{"id":14184,"date":"2024-03-02T14:46:40","date_gmt":"2024-03-02T14:46:40","guid":{"rendered":"https:\/\/www.writemyessays.app\/blog\/questions\/ai-generated-alternative-text-suggestions-for-images-in-moodle-enhancing-web-accessibility-for-visually-impaired-users\/"},"modified":"2024-03-02T14:46:40","modified_gmt":"2024-03-02T14:46:40","slug":"ai-generated-alternative-text-suggestions-for-images-in-moodle-enhancing-web-accessibility-for-visually-impaired-users","status":"publish","type":"questions","link":"https:\/\/www.writemyessays.app\/blog\/questions\/ai-generated-alternative-text-suggestions-for-images-in-moodle-enhancing-web-accessibility-for-visually-impaired-users\/","title":{"rendered":"AI-Generated Alternative Text Suggestions for Images in Moodle: Enhancing Web Accessibility for Visually Impaired Users"},"content":{"rendered":"<p><span style=\"cursor: auto; color: inherit;\">The enclosed documents pertain to the proposal and the desired structure of the thesis, which focuses on developing a plugin for the Moodle forum system that utilizes a large language model. This Thesis focuses on comparing newest pretrained Image to Text Models<\/span><\/p>\n<div>\n<ul>\n<li><span style=\"cursor: auto; color: inherit;\"><a style=\"font-variant-ligatures: inherit; font-variant-caps: inherit; margin-top: 1.25em; margin-bottom: 1.25em; cursor: auto;\">UForm (unum-cloud)<\/a><\/span><\/li>\n<li><span style=\"cursor: auto; color: inherit;\"><span style=\"color: inherit; background-color: var(--color-6); font-variant-ligatures: inherit; font-variant-caps: inherit;\">InstructBLIP-Vicuna13B<\/span><\/span><\/li>\n<li><span style=\"cursor: auto; color: inherit;\"><span style=\"color: inherit; background-color: var(--color-6); font-variant-ligatures: inherit; font-variant-caps: inherit;\">CLIP-Interrogator<\/span><\/span><\/li>\n<li><span style=\"cursor: auto; color: inherit;\"><span style=\"color: inherit; background-color: var(--color-6); font-variant-ligatures: inherit; font-variant-caps: inherit;\">Img2Prompt<\/span><\/span><\/li>\n<li><span style=\"cursor: auto; color: inherit;\"><span style=\"color: inherit; background-color: var(--color-6); font-variant-ligatures: inherit; font-variant-caps: inherit;\">LLaMA-13B<\/span><\/span><\/li>\n<li><span style=\"cursor: auto; color: inherit;\"><span style=\"color: inherit; background-color: var(--color-6); font-variant-ligatures: inherit; font-variant-caps: inherit;\">LLaMA-7B<\/span><\/span><\/li>\n<li><span style=\"cursor: auto; color: inherit;\"><span style=\"color: inherit; background-color: var(--color-6); font-variant-ligatures: inherit; font-variant-caps: inherit;\">BLIP-2<\/span><\/span><\/li>\n<li><span style=\"cursor: auto; color: inherit;\"><span style=\"color: inherit; background-color: var(--color-6); font-variant-ligatures: inherit; font-variant-caps: inherit;\">OpenAI GPT-4-Vision-Preview<\/span><\/span><\/li>\n<\/ul>\n<div>Some of the&nbsp;<span style=\"background-color: var(--color-6); color: inherit; font-variant-ligatures: inherit; font-variant-caps: inherit; font-weight: 600;\">E<\/span><span style=\"background-color: var(--color-6); color: inherit; font-variant-ligatures: inherit; font-variant-caps: inherit;\">valuation Metrics could be&nbsp;<\/span><\/div>\n<\/div>\n<div>\n<ul style=\"margin: 1.25em 0px; cursor: auto; color: inherit;\">\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">SQA (Semantic Quality Assessment)<\/li>\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">MME (Multimodal Embedding Evaluation)<\/li>\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">MMBench (Multimodal Benchmarking)<\/li>\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">Average Size (of the model)<\/li>\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">Caption Length (generated text length)<\/li>\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">CLIPScore (for measuring the relevance of the generated text to the image)<\/li>\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">RefCLIPScore (reference-based CLIPScore for contextual accuracy)<\/li>\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">VQAv2 (Visual Question Answering version 2 performance)<\/li>\n<li style=\"padding-left: 0.375em; cursor: auto; color: inherit;\">Token Speed (generation speed measured in tokens per second)<\/li>\n<\/ul>\n<div>The Thesis requirses a working Plugin for Moodle Image to Text writen in Php\/Javascript to generate Alternative Text in the Field &#8220;<span style=\"color: inherit; font-size: 14px; background-color: var(--color-6); font-variant-ligatures: inherit; font-variant-caps: inherit;\">image_altentry&#8221; for Atto and TinyMCE<\/span><\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>The enclosed documents pertain to the proposal and the desired structure of the thesis, which focuses on developing a plugin for the Moodle forum system that utilizes a large language model. This Thesis focuses on comparing newest pretrained Image to Text Models UForm (unum-cloud) InstructBLIP-Vicuna13B CLIP-Interrogator Img2Prompt LLaMA-13B LLaMA-7B BLIP-2 OpenAI GPT-4-Vision-Preview Some of the&nbsp;Evaluation [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"closed","template":"","meta":[],"disciplines":[63],"paper_types":[],"tagged":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/questions\/14184"}],"collection":[{"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/questions"}],"about":[{"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/types\/questions"}],"author":[{"embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/comments?post=14184"}],"version-history":[{"count":0,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/questions\/14184\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/media?parent=14184"}],"wp:term":[{"taxonomy":"disciplines","embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/disciplines?post=14184"},{"taxonomy":"paper_types","embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/paper_types?post=14184"},{"taxonomy":"tagged","embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/tagged?post=14184"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}