...

We present an algorithm which is capable of globally solving a well-constrained transcendental system over some sub-domainD ⊂ R, isolating all roots. Such a system consists of n unknowns and n regular functions, where each may contain non-algebraic (transcendental) functions like sin, exp or log. Every equation is considered as a hyper-surface in R and thus a bounding cone of its normal (gradie...

With recent innovations in dense image captioning, it is now possible to describe every object of the scene with a caption while objects are determined by bounding boxes. However, interpretation of such an output is not trivial due to the existence of many overlapping bounding boxes. Furthermore, in current captioning frameworks, the user is not able to involve personal preferences to exclude o...