AbstractOpen Set Video Anomaly Detection (OpenVAD) aims to identify abnormal events from video data where both known anomalies and novel ones exist in testing. Unsupervised models learned solely normal videos are applicable any testing but suffer a high false positive rate. In contrast, weakly supervised methods effective detecting could fail an open world. We develop method for the OpenVAD pro...

In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances collectively coming in batch. Recognizers decision either reject or categorize them to some known class using empirically-set threshold. Thus the threshold plays a key role. However, selection it usually depends on knowledge of classes, inevitably incurrin...

Many existing conditional Generative Adversarial Networks (cGANs) are limited to conditioning on pre-defined and fixed class-level semantic labels or attributes. We propose an open set GAN architecture (OpenGAN) that is conditioned per-input sample with a feature embedding drawn from metric space. Using state-of-the-art learning model encodes both fine-grained information, we able generate samp...

Incremental learning aims to learn new classes if they emerge while maintaining the performance for previously known classes. It acquires useful information from incoming data update existing models. Open-set recognition, however, requires ability recognize examples and reject new/unknown There are two main challenges in this matter. First, class discovery: algorithm needs not only but it must ...

In this paper, we introduce the concept of free abstract fuzzy economy and, using Wu’s existence theorem of maximal elements for lower semicontinuous correspondences [26] and Kim and Lee’s existence theorems of best proximity pairs [14], we prove the existence of fuzzy equilibrium pairs for free abstract fuzzy economies first with upper semicontinuous and then with lower semicontinuous constrai...

In this paper, we establish some results on strong convergence for weighted sums of uniformly integrable fuzzy random variables taking values in the space of upper-semicontinuous fuzzy sets in Rp.

We consider the problem of learning a classifier when we dispose little training data from the target domain but abundant training data from several source domains. We make two contributions to the domain adaptation problem. First we extend the Nearest Class Mean (NCM) classifier by introducing for each class domain-dependent mean parameters as well as domain-specific weights. Second, we propos...