More Like this

1. Event Trend Aggregation Under Rich Event Matching Semantics

   https://doi.org/10.1145/3299869.3319862  

   Poppe, Olga ; Lei, Chuan ; Rundensteiner, Elke A. ; Maier, David ( June 2019 , SIGMOD)

   null (Ed.)

   Streaming applications from cluster monitoring to algorithmic trading deploy Kleene queries to detect and aggregate event trends. Rich event matching semantics determine how to compose events into trends. The expressive power of stateof- the-art streaming systems remains limited since they do not support many of these semantics. Worse yet, they suffer from long delays and high memory costs because they maintain aggregates at a fine granularity. To overcome these limitations, our Coarse-Grained Event Trend Aggregation (Cogra) approach supports a rich variety of event matching semantics within one system. Better yet, Cogra incrementally maintains aggregates at the coarsest granularity possible for each of these semantics. In this way, Cogra minimizes the number of aggregates – reducing both time and space complexity. Our experiments demonstrate that Cogra achieves up to six orders of magnitude speed-up and up to seven orders of magnitude memory reduction compared to state-of-the-art approaches. 

   more » « less
2. Pre-Event Trends in the Panel Event-Study Design

   https://doi.org/10.1257/aer.20180609  

   Freyaldenhoven, Simon ; Hansen, Christian ; Shapiro, Jesse M. ( September 2019 , American Economic Review)
3. Towards fully automated post-event data collection and analysis: Pre-event and post-event information fusion

   https://doi.org/10.1016/j.engstruct.2019.109884  

   Lenjani, Ali ; Dyke, Shirley J. ; Bilionis, Ilias ; Yeum, Chul Min ; Kamiya, Kenzo ; Choi, Jongseong ; Liu, Xiaoyu ; Chowdhury, Arindam G. ( April 2020 , Engineering Structures)

   null (Ed.)
4. Generalized Event Cameras

   Sundar, Varun Sundar ; Dutson, Matthew ; Ardelean, Andrei ; Bruschini, Claudio ; Charbon, Edoardo ; Gupta, Mohit ( June 2024 , IEEE CVPR 2024 (Conference on Computer Vision and Pattern Recognition))

   Event cameras capture the world at high time resolution and with minimal bandwidth requirements. However, event streams, which only encode changes in brightness, do not contain sufficient scene information to support a wide variety of downstream tasks. In this work, we design generalized event cameras that inherently preserve scene intensity in a bandwidth-efficient manner. We generalize event cameras in terms of when an event is generated and what information is transmitted. To implement our designs, we turn to single-photon sensors that provide digital access to individual photon detections; this modality gives us the flexibility to realize a rich space of generalized event cameras. Our single-photon event cameras are capable of high-speed, high-fidelity imaging at low readout rates. Consequently, these event cameras can support plug-and-play downstream inference, without capturing new event datasets or designing specialized event-vision models. As a practical implication, our designs, which involve lightweight and near-sensor-compatible computations, provide a way to use single-photon sensors without exorbitant bandwidth costs. 

   more » « less
5. Event Neural Networks

   Dutson, Matthew ; Li, Yin ; Gupta, Mohit ( August 2022 , Springer (European Conference on Computer Vision - ECCV))

   Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated. Such redundancy occurs at multiple levels of complexity, from low-level pixel values to textures and high-level semantics. We propose Event Neural Networks (EvNets), which leverage this redundancy to achieve considerable computation savings during video inference. A defining characteristic of EvNets is that each neuron has state variables that provide it with long-term memory, which allows low-cost, high-accuracy inference even in the presence of significant camera motion. We show that it is possible to transform a wide range of neural networks into EvNets without re-training. We demonstrate our method on state-of-the-art architectures for both high- and low-level visual processing, including pose recognition, object detection, optical flow, and image enhancement. We observe roughly an order-ofmagnitude reduction in computational costs compared to conventional networks, with minimal reductions in model accuracy. 

   more » « less