Event-Driven Attention Network: A Cross-Modal Framework for Efficient Image-Text Retrieval in Mass Gathering Events
Source abstract
Abstract
Research on mass gathering events is critical for ensuring public security and maintaining social order. However, most of the existing works focus on crowd behavior analysis areas such as anomaly detection and crowd counting,... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques · Multimodal Machine Learning Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (55)
Show source-provided references
1. Varghese · Intelligent image and video analytics · 2023 · 5710.1201/9781003053262-3 ↗
2. Deep-cascade: cascading 3D deep neurnetworks for fast anomaly detection and localization in crowded scenes10.1109/TIP.2017.2670780 ↗
3. Spatial-temporal convolutional neural networks for anomaly detection and localization in crowded scenes
4. Violent crowd flow detection using deep learning
5. Single-image crowd counting via multi-column convolutional neural network
6. Context-aware crowd counting
7. CSRNet: dilated convolutional neural networks for understanding the highly congested scenes
8. To choose or to fuse? Scale selection for crowd counting
9. Video anomaly detection with sparse coding inspired deep neural networks10.1109/TPAMI.2019.2944377 ↗
10. NM-GAN: noisemodulated generative adversarial network for video anomaly detection10.1016/j.patcog.2021.107969 ↗
11. Training adversarial discriminators for cross-channel abnormal event detection in crowds
12. Simple online and realtime tracking
13. Simple online and realtime tracking with a deep association metric
14. Towards real-time multiobject tracking
15. Deep-learning-enhanced multitarget detection for end-edge–cloud surveillance in smart IoT10.1109/JIOT.2021.3077449 ↗
16. The BEHAVE video dataset: ground truthed video for multi-person behavior classification
17. Real-world anomaly detection in surveillance videos
18. Crowd descriptors and interpretable gathering understanding10.1109/TMM.2024.3381040 ↗
19. Learning cross-modal contrastive features for zero-shot action recognition and localization
20. VSE++: improving visual-semantic embeddings with hard negatives
21. Deep visual-semantic alignments for generating image descriptions
22. Lee · Computer vision-ECCV 2018 · 2018 · 21210.1007/978-3-030-01225-0_13 ↗
23. Efficient token-guided image-text retrieval with consistent multimodal contrastive training10.1109/TIP.2023.3286710 ↗
24. Learning relationship-enhanced semantic graph for fine-grained image-text matching10.1109/TCYB.2022.3179020 ↗
25. Learning deep event models for crowd anomaly detection10.1016/j.neucom.2016.09.063 ↗
26. PCANet: a simple deep learning baseline for image classification?10.1109/TIP.2015.2475625 ↗
27. An efficient deep neural model for detecting crowd anomalies in videos10.1007/s10489-022-04233-5 ↗
28. Where are they going? Predicting human behaviors in crowded scenes
29. A new approach for social group detection based on spatio-temporal interpersonal distance measurement10.1016/j.heliyon.2022.e11038 ↗
30. Generative adversarial network based abnormal behavior detection in massive crowd videos: a Hajj case study10.1007/s12652-021-03323-5 ↗
31. DeViSE: a deep visual-semantic embedding model
32. Bottom-up and top-down attention for image captioning and visual question answering
33. SAM: cross-modal semantic alignments module for image-text retrieval10.1007/s11042-023-15798-9 ↗
34. Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models10.1007/s11263-016-0965-7 ↗
35. Lin · Computer vision-ECCV 2014 · 2014 · 74010.1007/978-3-319-10602-1_48 ↗
36. Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning
37. Faster R-CNN: towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
38. Visual genome: connecting language and vision using crowdsourced dense image annotations10.1007/s11263-016-0981-7 ↗
39. Bert: pre-training of deep bidirectional transformers for language understanding
40. Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. arXiv:1301.3781. 2013.
41. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. arXiv:1706.03762. 2017.
42. Triplet online instance matching loss for person re-identification10.1016/j.neucom.2020.12.018 ↗
43. BLIP: bootstrap** language-image pre-training for unified vision-language understanding and generation
44. Brown T, Mann B, Ryde NR, Subbiah M, Kaplan J, Dhariwal P, et al. Language models are few-shot learners. arxiv:2005.14165. 2020.
45. Multi-modality cross attention network for image and sentence matching
46. Class rectification hard mining for imbalanced deep learning
47. Luo G, Darrell T, Rohrbach A. NewsCLIPpings: Automatic generation of out-of-context multimodal media. arXiv:2104.05893. 2021.10.18653/v1/2021.emnlp-main.545 ↗
48. Visualizing data using t-SNE
49. Matching images and text with multi-modal tensor fusion and re-ranking
50. Learning the best pooling strategy for visual semantic embedding
51. Negative-aware attention framework for image-text matching
52. Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders10.1145/3451390 ↗
53. Similarity reasoning and filtration for image-text matching
54. Cross-modal graph matching network for image-text retrieval10.1145/3499027 ↗
55. Cross-modal semantic enhanced interaction for image-sentence retrieval