过去一年中添加的文章，按日期排序
Semantic Enhancements in Image Captioning: Leveraging Neural Networks to Improve BLIP and GPT-2
SK Srivastava - 2024 - nmbu.brage.unit.no
8 天前 - … captions and their potential biases across different image … that produce captions
more akin to humangenerated text, … and set a new benchmark in automated image captioning. …
more akin to humangenerated text, … and set a new benchmark in automated image captioning. …
Surgical Text-to-Image Generation
C Innocent Nwoye, R Bose, K Elgohary… - arXiv e …, 2024 - ui.adsabs.harvard.edu
47 天前 - … between long and triplet-based captions, supporting the use of … text-to-image
models on triplet-based captions without additional input signals by uncovering that triplet text …
models on triplet-based captions without additional input signals by uncovering that triplet text …
Surgical Text-to-Image Generation
CI Nwoye, R Bose, K Elgohary, L Arboit… - arXiv preprint arXiv …, 2024 - arxiv.org
52 天前 - … between long and tripletbased captions, supporting the use of triplet… text-to-image
models on triplet-based captions without additional input signals by uncovering that triplet text …
models on triplet-based captions without additional input signals by uncovering that triplet text …
Symbol builder for autocreation of images for alternative and augmentative communication
EA Draffan, D Banes, C Ding - … on Computers Helping People with Special …, 2024 - Springer
59 天前 - … to feed the image-to-text model (Microsoft Kosmos-2) in order to generate image
captions (visual … Team members assessed the quality of auto-generated captions and provided …
captions (visual … Team members assessed the quality of auto-generated captions and provided …
Accessibility of COVID-19-related Public Websites in Japan
E Furukawa, T Okuhara, H Okada… - American Journal of …, 2024 - Taylor & Francis
104 天前 - … COVID-19 information must be presented along with clear contrasts, alternative
text, and informative captions so that users can perceive it appropriately. Public health officials …
text, and informative captions so that users can perceive it appropriately. Public health officials …
EmoScribe Camera: A Virtual Camera System to Enliven Online Conferencing with Automatically Generated Emotional Text Captions
A Hautasaari, M Aramaki, R Chujo… - Extended Abstracts of the …, 2024 - dl.acm.org
113 天前 - … a virtual camera system that generates images of automatic text captions in real time
and … efficacy of EmoScribe Camera as an alternative communication channel during online …
and … efficacy of EmoScribe Camera as an alternative communication channel during online …
What's that you say? Capturing class content through captioning
L Stvan - The Journal for Research and Practice in College …, 2024 - journals.uc.edu
200 天前 - … alt text for images. And keeping content accessible can also mean not triggering or
tripping up students with anxiety, time management difficulties, dyslexia, PTSD, or autism. Or …
tripping up students with anxiety, time management difficulties, dyslexia, PTSD, or autism. Or …
Transforming Remote Sensing Imagery into Descriptive Text
RSP Balla, T Anuradha, YS Tummala… - … on Advances in …, 2024 - ieeexplore.ieee.org
235 天前 - … In order to generate region proposals and broad features for image captioning, [18]
combined attention mechanisms using CNN and Faster R-CNN [14]. The relationship …
combined attention mechanisms using CNN and Faster R-CNN [14]. The relationship …
A picture is worth a thousand words: Principled recaptioning improves image generation
312 天前 - … of (image, caption) pairs where the images often come from the web, and the captions
are their HTML alternate text. A … Image captioning is a fundamental problem in computer …
are their HTML alternate text. A … Image captioning is a fundamental problem in computer …