mlsanityData to 7 Oct 2026

LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition

arXiv 1912.01601 ↗First posted 3 Dec 2019cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

This paper presents LiteEval, a simple yet effective coarse-to-fine framework for resource efficient video recognition, suitable for both online and offline scenarios. Exploiting decent yet computationally efficient features derived at a coarse scale with a lightweight CNN model, LiteEval dynamically decides on-the-fly whether to compute more powerful features for incoming video frames at a finer scale to obtain more details. This is achieved by a coarse LSTM and a fine LSTM operating cooperatively, as well as a conditional gating module to learn when to allocate more computation. Extensive experiments are conducted on two large-scale video benchmarks, FCVID and ActivityNet, and the results demonstrate LiteEval requires substantially less computation while offering excellent classification accuracy for both online and offline predictions.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 15; 2023: 11; 2024: 9; 2025: 2; 2026: 3.

65 papers.

Sort:

By area:

  1. 2021Dynamic Neural Networks: A Surveycited by 405
  2. 2024VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videoscited by 242
  3. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  4. 2021BEVT: BERT Pretraining of Video Transformerscited by 169
  5. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
  6. 2021SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Eventscited by 84
  7. 2021Adaptive Focus for Efficient Video Recognitioncited by 76
  8. 2022SVFormer: Semi-supervised Video Transformer for Action Recognitioncited by 67
  9. 2021FrameExit: Conditional Early Exiting for Efficient Video Recognitioncited by 59
  10. 2021Efficient Video Transformers with Spatial-Temporal Token Selectioncited by 58
  11. 2021MGSampler: An Explainable Sampling Strategy for Video Action Recognitioncited by 49
  12. 2021AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognitioncited by 48
38 more
  1. 2021AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognitioncited by 37
  2. 2021AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognitioncited by 36
  3. 2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
  4. 2022Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrievalcited by 34
  5. 2021Skip-Convolutions for Efficient Video Processingcited by 32
  6. 2022MAR: Masked Autoencoders for Efficient Action Recognitioncited by 29
  7. 2021Coarse-Fine Networks for Temporal Activity Detection in Videoscited by 28
  8. 2021No frame left behind: Full Video Action Recognitioncited by 24
  9. 2023Text-Conditioned Resampler For Long Form Video Understandingcited by 24
  10. 2022OCSampler: Compressing Videos to One Clip with Single-step Samplingcited by 22
  11. 2021AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognitioncited by 21
  12. 2021Can An Image Classifier Suffice For Action Recognition?cited by 20
  13. 2022AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognitioncited by 18
  14. 2021EAN: Event Adaptive Network for Enhanced Action Recognitioncited by 16
  15. 2022Gate-Shift-Fuse for Video Action Recognitioncited by 15
  16. 2022NSNet: Non-saliency Suppression Sampler for Efficient Video Recognitioncited by 15
  17. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
  18. 2023Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformerscited by 13
  19. 2024LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognitioncited by 13
  20. 2021MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurationscited by 12
  21. 2023AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognitioncited by 10
  22. 2021Coarse-to-Fine Curriculum Learningcited by 9
  23. 2022ERA: Expert Retrieval and Assembly for Early Action Predictioncited by 9
  24. 2022Temporal Saliency Query Network for Efficient Video Recognitioncited by 9
  25. 2023System-status-aware Adaptive Network for Online Streaming Video Understandingcited by 9
  26. 2024Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognitioncited by 9
  27. 2022Rethinking Resolution in the Context of Efficient Video Recognitioncited by 8
  28. 2022A Visual Active Search Framework for Geospatial Explorationcited by 8
  29. 2023A Partially Supervised Reinforcement Learning Framework for Visual Active Searchcited by 8
  30. 2023Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understandingcited by 7
  31. 2022Look More but Care Less in Video Recognitioncited by 6
  32. 2021Event Neural Networkscited by 5
  33. 2025D'ej`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reusecited by 5
  34. 2026Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Languagecited by 5
  35. 2022ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention networkcited by 4
  36. 2023View while Moving: Efficient Video Recognition in Long-untrimmed Videoscited by 4
  37. 2023Audio-Visual Glance Network for Efficient Video Recognitioncited by 4
  38. 2021Modeling Temporal Concept Receptive Field Dynamically for Untrimmed Video Analysiscited by 3

50 most cited of 65 All 65 (JSON)