Causal Decoding for Hallucination-Resistant Multimodal Large Language Models
Shiwei Tan, Hengyi Wang, Weiyi Qin, Qi Xu, Zhigang Hua, Hao Wang
Action editor: Ali Etemad
https://openreview.net/forum?id=5Wb5c0FaCG
#captioning #multimodal #hallucination
CreatorCaps update: just shipped a small maintenance release focused on stability and a few refinements across the app to keep the caption editing workflow smooth.
If you create captions on iPhone or iPad, give it a try.
#IndieDev #BuildInPublic #iOS #Captioning
Anyone out there know what's up with #aegisub? It was abandoned for years, I was very happy to see development get picked up again last year sometime, but now the website just says "This deployment is temporarily paused". It's the tool I usually recommend for better subtitle editing, but it's […]
Efficient Few-Shot Continual Learning in Vision-Language Models
Aristeidis Panos, Rahaf Aljundi, Daniel Olmeda Reino, Richard E. Turner
Action editor: Soma Biswas
https://openreview.net/forum?id=sQ1w92WW0V
#visual #captioning #forgetting
Heydon with mohawk leaning over the back of a seat at SOTB 2023
Fireside chat (part 1) with @heydonworks.com
#a11y #captioning #AI #HTML #Norwich #Partridge
html5accessibility.com/stuff/2026/0...
Audio to file transcription #Transcription #AudioTranscription #Transcribe #TranscriptionServices #Freelance#Writing #Writing #Translation #Translators #RemoteWork #WorkFromHome #VirtualAssistant #ContentCreation #Captioning #AudioToText #Transcriber
cryptogig.com/job/writing-...
NBCUniversal is expanding accessibility features for the Milan Cortina 2026 Winter Olympics, including CC, more audio description, and improved digital access tools like screen reader support and keyboard navigation. Coverage begins Feb. 6. #AudioDescription #Captioning #WinterOlympics
Screenshot of a video transcription app displaying a video of two women sitting and talking. The transcription text reads, "So good morning everyone I figured I would take a minute to tell you how my Saturday actually went because a lot of you keep asking what my weekends look like when I am not." The app interface includes playback controls, editing options, and an export button. The devices shown are an iPad and an iPhone, both with status bars indicating time, battery, and connectivity.
CreatorCaps on iPad is taking shape.
Bigger canvas, same fast captioning workflow.
Still exploring whether this becomes a first-class release.
#indiedev #buildinpublic #captioning
Screenshot of a video editing application with a dark interface displaying a video preview and transcription. The video shows two people sitting and talking, with a play button overlay. The transcription on the right reads: "So good morning everyone I figured I would take a minute to tell you how my Saturday actually went because a lot of you keep asking what my weekends look like when I am not." The sidebar on the left includes options like "Import," "Projects," "Recent," and "Settings." At the bottom, there are editing tools for splitting, merging, deleting, positioning, styling, adjusting volume, and translating text. The date and time are shown at the top as "Tue Jan 6 12:59."
I’m actively building an iPad version of CreatorCaps.
Not sure I’ll ship it yet.
Would this fit your captioning workflow?
#indiedev #buildinpublic #captioning #creatortools
One of our users shared how they are using Zip Captions in a church setting. They are running Zip Captions into OBS and using our Companion plug in for the Streamdeck. The end result is seriously professional!
#worship #church #livevideo #videoengineering #videoproduction #captions #captioning
Dual Caption Preference Optimization for Diffusion Models
Amir Saeidi, Yiran Lawrence Luo, Agneet Chatterjee et al.
Action editor: Jia-Bin Huang
https://openreview.net/forum?id=ruZksIJBBd
#captioning #captions #caption
I will #transcribe your #audio or #video to #text and create SRT #subtitles #AudioTranscription #VideoTranscription #SRTSubtitles #TranscriptionService #Captioning #TextConversion #SubtitleCreation #ContentAccessibility #FastTranscription zeerk.com/job/writing-...
I do not like this at all, but par for the course with Meta.
www.404media.co/instagram-is-generating-...
#AI #Metadata #Captioning #SEO
Very happy that I finally got captioning working for my streams, but very disappointed in the quality of google's speech to text dictation software and wondering if there's a better alternative
#vtuber #indieVtuber #accessibility #captioning #captions
Wolf: Dense Video Captioning with a World Summarization Framework
Boyi Li, Ligeng Zhu, Ran Tian et al.
Action editor: Wei Liu
https://openreview.net/forum?id=Z1dH7hao7p
#captioning #captions #caption
i got captioning software (the video isnt done this was just so i could figure it out)
#stillstanding #voiceacting #captioning #hashtag
LLaVA-Video: Video Instruction Tuning With Synthetic Data
Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun MA, Ziwei Liu, Chunyuan Li
Action editor: Boqing Gong
https://openreview.net/forum?id=EElFGvt39K
#multimodal #captioning #benchmarks
Whenever an app has a way to make open captions, you should. I discuss it over on #TikTok.
#captioning #hardofhearing #disabledcreator
New #J2C Certification:
No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning
Manu Gaur, Darshan Singh S, Makarand Tapaswi
https://openreview.net/forum?id=gqh0yzPYdo
#captioners #captioning #captioner
For #deaf / hard of hearing people interested in improving access to live music at events, gigs, concerts.
The in-person event on 28th Oct has live captions & BSL.
#deaf #captioning #livemusic #musicevents #accessibility #subtitles
Captioning matters! Ken Nakata shows how to make your Vimeo videos accessible for everyone. Quick, practical, and essential.
convergeaccessibility.com/2025/09/22/c...
#DigitalAccessibility #A11y #InclusiveDesign #VideoAccessibility #Captioning #UX #Vimeo
Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transfera...
Atharv Mittal, Agam Pandey, Amritanshu Tiwari, Sukrit Jindal, Swadesh Swain
Action editor: Dit-Yan Yeung
https://openreview.net/forum?id=5L90cl0xtf
#adversarial #attention #captioning
Captioning-Enhanced Visual Lifelog Retrieval Improves Memory Recall
The CIVIL Retrieval System adds captions to lifelog images, enabling natural-language queries to retrieve moments; tests show it beats traditional visual-embedding methods. getnews.me/captioning-enhanced-visu... #lifelog #captioning
That includes accurate #captioning and #AltText in the descriptions so that if someone is visually impaired and listening, they aren't missing out on that aspect entirely.
Also especially important when I'm using a warning scroll that I didn't record audio for. Like in the coming episode.
VidBridge-R1 Unites Video QA and Captioning with New Proxy Tasks
VidBridge‑R1 unites video QA and captioning with two proxy tasks—DarkEventInfer (infers masked events) and MixVidQA (isolates clip)—boosting benchmark performance. Read more: getnews.me/vidbridge-r1-unites-vide... #vidbridger1 #videoqa #captioning
Jacob sits and speaks behind a wall of acoustic panels. A label reads "Accessibility Producer".
Our very own @jacobstar.me is back doing a small round of shorts this week on TikTok and YouTube. This first one goes into why his job title is Accessibility Producer. #captioning #a11y
youtube.com/shorts/8B0dG...
www.tiktok.com/@jacobstarno...
Poster for a paper session titled “Unlocking Audiovisual Media for All: How AI-Generated Subtitles Enhance Audience Engagement and Emotional Connection” at the Conference on Disability, Accessibility and Representation in the Creative Industries. DARCI. The session presents findings from a pilot study on emotionally tuned subtitles created with AI to improve accessibility and emotional resonance for hearing and d/Deaf audiences. Scheduled for 11th September at the University of York. Led by Grzegorz Kata, Monika Zabrocka, and Wiesław Poleszak. Logos for DARCI, University of York, EAD project, and the Arts and Humanities Research Council appear at the bottom. The design features coloured swirls in the corners.
Moving to the realm of subtitling, Grzegorz Kata, Monika
Zabrocka & Wiesław Poleszak will be discussing AI-generated emotional subtitles #Subtitling #Captioning
Once more, with #captions!
Trying to work on making things more accessible in general, even if alt text for videos hasn’t been working.
What (free) apps do y’all use to add captions to your videos? 🤔
#weather #colorado #skyscape #cloudscape #summerskies #sunshine #captioning #accessibility #sky
🎧 Sound is not enough!
Discover how deafness awareness, accessibility, and smart communication can grow your audience and impact. 🌍
Read more on LinkedIn: www.linkedin.com/posts/activi...
#business #Accessibility #InclusiveDesign #Captioning #communication
