mlsanityData to 7 Oct 2026

PatchNet -- Short-range Template Matching for Efficient Video Processing

arXiv 2103.07371 ↗First posted 10 Mar 2021cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Object recognition is a fundamental problem in many video processing tasks, accurately locating seen objects at low computation cost paves the way for on-device video recognition. We propose PatchNet, an efficient convolutional neural network to match objects in adjacent video frames. It learns the patchwise correlation features instead of pixel features. PatchNet is very compact, running at just 58MFLOPs, 5× simpler than MobileNetV2. We demonstrate its application on two tasks, video object detection and visual object tracking. On ImageNet VID, PatchNet reduces the flops of R-FCN ResNet-101 by 5x and EfficientDet-D0 by 3.4x with less than 1% mAP loss. On OTB2015, PatchNet reduces SiamFC and SiamRPN by 2.5x with no accuracy loss. Experiments on Jetson Nano further demonstrate 2.8x to 4.3x speed-ups associated with flops reduction. Code is open sourced at https://github.com/RalphMao/PatchNet.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 35 references that are in the map. First posted on arXiv 10 Mar 2021.

Builds on

22 of 35 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2018On the Spectral Bias of Neural Networkscited by 1,321
  8. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  9. 2020Designing Network Design Spacescited by 954
  10. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
  11. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  12. 2018Distractor-aware Siamese Networks for Visual Object Trackingcited by 187
10 more
  1. 2016Deep Feature Flow for Video Recognitioncited by 186
  2. 2019Siam R-CNN: Visual Tracking by Re-Detectioncited by 174
  3. 2017Detect to Track and Track to Detectcited by 131
  4. 2017End-to-end representation learning for Correlation Filter based trackingcited by 90
  5. 2016Discriminative Scale Space Trackingcited by 46
  6. 2017Mobile Video Object Detection with Temporally-Aware Feature Mapscited by 39
  7. 2018Fast Object Detection in Compressed Videocited by 33
  8. 2019Looking Fast and Slow: Memory-Guided Mobile Video Object Detectioncited by 22
  9. 2018Detect or Track: Towards Cost-Effective Video Object Detection/Trackingcited by 18
  10. 2018CaTDet: Cascaded Tracked Detector for Efficient Object Detection from Videocited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 2; 2025: 1.

5 papers.

  1. 2022SALISA: Saliency-based Input Sampling for Efficient Video Object Detectioncited by 12
  2. 2022Delta Distillation for Efficient Video Processingcited by 10
  3. 2024MaskVD: Region Masking for Efficient Video Object Detectioncited by 5
  4. 2024Energy-Efficient & Real-Time Computer Vision with Intelligent Skipping via Reconfigurable CMOS Image Sensorscited by 1
  5. 2025A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applicationscited by 0