·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Here’s what Samsung’s smart glasses actually look like1h◆Arcee, a US open source AI lab, says Chinese models are not inherently dangerous1h◆Substack’s new tool tells you who’s been writing their newsletters with AI1h◆OpenAI’s AI spending spree has ballooned to $750B1h◆AMD commits up to $5 billion to Anthropic3h◆The browser wars aren’t about search anymore — here are the best alternatives to Chrome and Safari4h◆Building AI infrastructure with the Effingham County community4h◆3 Google updates from Galaxy Unpacked 20264h◆Passionfroot raises $15M to expand its B2B creator marketplace to the US4h◆Advancing the next era of national science5h◆Meta made its own AI detection system. It should have just used Google’s6h◆Utility companies promise to spare us from AI’s energy bill7h◆Glow emerges from stealth at $1.2B valuation to challenge endpoint security in the AI era7h◆Synthesia’s AI training platform is moving beyond videos into live coaching9h◆Introducing OpenAI Presence12h◆SkillSight: Seeing Through Shared Descriptions for Accurate Skill Retrieval13h◆DBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Models13h◆HPD-Parsing: Hierarchical Parallel Document Parsing13h◆Incomplete Observations Boost Evolutionary Performance in Ocean Modeling13h◆From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs13h◆Here’s what Samsung’s smart glasses actually look like1h◆Arcee, a US open source AI lab, says Chinese models are not inherently dangerous1h◆Substack’s new tool tells you who’s been writing their newsletters with AI1h◆OpenAI’s AI spending spree has ballooned to $750B1h◆AMD commits up to $5 billion to Anthropic3h◆The browser wars aren’t about search anymore — here are the best alternatives to Chrome and Safari4h◆Building AI infrastructure with the Effingham County community4h◆3 Google updates from Galaxy Unpacked 20264h◆Passionfroot raises $15M to expand its B2B creator marketplace to the US4h◆Advancing the next era of national science5h◆Meta made its own AI detection system. It should have just used Google’s6h◆Utility companies promise to spare us from AI’s energy bill7h◆Glow emerges from stealth at $1.2B valuation to challenge endpoint security in the AI era7h◆Synthesia’s AI training platform is moving beyond videos into live coaching9h◆Introducing OpenAI Presence12h◆SkillSight: Seeing Through Shared Descriptions for Accurate Skill Retrieval13h◆DBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Models13h◆HPD-Parsing: Hierarchical Parallel Document Parsing13h◆Incomplete Observations Boost Evolutionary Performance in Ocean Modeling13h◆From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs13h◆
News/Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness
arxiv
PublishedJune 18, 2026 at 4:00 AM
—neutral

Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2505.21954v2 Announce Type: replace-cross Abstract: We present UniTalk, a novel dataset emphasizing challenging scenarios to enhance model generalization for the task of active speaker detection (ASD). Previously established benchmarks such as AVA predominantly comprise old movies and thus exh

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSkillSight: Seeing Through Shared Descriptions for Accurate Skill Retrieval13harxivDBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Models13harxivHPD-Parsing: Hierarchical Parallel Document Parsing13harxivIncomplete Observations Boost Evolutionary Performance in Ocean Modeling13h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews