Index

System

• Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices - Chen et al., SenSys '15

  • Cache the results to hide the network delivery and server processing latency

  • Only send the frames that are largely different from the previous frames

• Starfish: Efficient Concurrency Support for Computer Vision Applications - LiKamWa et al., MobiSys '15

  • Track identical library calls and reuse computed results across multiple applications

• The Design and Implementation of a Wireless Video Surveillance System - Zhang et al., MobiCom '15

  • Group cameras monitoring the same area into clusters

  • Uploads frames with high “utility”(e.g., object count)

  • Uploads frames that are different from previous frames(e.g., different object counts)

• MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints - Han et al., MobiSys '16

  • Adaptively pick the best specialized model

• Optasia: A Relational Platform for Efficient Large-Scale Video Analytics - Lu et al., SOCC '16

• DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware - Mathut et al., MobiSys '17

  • A system that can run multiple cloud-scale DL models locally on wearable devices

  • Interleave the loading of memory-intensive FC layers and the execution of compute-intensive convolution layers

• Fast Video Classification via Adaptive Cascading of Deep Models - Shen et al., CVPR '17

  • Leverage the short-term class skew using model cascade

  • Train specialized video online

• NoScope: Optimizing Neural Network Queries over Video at Scale - Kang et al., VLDB '17

  • Model cascade: difference detector(MSE) → cheap/specialized model → full model

• Live Video Analytics at Scale with Approximation and Delay-Tolerance - Zhang et al., NSDI '17

  • Objective: support efficient real-time analytics for multiple queries which have different quality and lag goals

  • Offline Phase: use profiler to get a set of pareto-optimal configurations(a combination of knobs) from resource-quality space (with a variant of greedy hill-climbing)

  • Online Phase: periodically change running queries’ configurations/placement/resource allocation to maximize total utility(quality + lag goals)

• Cachier: Edge-Caching for Recognition Applications - Drolia et al., ICDCS '17

  • Use edge server as a cache with compute resources(similar to CDN)

• LAVEA: Latency-aware Video Analytics on Edge Computing Platform - Yi et al., SEC '17

• Neurosurgeon: collaborative intelligence between the cloud and the mobile edge - Kang et al., ASPLOS '17 [Morning Paper Summary]

  • Observed that 1) data transfer latency is often higher than mobile computation latency, especially on wireless networks. 2) inside a model, data size is decreasing at the front-end whereas per-layer latency is higher at the back-end.

  • NOTE: 2) isn't necessarily true for recent networks with global average pooling

• Scanner: Efficient Video Analysis at Scale - Poms et al., SIGGRAPH '18

  • Store videos as tables which are optimized for frame sampling on compressed videos

  • Express frame operations as dataflow graphs

• Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing - Jiang et al., ATC '18

  • Transfer learning → execute common layers only once

  • Processing more frames with shared DNN vs. greater per-frame accuracy with specialized DNN

• Chameleon: Scalable Adaptation of Video Analytics - Jiang et al., SIGCOMM '18

  • Resource-accuracy tradeoff is affected by some persistent characteristics, so we can reuse configurations over time → temporal correlation

  • Video cameras with the same characteristics share the same best configurations → cross-camera correlations

  • Configuration knobs independently impact accuracy → reduce search space

  • Divide cameras into groups → periodically re-profile “leader” videos

• AWStream: Adaptive Wide-Area Streaming Analytics - Zhang et al., SIGCOMM '18

  • Objective: low latency and high accuracy stream processing in WAN

  • Ask programmers to write degradation functions and profile those configurations

  • Adaptively change the configuration at runtime → react to congestions

• Focus: Querying Large Video Datasets with Low Latency and Low Cost - Hsieh et al., OSDI '18

  • Enable low-latency and low-cost querying over large historical video datasets.

  • At ingest time: classify objects using a cheap CNN, cluster similar objects(KNN search), and index each cluster using top-K most confident classification results.

  • At query-time: looks up the ingest index for cluster centroids that match the class and classifies them using expensive CNN.

• On-Demand Deep Model Compression for Mobile Devices: A Usage-Driven Model Selection Framework - Liu et al., MobiSys '18

  • Adaptively select DNN compression techniques based on user demand(Acc/Storage/Comp cost/Latency/Energy)

• Sprocket: A Serverless Video Processing Framework - Ao et al., SoCC '18

  • Extend the idea of ExCamera - enable users to build more complex pipelines

  • novel straggler mitigation strategy

• Potluck: Cross-Application Approximate Deduplication for Computation-Intensive Mobile Applications - Guo et al., ASPLOS '18

• ReXCam: Resource-Efficient, Cross-Camera Video Analytics at Scale - Jain et al., arXiv' 18

• DeepLens: Towards a Visual Data Management System - Krishnan et al., CIDR '19

  • Objective: Indexing and query optimization for VDMS(For complex queries like join)

  • A novel model for encoding, indexing and storing lineage

• VStore: A Data Store for Analytics on Large Videos - Xu et al., EuroSys '19

• Networked Cameras Are the New Big Data Clusters - Jiang et al., HotEdgeVideo '19

  • Proposes a new “camera cluster” abstraction

    • Saving computing resource

    • Resource Pooling

    • Improving analytics quality

    • Hiding low-level intricacies

• Cracking open the DNN black-box: Video Analytics with DNNs across the Camera-Cloud Boundary - Emmons et al., HotEdgeVideo '19

  • Split-brain inference

• Scaling Video Analytics on Constrained Edge Nodes - Canel et al., SysML '19

  • Assumption: relevant events are rare.

  • Filter frames by using a micro, binary classifier that extract feature maps from base DNN

• AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling - Chin et al., SysML '19

  • Down-sampling images are sometimes beneficial in terms of accuracy(e.g., removing background noise)

  • Adaptively scaling video to improve both speed and accuracy of object detectors

• Bridging the Edge-Cloud Barrier for Real-time Advanced Vision Analytics - Wang et al., HotCloud 19

  • Use super-resolution to enhance video quality before running analytics(related: NAS)

• Edge Assisted Real-time Object Detection for Mobile Augmented Reality - Liu et al., MobiCom '19

  • Dynamic RoI Encoding: decrease the encoding quality of uninterested areas(use the last processed frame as heuristic)

  • (Dependency-aware) Parallel streaming and inference: divide frames into slices and parallelize the processing between slices

• Scaling Video Analytics Systems to Large Camera Deployments - Jain et al., HotMobile '19

  • Leverage cross-camera correlations to reduce resource usage and achieve higher inference accuracy

• Visual Road: A Video Data Management Benchmark - Haynes et al., SIGMOD '19

  • An auto-generated benchmark that evaluates the performance of VDBMS

  • Let users place an arbitrary number of cameras, each with configurable position, resolution, and field of view

  • Composite queries and automatically generated ground truth labels

• Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels - Fu et al., arXiv '19

• BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics - Kang et al., VLDB '20

  • Objective: Support (approximate) aggregate and limit queries over large video dataset

  • At ingest time, run object detection on small samples of frames and store them

  • For each query, use them to train a query-specific proxy model

• MIRIS: Fast Object Track Queries in Video - Bastani et al., SIGMOD '20

• Server-Driven Video Streaming for Deep Learning Inference - Du et al., SIGCOMM '20

  • Iterative video processing driven by server-side DNN

• Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics - Li et al., SIGCOMM '20

  • Dynamically adapts filtering decisions based on feature type, threshold, etc.

• Visor: Privacy-Preserving Video Analytics as a Cloud Service - Poddar - et al., Security '20

• Panorama: A Data System for Unbounded Vocabulary Querying over Video - Zhang et al., VLDB '20

  • A system that let users generalize to unbounded vocabularies without manual retraining

• Real-Time Video Inference on Edge Devices via Adaptive Model Streaming - Khani et al., arXiv '20