mlsanityData to 14 Oct 2026

Tiny Video Networks

arXiv 1910.06961 ↗First posted 15 Oct 2019cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Video understanding is a challenging problem with great impact on the abilities of autonomous agents working in the real-world. Yet, solutions so far have been computationally intensive, with the fastest algorithms running for more than half a second per video snippet on powerful GPUs. We propose a novel idea on video architecture learning - Tiny Video Networks - which automatically designs highly efficient models for video understanding. The tiny video models run with competitive performance for as low as 37 milliseconds per video on a CPU and 10 milliseconds on a standard GPU.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 16; 2022: 4; 2023: 2; 2024: 2; 2025: 3.

27 papers.

Sort:

  1. 2021TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?cited by 127
  2. 2021VidTr: Video Transformer Without Convolutionscited by 112
  3. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 61
  4. 2021FrameExit: Conditional Early Exiting for Efficient Video Recognitioncited by 59
  5. 2021AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognitioncited by 36
  6. 2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
  7. 2021Contrastive Neural Architecture Search with Neural Architecture Comparatorscited by 34
  8. 2021Skip-Convolutions for Efficient Video Processingcited by 32
  9. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  10. 2021ViPNAS: Efficient Video Pose Estimation via Neural Architecture Searchcited by 26
  11. 2022OCSampler: Compressing Videos to One Clip with Single-step Samplingcited by 23
  12. 2021SSAN: Separable Self-Attention Network for Video Representation Learningcited by 13
15 more
  1. 2021Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memoriescited by 11
  2. 2022Hierarchical Compositional Representations for Few-shot Action Recognitioncited by 10
  3. 2021AdaXpert: Adapting Neural Architecture for Growing Datacited by 9
  4. 2023AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoningcited by 8
  5. 2021Visionary: Vision architecture discovery for robot learningcited by 4
  6. 2023View while Moving: Efficient Video Recognition in Long-untrimmed Videoscited by 4
  7. 2021Adaptive Intermediate Representations for Video Understandingcited by 3
  8. 2021Video Action Recognition Using spatio-temporal optical flow video framescited by 2
  9. 2022GraphVid: It Only Takes a Few Nodes to Understand a Videocited by 2
  10. 2024Streamlining Forest Wildfire Surveillance: AI-Enhanced UAVs Utilizing the FLAME Aerial Video Dataset for Lightweight and Efficient Monitoringcited by 1
  11. 2024Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Spacecited by 1
  12. 2025BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inferencecited by 1
  13. 2021Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Searchcited by 0
  14. 2025Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detectioncited by 0
  15. 2025Video Understanding by Design: How Datasets Shape Video Modelscited by 0