mlsanityData to 7 Oct 2026

ConvNet Architecture Search for Spatiotemporal Feature Learning

arXiv 1708.05038 ↗First posted 16 Aug 2017cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Learning image representations with ConvNets by pre-training on ImageNet has proven useful across many visual understanding tasks including object detection, semantic segmentation, and image captioning. Although any image representation can be applied to video frames, a dedicated spatiotemporal representation is still vital in order to incorporate motion patterns that cannot be captured by appearance based models alone. This paper presents an empirical ConvNet architecture search for spatiotemporal feature learning, culminating in a deep 3-dimensional (3D) Residual ConvNet. Our proposed architecture outperforms C3D by a good margin on Sports-1M, UCF101, HMDB51, THUMOS14, and ASLAN while being 2 times faster at inference time, 2 times smaller in model size, and having a more compact representation.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 10; 2023: 7; 2024: 11; 2025: 2.

40 papers.

Sort:

By area:

  1. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  2. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 106
  3. 2021FrameExit: Conditional Early Exiting for Efficient Video Recognitioncited by 59
  4. 2021MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognitioncited by 44
  5. 2024Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectivescited by 37
  6. 2021DCAN: Improving Temporal Action Detection via Dual Context Aggregationcited by 36
  7. 2021Aligning Correlation Information for Domain Adaptation in Action Recognitioncited by 30
  8. 2021Coarse-Fine Networks for Temporal Activity Detection in Videoscited by 28
  9. 2022BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detectioncited by 28
  10. 2021Learning from Temporal Gradient for Semi-supervised Action Recognitioncited by 26
  11. 2021Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognitioncited by 23
  12. 2023Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognitioncited by 17
28 more
  1. 2021SVIP: Sequence VerIfication for Procedures in Videoscited by 16
  2. 2022GL-RG: Global-Local Representation Granularity for Video Captioningcited by 16
  3. 2022End-to-End Compressed Video Representation Learning for Generic Event Boundary Detectioncited by 15
  4. 2023Deep Learning for Video-Text Retrieval: a Reviewcited by 15
  5. 2022Deep Unsupervised Key Frame Extraction for Efficient Video Classificationcited by 14
  6. 2024Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithmscited by 11
  7. 2022Hierarchical Compositional Representations for Few-shot Action Recognitioncited by 10
  8. 2024EZSR: Event-based Zero-Shot Recognitioncited by 8
  9. 2024A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalitiescited by 8
  10. 2022Lane Change Classification and Prediction with Action Recognition Networkscited by 3
  11. 2023Local Compressed Video Stream Learning for Generic Event Boundary Detectioncited by 3
  12. 2024Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognitioncited by 3
  13. 2024ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognitioncited by 3
  14. 2025DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detectioncited by 3
  15. 2023F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learningcited by 2
  16. 2021Efficient Spatialtemporal Context Modeling for Action Recognitioncited by 1
  17. 2022Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Samplingcited by 1
  18. 2022Adversarial Domain Adaptation for Action Recognition Around the Clockcited by 1
  19. 2022Deep set conditioned latent representations for action recognitioncited by 1
  20. 2023P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classificationcited by 1
  21. 2024TM-PATHVQA:90000+ Textless Multilingual Questions for Medical Visual Question Answeringcited by 1
  22. 2021Channel-Temporal Attention for First-Person Video Domain Adaptationcited by 0
  23. 2022SDFE-LV: A Large-Scale, Multi-Source, and Unconstrained Database for Spotting Dynamic Facial Expressions in Long Videoscited by 0
  24. 2023Texture-Based Input Feature Selection for Action Recognitioncited by 0
  25. 2023CNNs for JPEGs: A Study in Computational Costcited by 0
  26. 2024A multimodal gesture recognition dataset for desktop human-computer interactioncited by 0
  27. 2024Is 3D Convolution with 5D Tensors Really Necessary for Video Analysis?cited by 0
  28. 2025Multi-modal and Multi-view Fundus Image Fusion for Retinopathy Diagnosis via Multi-scale Cross-attention and Shifted Window Self-attentioncited by 0