Abnormal Action Detection Based on Parameter-Efficient Transfer Learning in Laboratory Scenarios
Source abstract
Abstract
Laboratory safety is a critical area of broad societal concern, particularly in the detection of abnormal actions. To enhance the efficiency and accuracy of detecting such actions, this paper introduces a novel method called ... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Human Pose and Action Recognition · Gait Recognition and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (43)
Show source-provided references
1. Parameter-efficient transfer learning for NLP
2. On space-time interest points10.1007/s11263-005-1838-7 ↗
3. Explicit modeling of human-object interactions in realistic videos10.1109/TPAMI.2012.175 ↗
4. Prime: Privacy-preserving video anomaly detection via motion exemplar guidance10.1016/j.knosys.2023.110872 ↗
5. DeepSegmenter: Temporal action localization for detecting anomalies in untrimmed naturalistic driving videos
6. Prompt-guided zero-shot anomaly action recognition using pretrained deep skeleton features
7. Attention-based residual autoencoder for video anomaly detection10.1007/s10489-022-03613-1 ↗
8. Finding action tubes
9. Rich feature hierarchies for accurate object detection and semantic segmentation
10. Faster R-CNN: Towards real-time object detection with region proposal networks
11. Deep learning for detecting multiple space-time action tubes in videos
12. Tube convolutional neural network (T-CNN) for action detection in videos
13. AVA: A video dataset of spatio-temporally localized atomic visual actions
14. SlowFast networks for video recognition
15. Actor-context-actor relation network for spatio-temporal action localization
16. Prototype contrastive learning for point-supervised temporal action detection
17. Attention is all you need
18. An image is worth 16x16 words: Transformers for image recognition at scale
19. End-to-end object detection with transformers
20. TubeR: Tubelet transformer for video action detection
21. Y. Xin et al., “Parameter-efficient fine-tuning for pre-trained vision models: A survey,” arXiv preprint arXiv:2402.02242, 2024.
22. AdaptFormer: Adapting vision transformers for scalable visual recognition
23. AIM: Adapting image models for efficient video action recognition
24. D. Yin, L. H. B. Li, and Y. Zhang, “Adapter is all you need for tuning visual tasks,” arXiv preprint arXiv:2311.15010, 2023.
25. S. Jie and Z. Deng, “Convolutional bypasses are better vision transformer adapters,” arXiv preprint arXiv:2207.07039, 2022.
26. Prefix-tuning: Optimizing continuous prompts for generation
27. C. Xu, S. Yang, Y. Wang, Z. Wang, Y. Fu and X. Xue, “Exploring efficient few-shot adaptation for vision transformers,” arXiv preprint arXiv:2301.02419, 2023.
28. A unified continual learning framework with general parameter-efficient tuning
29. The power of scale for parameter-efficient prompt tuning
30. Do better ImageNet models transfer better?
31. Low-rank adaptation of large language models
32. Prompting and adapter tuning for self-supervised encoder-decoder speech model
33. Compacter: Efficient low-rank hypercomplex adapter layers
34. B. X. Yu, J. Chang, L. Liu, Q. Tian, and C. W. Chen, “Towards a unified view on visual parameter-efficient transfer learning,” arXiv preprint arXiv:2210.00788, 2022.
35. Visual query tuning: Towards effective usage of intermediate representations for parameter and memory efficient transfer learning
36. D. Chen, “Aggregate, decompose, and fine-tune: A simple yet effective factor-tuning method for vision transformer,” arXiv preprint arXiv:2311.06749, 2023.
37. Visual prompt tuning
38. S. An et al., “Input-tuning: Adapting unfamiliar inputs to frozen pretrained models,” arXiv preprint arXiv:2203.03131, 2022.
39. Video classification with channel-separated convolutional networks
40. End-to-end object detection with adaptive clustering transformer
41. Towards a unified view of parameter-efficient transfer learning
42. Actor-centric relation network
43. VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training