ACSF-ED: Adaptive Cross-Scale Fusion Encoder-Decoder for Spatio-Temporal Action Detection
Source abstract
Abstract
Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Human Pose and Action Recognition · Anomaly Detection Techniques and Applications · Gait Recognition and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (53)
Show source-provided references
1. Abnormal detection of worker by interaction analysis of accident-causing objects
2. Action recognition system for security monitoring
3. Improved spatio-temporal action localization for surveillance videos
4. A constructive review on pedestrian action detection, recognition and prediction
5. Video-based driver action recognition via spatial-temporal and motion deep learning
6. Slowfast networks for video recognition
7. TubeR: Tubelet transformer for video action detection
8. O. Kopuklu, X. Wei, and G. Rigoll, “You only watch once: A unified CNN architecture for real-time spatiotemporal action localization,” 2019, arXiv:1911.06644.
9. Tube convolutional neural network (T-CNN) for action detection in videos
10. Action tubelet detector for spatio-temporal action localization
11. SSD: Single shot multibox detector
12. STEP: Spatio-temporal progressive learning for video action detection
13. Actions as moving points
14. Spatio-temporal action detector with self-attention
15. VideocapsuleNet: A simplified network for action detection
16. TACNet: Transition-aware context network for spatio-temporal action detection
17. Finding action tubes
18. Deep learning for detecting multiple space-time action tubes in videos
19. Multi-region two-stream R-CNN for action detection
20. Spatio-temporal action detection with cascade proposal and location anticipation
21. AVA: A video dataset of spatio-temporally localized atomic visual actions
22. Expanding architectures for efficient video recognition
23. Watch only once: An end-to-end video action detection framework
24. J. Yang and K. Dai, “YOWOv2: A stronger yet efficient multi-level detection framework for real-time spatio-temporal action detection,” 2023, arXiv:2302.06848.10.2139/ssrn.4485402 ↗
25. N. D. D. Manh, D. V. Hang, J. C. Wang, and B. D. Nhan, “YOWOv3: An efficient and generalized framework for human action detection and recognition,” 2024, arXiv:2408.02623.
26. Going deeper with convolutions
27. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
28. Pyramid scene parsing network
29. Feature pyramid networks for object detection
30. S. Liu, D. Huang, and Y. Wang, “Learning spatial fusion for single-shot object detection,” 2019, arXiv:1911.09516.
31. Rich feature hierarchies for accurate object detection and semantic segmentation
32. FCOS: Fully convolutional one-stage object detection
33. J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” 2018, arXiv:1804.02767.
34. A. Bochkovskiy, C. -Y. Wang, and H. -Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” 2020, arXiv:2004.10934.
35. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
36. C. Li et al., “YOLOv6 v3.0: A full-scale reloading,” 2023, arXiv:2301.05586.
37. Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, “YOLOX: Exceeding YOLO series in 2021,” 2021, arXiv:2107.08430.
38. Attention is all you need
39. End-to-end object detection with transformers
40. Dynamic anchor boxes are better queries for detr
41. DN-DETR: Accelerate DETR training by introducing query DeNoising10.1109/TPAMI.2023.3335410 ↗
42. DETRs beat YOLOs on real-time object detection
43. Deep-learning residual network based image analysis for an efficient two-stage recognition of neurological disorders
44. J. Lin, X. Mao, Y. Chen, L. Xu, Y. He and H. Xue, “D2ETR: Decoder-only DETR with computationally efficient cross-scale attention,” 2022, arXiv:2203.00860.
45. Aggregated residual transformations for deep neural networks
46. RepVGG: Making VGG-style ConvNets great again
47. Dual attention network for scene segmentation
48. DINO: DETR with improved denoising anchor boxes for end-to-end object detection
49. CAT: Cross attention in vision transformer
50. K. Soomro, A. Zamir, and M. J. A. Shah, “UCF101: A dataset of 101 human actions classes from videos in the wild,” 2012, arXiv:1212.0402.
51. Towards understanding action recognition
52. The pascal visual object classes (VOC) challenge10.1007/s11263-009-0275-4 ↗
53. CNN-based multiple path search for action tube detection in videos10.1109/TCSVT.2018.2887283 ↗