mlsanityData to 7 Oct 2026

Mobile Video Object Detection with Temporally-Aware Feature Maps

arXiv 1711.06368 ↗First posted 17 Nov 2017cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 14; 2023: 4; 2024: 4; 2025: 2; 2026: 3.

39 papers.

Sort:

  1. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  2. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  3. 2022TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 78
  4. 2021Temporal RoI Align for Video Object Recognitioncited by 44
  5. 2023SODFormer: Streaming Object Detection with Transformer Using Events and Framescited by 39
  6. 2022Monocular 3D Object Detection with Depth from Motioncited by 38
  7. 2021Deep Learning for UAV-based Object Detection and Tracking: A Surveycited by 33
  8. 2021Dogfight: Detecting Drones from Drones Videoscited by 18
  9. 2022Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Cloudscited by 17
  10. 2022A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillancecited by 14
  11. 2022SALISA: Saliency-based Input Sampling for Efficient Video Object Detectioncited by 12
  12. 2021Efficient Global-Local Memory for Real-time Instrument Segmentation of Robotic Surgical Videocited by 10
27 more
  1. 2022Delta Distillation for Efficient Video Processingcited by 10
  2. 2022A recurrent CNN for online object detection on raw radar framescited by 9
  3. 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
  4. 2023Oriented object detection in optical remote sensing images using deep learning: a surveycited by 7
  5. 2021ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregationcited by 6
  6. 2022Survey: Exploiting Data Redundancy for Optimization of Deep Learningcited by 6
  7. 2021PatchNet -- Short-range Template Matching for Efficient Video Processingcited by 5
  8. 2021Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregationcited by 5
  9. 2023Flying Bird Object Detection Algorithm in Surveillance Video Based on Motion Informationcited by 5
  10. 2021Temp-Frustum Net: 3D Object Detection with Temporal Fusioncited by 3
  11. 2021FFAVOD: Feature Fusion Architecture for Video Object Detectioncited by 2
  12. 2023ResQ: Residual Quantization for Video Perceptioncited by 2
  13. 2024Transtreaming: Adaptive Delay-aware Transformer for Real-time Streaming Perceptioncited by 2
  14. 2025MVP: Motion Vector Propagation for Zero-Shot Video Object Detectioncited by 2
  15. 2021TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Videocited by 1
  16. 2024SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Drivingcited by 1
  17. 2024Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoringcited by 1
  18. 2021MULTICAST: MULTI Confirmation-level Alarm SysTem based on CNN and LSTM to mitigate false alarms for handgun detection in video-surveillancecited by 0
  19. 2021SGE net: Video object detection with squeezed GRU and information entropy mapcited by 0
  20. 2022Representation Recycling for Streaming Video Analysiscited by 0
  21. 2022AdaEnlight: Energy-aware Low-light Video Stream Enhancement on Mobile Devicescited by 0
  22. 2022Person Detection Using an Ultra Low-resolution Thermal Imager on a Low-cost MCUcited by 0
  23. 2024STF: Spatio-Temporal Fusion Module for Improving Video Object Detectioncited by 0
  24. 2025Instant Video Models: Universal Adapters for Stabilizing Image-Based Networkscited by 0
  25. 2026CMTFormer: Marrying Transformer with Hierarchical Information Interaction for RGB-Event Object Detectioncited by 0
  26. 2026Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edgecited by 0
  27. 2026Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detectioncited by 0