Tootfinder

Ring rolls out Video Descriptions, an AI-powered beta feature that generates text summaries of motion activity from its doorbells and cameras (Jennifer Pattison Tuohy/The Verge)
https://www.theverge.com/news/692523/ring-ai-powe…

Ring camera alerts are about to get a lot smarter
Ring’s new Video Descriptions feature will tell you what your video doorbell or security camera sees, so you don’t have to watch the video.

Amazon says Prime Video in India caters to "subscription-ready" customers while Amazon MX Player is aimed at those transitioning from traditional media (Naman Ramachandran/Variety)
https://variety.com/2025/tv/news/amazon-india-st…

Amazon Preps Sets India Streaming Push With Prime Video, MX Player
Amazon targets India's diverse streaming market with Prime Video for premium subscribers and MX Player for mobile users.

Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization
Zhiwang Zhang, Dong Xu, Wanli Ouyang, Chuanqi Tan
https://arxiv.org/abs/2506.20567

Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization
In this work, we propose a division-and-summarization (DaS) framework for dense video captioning. After partitioning each untrimmed long video as multiple event proposals, where each event proposal consists of a set of short video segments, we extract visual feature (e.g., C3D feature) from each segment and use the existing image/video captioning approach to generate one sentence description for this segment. Considering that the generated sentences contain rich semantic descriptions about the …

Walging, walging en nog eens walging, dat roepen deze beelden bij mij op.
https://www.rtl.nl/nieuws/video/c275b611-c

Kijk terug: de opmerkelijkste momenten van de NAVO-top
Nu de NAVO-top afgelopen is, zetten we de belangrijkste momenten nog even voor je op een rijtje. Trump is blij met het akkoord van de NAVO-lidstaten om de defensie-uitgaven te verhogen; Zelensky ontvangt een staande ovatie van de Tweede Kamer, en Trump gaat op de foto met Willem-Alexander en Máxima.

How #Vietnam bets on serving the #Trump organization. Despicable, including land evictions—not particularly a thing the Vietnamese people fancy.

Video: Inside a Trump Family Project in Vietnam
As President Trump blurs the lines between politics and business — and threatens steep tariffs on trade partners — governments feel compelled to favor Trump-related projects. Damien Cave, Vietnam bureau chief for The New York Times, and Katrin Bennhold, a senior writer on the international desk, discuss how this dynamic has played out in Vietnam, at the groundbreaking of a fast-tracked $1.5 billion Trump golf complex.

Der Alte: Existenz (S46/E04) - 2024 - #ZDF #ARD
https://www.ardm…

We did a little promo video about the album for our Kickstarter campaign back then, and I think it’s pretty charming. The Kickstarter campaign is long since closed, but you can see see the video if you want to see the artists and get a little behind the scenes action:
https://www.kickstarter.com/projects/paul/the-river-inside-of-trees/

„Da die Münchner Burgkmairstraße recht eng ist, parken viele Autofahrer mit zwei Rädern auf dem Gehweg. Das ist zwar nicht erlaubt, wurde aber jahrzehntelang geduldet. Bis vergangenen April. Seitdem zeigen zwei Passanten die Gehweg-Parker an.“ Gehweg-Parker anzeigen wirkt.

I wonder where Ireland’s regulator got this idea?
https://mastodon.neilzone.co.uk/@neil/114751272606146547

Videos expose racism over use of Israeli bomb shelters | Social Media | Al Jazeera
https://www.aljazeera.com/video/newsfeed/2025/6/25/videos-expose-racism-over-use-of-israeli-bomb-shelters?traffic_source=rss

TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness
Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas
https://arxiv.org/abs/2506.20588

TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness
The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods depend heavily either on supervised annotations or on attention-based models, which are computationally expensive and brittle in the face of distribution shifts that hinder cross-domain applicability across datasets. We introduce a pioneering self-supervised vid…

Netanyahu says „Free Palestine is just today's version of Heil Hitler” — on the same day it has just become illegal in Germany to ask “Have we learned nothing from the Holocaust?” in regards to Palestine, as German courts deemed it trivialization of the holocaust.

Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation
Jun Wang, Xijuan Zeng, Chunyu Qiang, Ruilong Chen, Shiyao Wang, Le Wang, Wangjing Zhou, Pengfei Cai, Jiahui Zhao, Nan Li, Zihan Li, Yuzhe Liang, Xiaopeng Wang, Haorui Zheng, Ming Wen, Kang Yin, Yiran Wang, Nan Li, Feng Deng, Liang Dong, Chen Zhang, Di Zhang, Kun Gai

Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation
We propose Kling-Foley, a large-scale multimodal Video-to-Audio generation model that synthesizes high-quality audio synchronized with video content. In Kling-Foley, we introduce multimodal diffusion transformers to model the interactions between video, audio, and text modalities, and combine it with a visual semantic representation module and an audio-visual synchronization module to enhance alignment capabilities. Specifically, these modules align video conditions with latent audio elements a…

Some podcasters say Spotify's Partner Program, through which they get a cut of Spotify's ad and premium subscription revenue, pays out more than YouTube (Alexander Lee/Digiday)
https://digiday.com/media/spotifys-vid

Spotify’s video podcast program draws praise from creators — and skepticism from networks
Six months into the Spotify Partner Program, creators and podcast networks are split on the opportunity, with ad monetization at the core.

Talking Heads Share New “Psycho Killer” Video Starring Saoirse Ronan https://pitchfork.com/news/talking-heads-share-new-psycho-killer-video-starring-saoirse-ronan-watch?utm_source=dlvr.it&…

Talking Heads Share New “Psycho Killer” Video Starring Saoirse Ronan: Watch
Mike Mills directs a video for the classic early single as the band celebrates its 50th anniversary

Beitrag vom #ZDF zu #Influencer n und #Freikirche n - Likes im Namen Gottes? Wie Influencer für Freikirchen werben.

A few notes on iPadOS 26 audio and video capture
https://sixcolors.com/post/2025/06/a-few-notes-on-ipados-26-audio-and-video-capture/

Say hello to The Fairphone (Gen.6)
Get ready for a new smartphone experience—modular, long-lasting, high-performance, distraction-free, and fairer than ever.
Launch video: https://www.youtube.com/watch?v=GpUkYw4i6Kk&t=2s
Guide tour video:

Time is On My Side: Dynamics of Talk-Time Sharing in Video-chat Conversations
Kaixiang Zhang, Justine Zhang, Cristian Danescu-Niculescu-Mizil
https://arxiv.org/abs/2506.20474

Time is On My Side: Dynamics of Talk-Time Sharing in Video-chat Conversations
An intrinsic aspect of every conversation is the way talk-time is shared between multiple speakers. Conversations can be balanced, with each speaker claiming a similar amount of talk-time, or imbalanced when one talks disproportionately. Such overall distributions are the consequence of continuous negotiations between the speakers throughout the conversation: who should be talking at every point in time, and for how long? In this work we introduce a computational framework for quantifying bot…

A quick video of our #cycling loop today. Enjoy!
https://loops.video/v/954LE8jJtK

Watch @hikingdude's loop on Loops.video
Just some cycling #c... • 0 likes • 0 comments

Buy this Patreon Exclusive video for just $3.00!
In this video, I look at some of the #AI slop on Redbubble.
https://www.patreon.com/posts/reacting-to-ai-132305260

Hightlights im Video - Inter löst Achtelfinal-Ticket als Gruppensieger #News #Nachrichten

Der #livestream der #rp25 im @… steht.

Weißt du, woher unser Show-Intro wirklich kommt? 👀
Lindworm lüftet das Geheimnis – und gibt exklusive Einblicke hinter die Kulissen von Traitor 🖤
👉 Jetzt die neue Folge von The Darkk Show auf YouTube schauen!
📺 https://youtu.be/EtHkNHh4osc

2016 Video RTBF-TIPIK : Ils ont grandi dans la secte OKC https://chardonsbleus.org/rtbf-tipik-ils-ont-grandi-dans-la-secte-okc/

Sydney Sprague - "Flat Circle" (Music Video)
#music

#captcha

Dallas Cowboys rookie wide receiver shares video of major life milestone https://www.si.com/nfl/cowboys/news/dallas-cowboys-rookie-wide-receiver-shares-video-major-life-milestone

Dense Video Captioning using Graph-based Sentence Summarization
Zhiwang Zhang, Dong Xu, Wanli Ouyang, Luping Zhou
https://arxiv.org/abs/2506.20583 https://…

Dense Video Captioning using Graph-based Sentence Summarization
Recently, dense video captioning has made attractive progress in detecting and captioning all events in a long untrimmed video. Despite promising results were achieved, most existing methods do not sufficiently explore the scene evolution within an event temporal proposal for captioning, and therefore perform less satisfactorily when the scenes and objects change over a relatively long proposal. To address this problem, we propose a graph-based partition-and-summarization (GPaS) framework for d…

Die Sendung mit der Maus vom 22.06.2025 erklärt anschaulich und trotzdem korrekt wie "KI" funktioniert. Das ist auch was für die eigenen Kinder!
https://www.

Die Sendung mit der Maus vom 22.06.2025 - hier anschauen
Lach- und Sachgeschichten, heute mit dem Geheimnis der Künstlichen Intelligenz, Trudes Tier und einer neuen Freundin, dem Lied vom KI-Mäleon, Shaun und einer wilden Scheunen-Party – und natürlich mit der Maus, dem Elefanten und der Ente. Aus einer Idee einen Text zu machen – das schafft eine Künstliche Intelligenz in Sekundenschnelle. Aber wie funktioniert das eigentlich? Ralph erklärt, warum eine KI viel mehr zählt, als sie schreibt. Denn erst durch das Zählen von Wörtern, Buchst…

Here's the Video for Our Sixth FOIA Forum: Massive Blue https://www.404media.co/heres-the-video-for-our-sixth-foia-forum-massive-blue/

Jag delade resultatet från en randomiserad studie för någon vecka sedan och fick då en fråga hur man kunde veta att resultatet inte bara berodde på att de som tränar är friskar från start.
Så jag gjorde en kort video som förklarar varför RCTs är kraftfullt för att avgöra vad som orsakar vad? https://www.

Launch of #Axiom4: https://x.com/SpaceX/status/1937805773402460315. Video clip from ESA: https://www.youtube.com/watch?v=-WTTcuGJE4o. Docking planned for 11:00 UTC Thursday: https://www.nasa.gov/blogs/spacestation/2025/06/25/ax-4-orbiting-toward-station-as-expedition-73-studies-pharma-blood-pressure/

Great closing keynote on 'rewilding' the internet by @… at the 2025 PublicSpaces conference. She talks about how a few fucked up right wing men think they own the internet, why they DON'T, and why the web is still ours and just needs (more) rewilding.

Watch: Raiders host all-star girls flag football showcase https://www.raiders.com/video/watch-raiders-host-all-star-inspire-flag-football-event-2025

Packed up my XBOX and large TV in the basement today :-(
I don't play video games every day, but 2 or 3 days a week, my daughter, who lives in Toronto, and I will play Halo online and defend the universe from Covenant forces. It's now 22 days until the moving trucks arrive, and planning for activities each day is underway. We have to allocate time for yard maintenance, packing, and cleaning. Accompanying music choices are important...
#MyPlaylist #RandomTune
https://youtu.be/t267aQJcwjs?si=jb8_X470NFFXY6Yp

EU-Gipfel mit Gesprächen über Unterstützung für Ukraine
Nur einen Tag nach dem Gipfeltreffen der NATO-Alliierten in Den Haag kommen am Vormittag die Staats- und Regierungschefs der 27 EU-Länder in Brüssel zusammen, um unter anderem über die weitere Unterstützung der Ukraine im Abwehrkampf gegen Russland zu beraten. Der ukrainische Präsident, Wolodymyr Selenskyj, wird per Video zugeschaltet.
🔗

Nahost, Rüstung, Ukraine: Premiere beim EU-Gipfel für Merz
Die Weltlage bestimmt die Agenda des heutigen Treffens der EU-Staats- und Regierungschefs: Es soll einmal mehr um den Nahen Osten und den Ukraine-Krieg gehen. Für Merz ist es der erste EU-Gipfel als Bundeskanzler.

We’re learning how to create and share MEDIA in our “Creating Cool Websites” summer camp! Today we are adding AUDIO with Vocaroo to our “Favorite Animals”
Google Sites, and starting our “City Travel webpage” project with Adobe Express!
https://lessons.wesfryer.com/courses/sum…

Lessons by Dr. Wesley Fryer (wesfryer.com) - Cool Websites
These are resources for "Creating Cool Websites," a June 23 - 27, 2025 summer camp led by Dr. Wes Fryer. SHARE A LINK! (Google Form) - View Our Links! Camp Structure (Daily Schedule - 9:00 AM to 12:00 PM) 9:00–9:15: Greeting & Introduction to Design Process / Today's Focus 9:15–10:00: Skill

#LEPROUS - Like A Sunken Ship
#nowplaying

LEPROUS - Like A Sunken Ship (OFFICIAL VIDEO) by InsideOutMusicTV
Listen now on your favorite streaming service. Powered by Songlink/Odesli, an on-demand, customizable smart link service to help you share songs, albums, podcasts and more.

Clothes from UK brands found discarded in Ghana wetland dumps – video https://www.theguardian.com/environment/video/2025/jun/18/clothes-from-uk-brands-found-discarded-in-ghana-wetland-dumps-video

Wo seid ihr alle? #loops https://loops.video/@hnnng

I am losing this battle, aren't I.

I'm back at DumbTube to look up Keyoxide tutorials and I can do something about it this time because this video is Creative Commons Attribution 3!
Only problem is I would need PeerTube I think unless I want to really trash the resolution...
12 Megabytes...ok...no, it's fine...
Mastodon accepted my upload!
https://www.

If you're like me, you play multiple episodes in a row in #Jellyfin for #Roku and you're not always sure what the episode you've moved into is about.
So I've added a new button to the OSD that gives you the media overview text - the same content displayed on the detail scre…

Videoreihe: NEIN zur Pipeline und JA zum Leben
(Quelle: https://deinebahn.com/2025/05/23/videoreihe-nein-zur-pipeline-und-ja-zum-leben/)
Im südmexikanischen Veracruz regt sich Widerstand gegen ein umstrittenes Gasförderungs- und Pipelineprojekt…

Bidder Feedback in First-Price Auctions for Video Advertising
S\'ebastien Lahaie, Benjamin Schaeffer, Yuanjun Zhou
https://arxiv.org/abs/2506.17058 htt…

Bidder Feedback in First-Price Auctions for Video Advertising
In first-price auctions for display advertising, exchanges typically communicate the "minimum-bid-to-win" to bidders after the auction as feedback for their bidding algorithms. For a winner, this is the second-highest bid, while for losing bidders it is the highest bid. In this paper we investigate the generalization of this concept to general combinatorial auctions, motivated by the domain of video advertising. In a video pod auction, ad slots during an advertising break in a video stream are …

Offenbar zu "cringe": Apple-Werbung für Studenten zurückgezogen
Der Comedian Martin Herlihy sollte Apple trendy für angehende Studenten machen. Ein Video wurde nun aber gleich wieder gelöscht.

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlases
Starck, Sideri-Lampretsa, Kainz, Menten, Mueller, Rueckert

AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models
Zehuan Huang, Haoran Feng, Yangtian Sun, Yuanchen Guo, Yanpei Cao, Lu Sheng
https://arxiv.org/abs/2506.19851

AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models
We present AnimaX, a feed-forward 3D animation framework that bridges the motion priors of video diffusion models with the controllable structure of skeleton-based animation. Traditional motion synthesis methods are either restricted to fixed skeletal topologies or require costly optimization in high-dimensional deformation spaces. In contrast, AnimaX effectively transfers video-based motion knowledge to the 3D domain, supporting diverse articulated meshes with arbitrary skeletons. Our method r…

Amazon soll Werbung bei Prime Video verdoppelt haben
Dreieinhalb Minuten pro Stunde: So viel Werbung zeigte Amazon bei Prime Video bislang. Doch mittlerweile ist offenbar fast doppelt so viel Werbung zu sehen.

Always pack the essentials!

Politics Joe puts its video podcasts behind a Patreon paywall, citing YouTube's revenue model limitations, and has 400 subscribers five days after launch (Matt Smith/Press Gazette)
https://pressgazette.co.uk/paywalls/politics-joe-puts-video-…

Politics Joe puts video podcast behind paywall
Politics Joe put its video podcasts behind a paywall, in part citing the limitations of Youtube’s revenue model.

Listen to Original by Cooper T. Watch the Fucking video, listen to the tune, by the merch. Fucking love these #Manchester #scally #fuckers on

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/4]:
- Controllable Video Generation with Provable Disentanglement
Shen, Zhu, Li, Xie, Tang, Deka, Liu, Chen, Zhang

Supercell makes Brawl Stars available on WeChat and says Clash Royale is "currently being developed" for a September launch on the WeChat mini-game platform (Coco Feng/South China Morning Post)
https://www.scmp.com/tech/article/3315…

Tencent-owned Supercell to launch titles like Clash Royale as WeChat mini games
The video game Brawl Stars is already available within WeChat, while Clash Royale will exclusively launch on the messaging app in September.

Trump's Risky Gamble on Attacking Iran (New York Times)
https://www.nytimes.com/video/us/politics/100000010243288/trumps-risky-gamble-on-attacking-iran.html?smid=bs-share
http://www.memeorandum.com/250623/p2#a250623p2

Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
Xingyang Li, Muyang Li, Tianle Cai, Haocheng Xi, Shuo Yang, Yujun Lin, Lvmin Zhang, Songlin Yang, Jinbo Hu, Kelly Peng, Maneesh Agrawala, Ion Stoica, Kurt Keutzer, Song Han
https://arxiv.org/abs/2506.19852…

Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training and inference on long videos prohibitively expensive. In this paper, we identify a phenomenon we term Spatiotemporal Energy Decay in video diffusion models: post-softmax attention scores diminish as spatial and temporal distance between tokens increase, akin to the physical decay of signal or waves over space and time …

Dit is hoe fijn Maxima een foto-op met Trump vindt.

V-CASS: Vision-context-aware Expressive Speech Synthesis for Enhancing User Understanding of Videos
Qixin Wang, Songtao Zhou, Zeyu Jin, Chenglin Guo, Shikun Sun, Xiaoyu Qin
https://arxiv.org/abs/2506.16716

V-CASS: Vision-context-aware Expressive Speech Synthesis for Enhancing User Understanding of Videos
Automatic video commentary systems are widely used on multimedia social media platforms to extract factual information about video content. However, current systems may overlook essential para-linguistic cues, including emotion and attitude, which are critical for fully conveying the meaning of visual content. The absence of these cues can limit user understanding or, in some cases, distort the video's original intent. Expressive speech effectively conveys these cues and enhances the user's com…

An ETSI GS QKD compliant TLS implementation
Thomas Pr\'evost (I3S), Bruno Martin (I3S), Olivier Alibart (INPHYNI)
https://arxiv.org/abs/2506.19409 http…

An ETSI GS QKD compliant TLS implementation
A modification of the TLS protocol is presented, using our implementation of the Quantum Key Distribution (QKD) standard ETSI GS QKD 014 v1.1.1. We rely on the Rustls library for this. The TLS protocol is modified while maintaining backward compatibility on the client and server side. We thus wish to participate in the effort to generalize the use of QKD on the Internet. We used our protocol for a video conference call encrypted by QKD. Finally, we analyze the performance of our protocol, compa…

Crows are still understandably cautious around our new video enabled bird feeder
/cc @…

Si vous avez vu le documenaire ARTE, Bouddhisme la Loi du Silence ou la video résumé de la chaîne Dissecte sur l'OKC, cela soulève pas mal de question, nous avons tenté d'y répondre avec une page dédiée sur notre site : https://chardonsbleus.org/faq

Shelby: Decentralized Storage Designed to Serve
Guy Goren, Andrew Hariri, Timothy D. R. Hartley, Ravi Kappiyoor, Alexander Spiegelman, David Zmick
https://arxiv.org/abs/2506.19233

Shelby: Decentralized Storage Designed to Serve
Existing decentralized storage protocols fall short of the service required by real-world applications. Their throughput, latency, cost-effectiveness, and availability are insufficient for demanding workloads such as video streaming, large-scale data analytics, or AI training. As a result, Web3 data-intensive applications are predominantly dependent on centralized infrastructure. Shelby is a high-performance decentralized storage protocol designed to meet demanding needs. It achieves fast, re…

'Watch Your... Mouth!': North Carolina White Man Fired After Video Shows Him Yelling At Black Female Cyclist During Profane-laced Rant While Wearing Work Shirt
https://atlantablackstar.com/2025/06/25/north-carolina-white-man-fired/

Enhancing Programming Pair Workshops: The Case of Teacher Pre-Prompting
Johan Petersson
https://arxiv.org/abs/2506.20299 https://arxi…

Enhancing Programming Pair Workshops: The Case of Teacher Pre-Prompting
This paper explores the pedagogical potential of "teacher pre-prompting" as a means of guiding student collaboration in programming education. In particular, we investigate how brief teacher-initiated questions posed before students engage in pair programming workshops can help shape problem interpretation and division of labor. Based on qualitative analysis of video data from a university course in systems development, we identify five distinct pre-prompting patterns. Our findings suggest that…

Jony and Sam are both suddenly real quiet; wonder how their honeymoon is going
Oh
https://pivot-to-ai.com/2025/06/23/iyo-vs-io-openai-and-jony-ive-get-sued/
*Nelson laugh*
h/t @…

Iyo vs. Io — OpenAI and Jony Ive get sued
In May, legendary Apple designer Jony Ive hooked up with OpenAI to announce an unspecified gadget. [WSJ, archive] To promote this complete vaporware, OpenAI released a video of Sam Altman and Ive b…

Meanwhile, in fascist shithole dollar-store country: “We will kill you”: Florida sheriff issues stern warning to protesters
https://edition.cnn.com/2025/06/13/us/video/florida-sheriff-warns-protesters-we-will-kill-you-digvid

‘We will kill you’: Florida sheriff issues stern warning to protesters | CNN
As protests over the Trump administration’s immigration raids continue in Los Angeles and other cities, Florida Attorney General James Uthmeier and law enforcement officials warned that demonstrators could face a forceful response in the state, CNN affiliate WESH reports.

Buddhism in English: Bad things happen to good people?
Video page:
https://www.youtube.com/watch?v=TOlsnhu5F5g
Episode webpage:

An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on Spotify
Shivam Verma, Vivian Chen, Darren Mei
https://arxiv.org/abs/2506.18735

An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on Spotify
Spotify, a large-scale multimedia platform, attracts over 675 million monthly active users who collectively consume millions of hours of music, podcasts, audiobooks, and video content. This diverse content consumption pattern introduces unique challenges for computational advertising, which must effectively integrate a variety of ad modalities, including audio, video, and display, within a single user experience. Traditional ad recommendation models, primarily designed for foregrounded experien…

Filme in der #ARD: Die Büffel sind los!
https://www.ardmediathek.de/video/filme-in

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robus...
Zhang, Zhang, Cheng, Wang, Wang, Zhang, Yang, Wu, Huang, Aviles-Rivero, Gao, Yang, Lally
…

Check out my new blog post: Better Video Audio with Auphonic
https://www.speedofcreativity.org/2025/05/18/better-video-audio-with-auphonic/
Featuring my new video: Spring Cleaning My RecTeq RT-700 Bull Smoker: Tips & Tricks!

Midjourney launches V1, its first AI video generation model, letting subscribers animate images via its website; video jobs will cost ~8x more than image jobs (Carl Franzen/VentureBeat)
https://venturebeat.com/business/surpa…

‘Surpassing all my expectations’: Midjourney releases first AI video model amid Disney, Universal lawsuit
For enterprise leaders evaluating AI, Midjourney Video V1's a double-edged sword: a low-cost, fast-evolving tool with strong user adoption

Time to give the human their morning pep talk

Waiting for my new #patreon exclusive video to render! I'm very excited to post it.
Stay Tuned at https://www.patreon.com/raysofred

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/3]:
- DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs
Bo-Cheng Chiu, Jen-Jee Chen, Yu-Chee Tseng, Feng-Chi Chen

Dallas Cowboys' LB DeMarvion Overshown video shares encouraging injury update https://www.si.com/nfl/cowboys/news/dallas-cowboys-demarvion-overshown-video-encouraging-injury-update

Docu : Les enfants oubliés
c'était la première fois qu'on parlait, qu'on exposait dans une extrême prudence et pudeur, ce qui nous étaient arrivés, nous, enfants né en Belgique ou France dans la OKC, oubliés de tous
https://chardonsbleus.org/video-les-en

Polizeiruf 110: Making-of: Spiel gegen den Ball - #rbb 2025
https://www.ardmediathek.de/video/Y3JpZDovL2Rhc2Vyc…

Video Perception Models for 3D Scene Synthesis
Rui Huang, Guangyao Zhai, Zuria Bauer, Marc Pollefeys, Federico Tombari, Leonidas Guibas, Gao Huang, Francis Engelmann
https://arxiv.org/abs/2506.20601

Video Perception Models for 3D Scene Synthesis
Traditionally, 3D scene synthesis requires expert knowledge and significant manual effort. Automating this process could greatly benefit fields such as architectural design, robotics simulation, virtual reality, and gaming. Recent approaches to 3D scene synthesis often rely on the commonsense reasoning of large language models (LLMs) or strong visual priors of modern image generation models. However, current LLMs demonstrate limited 3D spatial reasoning ability, which restricts their ability to…

Video-Streaming: Lob für Apples Datenschutzansatz beim Apple TV
Apples Multimediabox ist nicht günstig, hat aber laut einer Analyse einen entscheidenden Vorteil: Nutzer werden in ihrer Privatsphäre deutlich besser geschützt.

#NowPlaying the rad, weird new Tuff Guac tune and video 'I Want It Too' from their new album that comes out in October. Rafael can do no wrong, man 😂🔥
https://youtu.be/qG6ThZtq-a4?si=Y9WY0E

InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
Minsoo Kim, Kyuhong Shim, Jungwook Choi, Simyung Chang
https://arxiv.org/abs/2506.15745

InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
Modern multimodal large language models (MLLMs) can reason over hour-long video, yet their key-value (KV) cache grows linearly with time--quickly exceeding the fixed memory of phones, AR glasses, and edge robots. Prior compression schemes either assume the whole video and user query are available offline or must first build the full cache, so memory still scales with stream length. InfiniPot-V is the first training-free, query-agnostic framework that enforces a hard, length-independent memory c…

GenHSI: Controllable Generation of Human-Scene Interaction Videos
Zekun Li, Rui Zhou, Rahul Sajnani, Xiaoyan Cong, Daniel Ritchie, Srinath Sridhar
https://arxiv.org/abs/2506.19840

GenHSI: Controllable Generation of Human-Scene Interaction Videos
Large-scale pre-trained video diffusion models have exhibited remarkable capabilities in diverse video generation. However, existing solutions face several challenges in using these models to generate long movie-like videos with rich human-object interactions that include unrealistic human-scene interaction, lack of subject identity preservation, and require expensive training. We propose GenHSI, a training-free method for controllable generation of long human-scene interaction videos (HSI). Ta…

Dez Bryant has succinct response after efforts to crown son prematurely https://cowboyswire.usatoday.com/story/sports/nfl/cowboys/2025/06/23/dez-bryant-social-media-son-video-training/84317727007/

Der Alte - Ein Tag im Leben #zdf
https://www.zdf.de/video/serien/der-alte-106/ein-tag-im-leben-100 (58min)
2022
Voor wie nog op is ...
Enjoy!

Google rolls out the ability to upload videos in the Gemini app for both free and paid accounts across Android and iOS; the feature is not yet live on the web (Abner Li/9to5Google)
https://9to5google.com/2025/06/17/gemini-app-video-upload/

Gemini app rolling out video upload and analysis
Besides the new navigation drawer and 2.5 Pro going stable, the Gemini app is rolling out video upload and analysis. 

Fascinating early internet stories
I’m not an Apple fan boy but, in the midst of reading Apple in China, reading the story of this video and watching it is really something. https://open.substack.com/pub/scottknaster/p/how-the-lost-mac-intro-video-was…

How the “lost” Mac intro video was found in my living room
2005

Max, soon to be called HBO Max, says it is working on an AI tool that will identify "standout" scenes from its shows and movies to play as video previews (Emma Roth/The Verge)
https://www.theverge.com/news/688313/max-video-previews-autoplay-update…

Max will show autoplaying video previews picked by AI
Max is rolling out an update that will show video previews of shows and movies as you scroll over them. It will use an AI tool to help pick which scenes to feature.

Meta adds AI video editing tools to the Edits app and Meta AI, letting users edit up to 10 seconds of a video with 50 preset prompts, free for a "limited time" (Emma Roth/The Verge)
https://www.theverge.com/news/685581/meta-video-editing-ai-pre…

Meta’s new AI video tool can put you in a desert (or at least try to)
Meta is rolling out new AI video editing tools that lets you change the theme of your video, change the background, or even transform what you’re wearing.

Ahh. ... Elon did it again...
Video:
#SpaceX

[2025-06-25 Wed (UTC), 16 new articles found for eess.IV Image and Video Processing]
toXiv_bot_toot

[2025-06-26 Thu (UTC), 10 new articles found for eess.IV Image and Video Processing]
toXiv_bot_toot

Polizeiruf 110: Aquarius
https://www.ardmediathek.de/video/polizeiruf-110/aquarius/ndr/Y3JpZDovL25kci5kZS9wcm9wbGFuXzE5NjA5MjU1N19nYW56ZVNlbmR1bmc (87min)
Terug in de tijd naar 2010 ...
…

Amazon's Ad Video Generator, a free tool to create gen AI ads and depict items as they would be used in the real world, is now available for sellers in the US (Jess Weatherbed/The Verge)
https://www.theverge.com/news/685160/amazon-ads-…

Amazon is about to be flooded with AI-generated video ads
Amazon Ad’s Video Generator has some new tricks and is now generally available in the US to create “photorealistic video assets” in five minutes or less.

Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos
Yitong Quan, Benjamin Kiefer, Martin Messmer, Andreas Zell
https://arxiv.org/abs/2506.20550

Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos
Modern image-based object detection models, such as YOLOv7, primarily process individual frames independently, thus ignoring valuable temporal context naturally present in videos. Meanwhile, existing video-based detection methods often introduce complex temporal modules, significantly increasing model size and computational complexity. In practical applications such as surveillance and autonomous driving, transient challenges including motion blur, occlusions, and abrupt appearance changes can …

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/4]:
- LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
Chenjian Gao, Lihe Ding, Xin Cai, Zhanpeng Huang, Zibin Wang, Tianfan Xue

At Cannes, YouTube CEO Neal Mohan says YouTube plans to integrate Google's most advanced AI video generation tool, Veo 3, into YouTube Shorts later this summer (Alex Weprin/The Hollywood Reporter)
https://www.hollywoodreporter.com/business

YouTube to Add Google’s Veo 3 to Shorts in Move That Could Turbocharge AI on the Video Platform
The Veo 3 video generator is capable of creating both videos and sound based on text prompts, with YouTube CEO Neal Mohan saying the "AI technology will push the limits of human creativity."

SAG-AFTRA ends the 300 day video game actors strike after reaching a tentative deal for a new Interactive Media Agreement with the major video game companies (Erik Hayden/The Hollywood Reporter)
https://www.hollywoodreporter.com/business

SAG-AFTRA Suspends Strike Against Video Game Companies, Paving Way for Return to Work
The union had taken a stand on artificial intelligence, among other concerns, as it looked to advocate for voice and performance capture workers.

Sekai: A Video Dataset towards World Exploration
Zhen Li, Chuanhao Li, Xiaofeng Mao, Shaoheng Lin, Ming Li, Shitian Zhao, Zhaopan Xu, Xinyue Li, Yukang Feng, Jianwen Sun, Zizhen Li, Fanrui Zhang, Jiaxin Ai, Zhixiang Wang, Yuwei Wu, Tong He, Jiangmiao Pang, Yu Qiao, Yunde Jia, Kaipeng Zhang
https://arxiv.org/abs/2506.15675…

Sekai: A Video Dataset towards World Exploration
Video generation techniques have made remarkable progress, promising to be the foundation of interactive world exploration. However, existing video generation datasets are not well-suited for world exploration training as they suffer from some limitations: limited locations, short duration, static scenes, and a lack of annotations about exploration and the world. In this paper, we introduce Sekai (meaning ``world'' in Japanese), a high-quality first-person view worldwide video dataset with rich…