StreamingMemeStreamingMemeBuyers Guide
AboutLeaderboardsEventsSubmit News
Subscribe

Daily Brief

The streaming industry in your inbox every morning.

Daily Brief

The streaming industry in your inbox every morning.

StreamingMemeStreamingMeme

The independent buyers guide and news aggregator for the streaming technology industry.

Explore

Buyers GuideLeaderboardsEventsSubmit News

Stay updated

Weekly digest of new companies and streaming news.

Categories

Encoding & SoftwareVideo Delivery & CDNStreaming PlatformsAI for VideoProduction HardwareBusiness NewsMonetization & Ad TechRegulatory & Policy

© 2026 StreamingMeme. All rights reserved.

AboutPrivacy PolicyTermsContact
EncodingCDNPlatformsAI & VideoHardwareBusinessAd TechPolicy
← AI for Video
AI & VideoTechnical Development

Jina extends text embeddings to image, audio, and video

Jina extends text embeddings to image, audio, and video
Arxiv

Jina by Elastic researchers introduced jina-embeddings-v5-omni, a suite of multimodal embedding models that extends existing text embedding models to support image, audio, and video inputs. The models utilize a "frozen-encoder model composition" approach, connecting pre-trained modality-specific encoders to a frozen text embedding model via compact projectors, resulting in competitive performance with less training. The jina-embeddings-v5-omni-small model achieves strong text-only performance and competitive scores on image and audio tasks compared to other open-weight multimodal embedding models.

Key Takeaways

  • jina-embeddings-v5-omni comes in two base models: nano at 0.95B parameters and small at 1.57B parameters.
  • The training recipe freezes the text backbone, vision encoder, and audio encoder, and updates only fc_vision_2, fc_audio, and modality delimiter embeddings.
  • The paper says the trainable components are 0.35% of the joint model’s total weights.
  • On the open-weight benchmark table, jina-embeddings-v5-omni-small scores 67.00 on text, 56.05 on image, 41.20 on video, and 51.46 on audio, for a 53.93 average.
  • For visual document retrieval on ViDoRe-in-MIEB, jina-embeddings-v5-omni-small scores 79.08, while jina-embeddings-v5-omni-nano scores 70.05.

Why It Matters

This is a practical way to extend a text embedding stack into multimodal retrieval without retraining the full model. The paper keeps text embeddings identical to Jina Embeddings v5 Text, which matters for existing retrieval and RAG pipelines that depend on stable vector geometry. It also shows the strongest results on visual document retrieval, while video remains the weak spot in the benchmark tables. Watch the release’s task-specific variants and the gap between image/audio scores and MMEB-Video performance, since those are the clearest signs of where the recipe holds up and where it doesn’t.


Read full article at arxiv.org

Get this in your inbox → Subscribe

Enjoy our coverage?

Add StreamingMeme as a preferred source on Google to see more of our streaming news at the top of your Search results.

Add as preferred source

Related Articles

Qiang Zhang: DeltaToken cuts video tokens from 180K to under 1,000
ayushchat: Whisper runs locally on Apple Silicon with no network access
KDnuggets: Five open-source omni models collapse multimodal pipelines into single architectures
NVIDIA Technical Blog: NVIDIA TensorRT converts FP8 checkpoints to high-efficiency video inference engines

Newest

about 9 hours ago
AOL: UK Government considers complete Freeview switch-off between 2034 and 2044
about 9 hours ago
Broadcast: Games of the Future 2026 secures global streaming and broadcast distribution
about 9 hours ago
Investing.com: Alphabet upgraded as Google Cloud revenue surges 82% on AI demand
about 10 hours ago
The Desk: Phynd launches ad-supported cloud gaming beta on LG webOS
about 10 hours ago
Kalkine Media: Adveritas hits A$16.3M recurring revenue, shifts toward cash flow breakeven
about 15 hours ago
Hyper.ai: Google DeepMind and UC Riverside launch framework to trace synthetic video
about 15 hours ago
MediaPost: Microsoft launches Project Perception to defend programmatic supply chains from AI-driven fraud
about 15 hours ago
Digiday: IAB Redefining Media Types Standard targets automated video ad transparency
about 15 hours ago
VentureBeat: Moonshot AI releases Kimi K3 weights with $20M revenue licensing threshold
about 15 hours ago
AdExchanger: Streaming ad tech consolidation turns independent platforms into proprietary gardens
about 15 hours ago
The Fast Mode: AMD and South Korea Partner to Build Heterogeneous Sovereign AI Infrastructure
about 15 hours ago
Advanced Television: Roku and Fire TV solidify gatekeeper status as OS influence grows
about 15 hours ago
AdExchanger: Google mandates biometric passkeys for Ads API as AI costs reshape agency deals
about 15 hours ago
Exame: Brazil launches TV 3.0 with 4K VVC and interactive IP layers
1 day ago
Hackernoon: Production voice pipeline solves African language latency and hallucination problems
1 day ago
Startup Fortune: Higgsfield AI integrates third-party models as revenue run rate hits $300M
1 day ago
Design & Reuse: Stricter ETSI secure boot standards mandate hardware-level chain of trust
1 day ago
UK Parliament: UK Parliament launches investigation into Ofcom's Online Safety Act enforcement
1 day ago
SVG Europe: WBD streams 600 hours of Glasgow 2026 via remote-first infrastructure
1 day ago
TradingView: Amazon settles FTC Prime suit for $2.5B amid AI-focused redesign

Upcoming Events

Jul
29–30
Buffer-Free VideoSeattle
Aug
17–20
SET EXPOSao Paulo
Sep
11–14
IBCAmsterdam
Sep
13
SportsPro Streamtime Sports LiveAmsterdam
Sep
16–18
RTC.ONKrakow
View all events →

Top Sources

  1. 1.Sports Video Group105
  2. 2.SiliconANGLE93
  3. 3.AdExchanger66
  4. 4.Tech Times65
  5. 5.YouTube62
  6. 6.TechCrunch56
  7. 7.PPC Land51
  8. 8.arXiv50
Full leaderboards →

Newest

about 9 hours ago
AOL: UK Government considers complete Freeview switch-off between 2034 and 2044
about 9 hours ago
Broadcast: Games of the Future 2026 secures global streaming and broadcast distribution
about 9 hours ago
Investing.com: Alphabet upgraded as Google Cloud revenue surges 82% on AI demand
about 10 hours ago
The Desk: Phynd launches ad-supported cloud gaming beta on LG webOS
about 10 hours ago
Kalkine Media: Adveritas hits A$16.3M recurring revenue, shifts toward cash flow breakeven
about 15 hours ago
Hyper.ai: Google DeepMind and UC Riverside launch framework to trace synthetic video
about 15 hours ago
MediaPost: Microsoft launches Project Perception to defend programmatic supply chains from AI-driven fraud
about 15 hours ago
Digiday: IAB Redefining Media Types Standard targets automated video ad transparency
about 15 hours ago
VentureBeat: Moonshot AI releases Kimi K3 weights with $20M revenue licensing threshold
about 15 hours ago
AdExchanger: Streaming ad tech consolidation turns independent platforms into proprietary gardens
about 15 hours ago
The Fast Mode: AMD and South Korea Partner to Build Heterogeneous Sovereign AI Infrastructure
about 15 hours ago
Advanced Television: Roku and Fire TV solidify gatekeeper status as OS influence grows
about 15 hours ago
AdExchanger: Google mandates biometric passkeys for Ads API as AI costs reshape agency deals
about 15 hours ago
Exame: Brazil launches TV 3.0 with 4K VVC and interactive IP layers
1 day ago
Hackernoon: Production voice pipeline solves African language latency and hallucination problems
1 day ago
Startup Fortune: Higgsfield AI integrates third-party models as revenue run rate hits $300M
1 day ago
Design & Reuse: Stricter ETSI secure boot standards mandate hardware-level chain of trust
1 day ago
UK Parliament: UK Parliament launches investigation into Ofcom's Online Safety Act enforcement
1 day ago
SVG Europe: WBD streams 600 hours of Glasgow 2026 via remote-first infrastructure
1 day ago
TradingView: Amazon settles FTC Prime suit for $2.5B amid AI-focused redesign

Upcoming Events

Jul
29–30
Buffer-Free VideoSeattle
Aug
17–20
SET EXPOSao Paulo
Sep
11–14
IBCAmsterdam
Sep
13
SportsPro Streamtime Sports LiveAmsterdam
Sep
16–18
RTC.ONKrakow
View all events →

Top Sources

  1. 1.Sports Video Group105
  2. 2.SiliconANGLE93
  3. 3.AdExchanger66
  4. 4.Tech Times65
  5. 5.YouTube62
  6. 6.TechCrunch56
  7. 7.PPC Land51
  8. 8.arXiv50
Full leaderboards →