Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous events in the training data. We propose a weakly supervised anomaly detection system that has multiple contributions including a random batch selection mechanism to reduce interbatch correlation and a normalcy suppression block (NSB) which learns to minimize anomaly scores over normal regions of a video by utilizing the overall information available in a training batch. In addition, a clustering loss block (CLB) is proposed to mitigate the label noise and to improve the representation learning for the anomalous and normal regions. This block encourages the backbone network to produce two distinct feature clusters representing normal and anomalous events. An extensive analysis of the proposed approach is provided using three popular anomaly detection datasets including UCF-Crime, ShanghaiTech, and UCSD Ped2. The experiments demonstrate the superior anomaly detection capability of our approach.

Due to the rarity of anomalous events, video anomaly detection is typically approached as one-class classification (OCC) problem. Typically in OCC, an autoencoder (AE) is trained to reconstruct the normal only training data with the expectation that, in test time, it can poorly reconstruct the anomalous data. However, previous studies have shown that, even trained with only normal data, AEs can often reconstruct anomalous data as well, resulting in a decreased performance. To mitigate this problem, we propose to limit the anomaly reconstruction capability of AEs by incorporating pseudo anomalies during the training of an AE. Extensive experiments using five types of pseudo anomalies show the robustness of our training mechanism towards any kind of pseudo anomaly. Moreover, we demonstrate the effectiveness of our proposed pseudo anomaly based training approach against several existing state-of-the-art (SOTA) methods on three benchmark video anomaly datasets, outperforming all the other reconstruction-based approaches in two datasets and showing the second best performance in the other dataset.

Thanks to Earth-level Street View images from Google Maps, a visual image geo-localization can estimate the coarse location of a query image with a visual place recognition process. However, this can get very challenging when non-static objects change with time, severely degrading image retrieval accuracy. We address the problem of city-scale visual place recognition in complex urban environments crowded with non-static clutters. To this end, we first analyze what clutters degrade similarity matching between the query and database images. Second, we design a self-supervised trainable de-attention module that prevents the network from focusing on non-static objects in an input image. In addition, we propose a novel triplet marginal loss called sharpened triplet marginal loss to make feature descriptors more discriminative. Lastly, due to the lack of geo-tagged public datasets with a high density of non-static objects, we propose a clutter augmentation method to evaluate our approach. The experimental results show that our model has notably improved over the existing attention methods in geo-localization tasks on the public benchmark datasets and on their augmented versions with high population and traffic. Our code is available at https://github.com/ccsmm78/deattention_with_stml_for_vpr.

Video anomaly detection is well investigated in weakly-supervised and one-class classification (OCC) settings. However, unsupervised video anomaly detection methods are quite sparse, likely because anomalies are less frequent in occurrence and usually not well-defined, which when coupled with the absence of ground truth supervision, could adversely affect the performance of the learning algorithms. This problem is challenging yet rewarding as it can completely eradicate the costs of obtaining laborious annotations and enable such systems to be deployed without human intervention. To this end, we propose a novel unsupervised Generative Cooperative Learning (GCL) approach for video anomaly detection that exploits the low frequency of anomalies towards building a cross-supervision between a generator and a discriminator. In essence, both networks get trained in a cooperative fashion, thereby allowing unsupervised learning. We conduct extensive experiments on two large-scale video anomaly detection datasets, UCF crime and ShanghaiTech. Consistent improvement over the existing state-of-the-art unsupervised and OCC methods corroborate the effectiveness of our approach.

Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such networks challenging. Attributed to the adversarial training, performance of such models fluctuates drastically with each training step, making it difficult to halt the training at an optimal point. In the current study, we propose a robust anomaly detection framework that overcomes such instability by transforming the fundamental role of the discriminator from identifying real vs. fake data to distinguishing good vs. bad quality reconstructions. For this purpose, we propose a method that utilizes the current state as well as an old state of the same generator to create good and bad quality reconstruction examples. The discriminator is trained on these examples to detect the subtle distortions that are often present in the reconstructions of anomalous data. In addition, we propose an efficient generic criterion to stop the training of our model, ensuring elevated performance. Extensive experiments performed on six datasets across multiple domains including image and video based anomaly detection, medical diagnosis, and network security, have demonstrated excellent performance of our approach.

A popular method for anomaly detection is to use the generator of an adversarial network to formulate anomaly score over reconstruction loss of input. Due to the rare occurrence of anomalies, optimizing such networks can be a cumbersome task. Another possible approach is to use both generator and discriminator for anomaly detection. However, attributed to the involvement of adversarial training, this model is often unstable in a way that the performance fluctuates drastically with each training step. In this study, we propose a framework that effectively generates stable results across a wide range of training steps and allows us to use both the generator and the discriminator of an adversarial model for efficient and robust anomaly detection. Our approach transforms the fundamental role of a discriminator from identifying real and fake data to distinguishing between good and bad quality reconstructions. To this end, we prepare training examples for the good quality reconstruction by employing the current generator, whereas poor quality examples are obtained by utilizing an old state of the same generator. This way, the discriminator learns to detect subtle distortions that often appear in reconstructions of the anomaly inputs. Extensive experiments performed on Caltech-256 and MNIST image datasets for novelty detection show superior results. Furthermore, on UCSD Ped2 video dataset for anomaly detection, our model achieves a frame-level AUC of 98.1%, surpassing recent state-of-the-art methods.

Anomalous event detection in surveillance videos is a challenging and practical research problem among image and video processing community. Compared to the frame-level annotations of anomalous events, obtaining video-level annotations is quite fast and cheap though such high-level labels may contain significant noise. More specifically, an anomalous labeled video may actually contain anomaly only in a short duration while the rest of the video frames may be normal. In the current work, we propose a weakly supervised anomaly detection framework based on deep neural networks which is trained in a self-reasoning fashion using only video-level labels. To carry out the self-reasoning based training, we generate pseudo labels by using binary clustering of spatio-temporal video features which helps in mitigating the noise present in the labels of anomalous videos. Our proposed formulation encourages both the main network and the clustering to complement each other in achieving the goal of more accurate anomaly detection. The proposed framework has been evaluated on publicly available real-world anomaly detection datasets including UCF-crime, ShanghaiTech and UCSD Ped2. The experiments demonstrate superiority of our proposed framework over the current state-of-the-art methods.

There have been several efforts to provide service-aware technologies in the networks, such as Service-Oriented Architecture (SOA) and Service Delivery Platform (SDP). These technologies were integrated with Service Overlay Network (SON) infrastructure to support control and delivery of services over multiple network domains. However, SON has the limitations of handling the increasing need of ubiquitous and dynamic environment of users and services. To provide better Quality of Experience (QoE) to users in the ubiquitous and dynamic environment, we advocate the notion of Context-aware SON (CSON) to support context-aware and dynamically adaptive service delivery and control. In this paper, we introduce the concept of CSON, and provide a comprehensive review of the basic ideas by visiting our experiences on designing and developing a prototype for CSON.

In this paper, we propose QoS-constrained peer selection and nondisruptive rate adaptation schemes with considering shared bottleneck problem to provide a stable peer-to-peer live video streaming service during vertical handoff. In the proposed scheme, a QoS-constrained peer is selected by estimating bandwidth with active probing, and a reception rate converges to a stable state without any QoS degradation with help of multi-path handoff. The shared bottleneck problem is addressed by adjusting the estimated bandwidth and yielding the redundant bandwidth usage.

An emotional robot is regarded as being able to express its diverse emotions in response to internal or external events. This paper presents a robot affective system that is able to express life-like emotions. In order to do that, the overall architecture of our affective system is based on neuroscience from which we obtained the natural emotional processing routines. Based on that architecture, we apply the reinforcer effects expecting that those would lead the affective system to be more similar to real-life's emotion expression. The robot affective system has responsibility for gathering environmental information and evaluating which environmental stimuli are rewarding or punishing. The emotion processing involves with appraisal of the external and internal stimuli, such as homeostasis, and generates the affective states of the robot. Therefore, emotions are associated with the presentation, omission, and termination of the expected rewards or punishers (reinforcers). The experimental results show that our affective system can express several emotions simultaneously as well as the emotions decrease, increase, or changes to another emotion seamlessly as time passes.

This paper reviews and discusses many issues and implementation details of an intelligent home service robot in a URC (Ubiquitous Robotic Companion) environment. In contrast to standalone service robots, URC service robots provide a variety of functions by the full utilization of network infrastructure. Many challenges are waiting to be faced in front of us—for example, the execution and coordination of services, multiple team support, session and service management, and communication protocol and its architecture, and resource management of a robot. This paper proposes solutions for the above issues and applies the solutions to a network-based home service robot called Nettoro. As an application of the proposed architecture, a pilot project launched December, 2006 is presented and the results are briefly discussed.

For a service robot to be more human friendly, it is required to have various emotional interactions with human. Inspired from both neuroscience and cognitive science, this paper proposes a dynamic robot affective system that can have various emotional states at the same time and express those combined emotions just like humans do. The system comprises three modules: an appraisal module, an emotion-generation module, and an emotional expression module. The appraisal module has responsibility for gathering environmental information and evaluating whether external stimuli are rewarding or punishing. Based on the appraisal results and the homeostasis, the emotion-generation module generates affective states of the robot. The emotional expression module, then, combines and expresses emotional behaviors in accordance with the current affective states (e.g., producing facial expressions). As a result, the robot affective system can generate various emotions simultaneously and produces various emotional expressions continuously, just like human's sequential or parallel execution of emotional behaviors

This paper illustrates the evolutionary adaptive process of the rules of a fuzzy controller evolved by a genetic algorithm. Evolutionary activity and schema analysis are used to evaluate and analyze the evolution. The analysis shows that the evolution has been adaptive and final fuzzy rules have evolved from adaptive ones of earlier generations.

We present the design, implementation, and performance analysis of group-aided multicast (GAM), a scalable many-to-many reliable multicast transport protocol. GAM achieves high quality ACK trees while keeping the tree maintenance overhead reasonably low in the presence of dynamic group membership and route changes. It is supported by a group configuration mechanism organizing the members in a multicast session into multiple small groups and a tree configuration mechanism maintaining logical trees according to the underlying multicast routing trees. With the two mechanisms, GAM builds a two-layer hierarchy of multi-level logical trees from which high-quality per-source ACK trees are generated. Simulation results show that the GAM protocol is more scalable than a NACK suppression protocol in terms of processing time for request/repair messages and recovery latency.

Explaining emergence is a difficult work, such that there are many arguments on what it is or how it can be explained. Nonetheless, it is frequently referred to in many fields, such as behavior-based robotics, artificial life and complex systems, without any formal definition. In this paper, we develop a fuzzy logic controller for a simulated mobile robot with a genetic algorithm and analyze the behavior of the controller from the perspective of observational emergence. The analysis shows that the fuzzy logic controller has acquired emergent behavior through the interactions of the underlying fuzzy rules.

Recently, there has been extensive work on the construction of fuzzy controllers for mobile robots by a genetic algorithm (GA); therefore, we can realize evolutionary optimization as a promising method for developing fuzzy controllers. However, much investigation on the evolutionary fuzzy controller remains because most of the previous works have not seriously attempted to analyze the fuzzy controller obtained by evolution. This paper develops a fuzzy logic controller for a mobile robot with a GA in simulation environments and analyzes the behaviors of the controller with a state transition diagram of the internal model. Experimental results show that appropriate control mechanisms of the fuzzy controller are obtained by evolution. The controller has evolved wen enough to smoothly drive the robot in different environments. The robot produces emergent behaviors by the interaction of several fuzzy rules obtained.