Bounding overwatch

About: Bounding overwatch is a research topic. Over the lifetime, 966 publications have been published within this topic receiving 15156 citations.

Instrument-tissue Interaction Quintuple Detection in Surgery Videos

Abstract: Instrument-tissue interaction detection in surgical videos is a fundamental problem for surgical scene understanding which is of great significance to computer-assisted surgery. However, few works focus on this fine-grained surgical activity representation. In this paper, we propose to represent instrument-tissue interaction as $$\langle $$ instrument bounding box, tissue bounding box, instrument class, tissue class, action class $$\rangle $$ quintuples. We present a novel quintuple detection network (QDNet) for the instrument-tissue interaction quintuple detection task in cataract surgery videos. Specifically, a spatiotemporal attention layer (STAL) is proposed to aggregate spatial and temporal information of the regions of interest between adjacent frames. We also propose a graph-based quintuple prediction layer (GQPL) to reason the relationship between instruments and tissues. Our method achieves an $$\textrm{mAP}$$ of 42.24% on a cataract surgery video dataset, significantly outperforming other methods.

On Adaptive Influence Maximization under General Feedback Models

Abstract: The classic influence maximization problem explores the strategies for deploying cascades such that the total influence is maximized, and it assumes that the seed nodes that initiate the cascades are computed prior to the diffusion process. In its adaptive version, the seed nodes are allowed to be launched in an adaptive manner after observing certain diffusion results. In this paper, we provide a systematic study on the adaptive influence maximization problem, focusing on the algorithmic analysis of the general feedback models. We introduce the concept of regret ratio to characterize the key trade-off in designing adaptive seeding strategies, based on which we present the approximation analysis for the well-known greedy policy. In addition, we provide analysis concerning improving the efficiencies and bounding the regret ratio. Finally, we propose several future research directions.

Providing Response Times Guarantees for Mixed-Criticality Network Slicing in 5G

Abstract: Mission critical applications in domains such as Industry 4.0, autonomous vehicles or Smart Grids are increasingly dependent on flexible, yet highly reliable communication systems. In this context, Fifth Generation of mobile Communication Networks (5G) promises to support mixed-criticality applications on a single unified physical communication network. This is achieved by a novel approach known as network slicing, that promises to fulfil diverging requirements while providing strict separation between network tenants. We focus in this work on hard performance guarantees by formalizing an analytical method for bounding response times in mixed-criticality 5G network slicing. We reduce pessimism considering models on workload variations.

Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors

Abstract: With the recent development of Semi-Supervised Object Detection (SS-OD) techniques, object detectors can be improved by using a limited amount of labeled data and abundant unlabeled data. However, there are still two challenges that are not addressed: (1) there is no prior SS-OD work on anchor-free detectors, and (2) prior works are ineffective when pseudo-labeling bounding box regression. In this paper, we present Unbiased Teacher v2, which shows the generalization of SS-OD method to anchor-free detectors and also introduces Listen2Student mechanism for the unsupervised regression loss. Specifically, we first present a study examining the effectiveness of existing SS-OD methods on anchor-free detectors and find that they achieve much lower performance improvements under the semi-supervised setting. We also observe that box selection with centerness and the localization-based labeling used in anchor-free detectors cannot work well under the semi-supervised setting. On the other hand, our Listen2Student mechanism explicitly prevents misleading pseudo-labels in the training of bounding box regression; we specifically develop a novel pseudo-labeling selection mechanism based on the Teacher and Student's relative uncertainties. This idea contributes to favorable improvement in the regression branch in the semi-supervised setting. Our method, which works for both anchor-free and anchor-based methods, consistently performs favorably against the state-of-the-art methods in VOC, COCO-standard, and COCO-additional.

Validating complex agent behavior

Abstract: Developing software agents that replicate human behavior, even within a narrow domain, is a time consuming and error prone process. The most widely used methodology for designing these agents is based on the complementary processes of knowledge acquisition and validation, both of which have been cited as significant bottlenecks. In this thesis, we identify two methods for comparing actors' behavior that have the potential to decrease the cost of validation. The first is a simple sequence-based approach that can be used to compare many different aspects of two actors' behavior. Although initially promising, our empirical and analytical analysis exposes significant limitations with this general class of approaches, especially as the complexity of the domain increases. As a result, we turn to a novel comparison approach that we call behavior bounding. Unlike the sequential approaches, behavior bounding uses a concise representation of an actor's aggregate behavior as a basis for performing its comparison. We show that behavior bounding requires minimal human effort to use and that its representation of behavior is efficient to construct and maintain even as the complexity of the environment increases. Furthermore, we show that behavior bounding outperforms the sequential comparison approach in two domains of distinct complexity. Finally, we provide empirical evidence that behavior bounding's summary of the differences in two actors' behavior can be used to significantly speed up the knowledge validation process.