Fine-Grained Features for Image Captioning
Source abstract
Abstract
Image captioning involves two different major modalities (image and sentence) that convert a given image into a language that adheres to visual semantics. Almost all methods first extract image features to reduce the difficul... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Multimodal Machine Learning Applications · Domain Adaptation and Few-Shot Learning · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (42)
Show source-provided references
1. Show and tell: A neural image caption generator
2. Bottom-up and top-down attention for image captioning and visual question answering
3. Image segmentation and optimization techniques: A short overview
4. Attention is all you need
5. X-linear attention networks for image captioning
6. Two-stream convolutional networks for action recognition in videos
7. Microsoft coco: Common objects in context
8. Bleu: A method for automatic evaluation of machine translation
9. Meteor universal: Language specific translation evaluation for any target language
10. Rouge: A package for automatic evaluation of summaries
11. Cider: Consensus-based image description evaluation
12. Spice: Semantic propositional image caption evaluation
13. Panoptic feature pyramid networks
14. Hierarchy parsing for image captioning
15. Boosting image captioning with attributes
16. Knowing when to look: Adaptive attention via a visual sentinel for image captioning
17. Learning transferable visual models from natural language supervision
18. Visual genome: Connecting language and vision using crowdsourced dense image annotations10.1007/s11263-016-0981-7 ↗
19. In defense of grid features for visual question answering
20. RSTNet: Captioning with adaptive attention on visual and non-visual words
21. Dual-level collaborative transformer for image captioning
22. R. Mokady, A. Hertz and A. Bermano, “Clipcap: Clip prefix for image captioning,” 2021. [Online]. Available: https://arxiv.org/abs/2111.09734
23. A position-aware transformer for image captioning
24. N. Nejatishahidin, P. Fayyazsanavi and J. Kosecka, “Object pose estimation using mid-level visual representations,” 2022. [Online]. Available: https://arxiv.org/abs/2203.0144910.1109/IROS47612.2022.9981452 ↗
25. Hierarchical attention network for image captioning
26. BERT: Pre-training of deep bidirectional transformers for language understanding
27. Transformer-XL: Attentive language models beyond a fixed-length context
28. Attention on attention for image captioning
29. Normalized and geometry-aware self-attention network for image captioning
30. Meshed-memory transformer for image captioning
31. Unified vision-language pre-training for image captioning and vqa
32. Efficient image captioning based on vision transformer models10.32604/cmc.2022.029313 ↗
33. Panoptic segmentation
34. Mask r-cnn
35. Fully convolutional networks for semantic segmentation
36. Deep visual-semantic alignments for generating image descriptions
37. Scheduled sampling for sequence prediction with recurrent neural networks
38. Self-critical sequence training for image captioning
39. Recurrent fusion network for image captioning
40. Exploring visual relationship for image captioning
41. Look back and predict forward in image captioning
42. Auto-encoding scene graphs for image captioning