Results 211 to 220 of about 487,083 (255)

UrbanClipAtlas: A Visual Analytics Framework for Event and Scene Retrieval in Urban Videos

open access: yesComputer Graphics Forum, EarlyView.
Abstract Extracting actionable insights from long‐duration urban videos is often labor‐intensive: analysts must manually sift through raw footage to pinpoint target events or uncover broader behavioral trends. In this work, we present UrbanClipAtlas, a visual analytics system for exploring long urban videos recorded at street intersections ...
Joel Perca   +5 more
wiley   +1 more source

KnowTI: Bridging the Knowledge Gap in Information Communication through Interactive Visual LLM Summarizations

open access: yesComputer Graphics Forum, EarlyView.
We propose KnowTI, a Knowledge Transfer framework that delivers interactive visual summarizations on demand. We conducted a mixed‐initiative within‐subject design study comparing traditional video‐based learning against KnowTI. We assessed statistical significance and qualitative utterances focusing on learning outcomes, knowledge gain and retention ...
S. El‐Sherbiny, R. G. Raidou
wiley   +1 more source

ConversationAlign: Open-source software for analyzing patterns of lexical use and alignment in conversation transcripts. [PDF]

open access: yesBehav Res Methods
Sacks B   +7 more
europepmc   +1 more source

Online‐optimized RAG for tool use and function calling

open access: yesDecision Sciences, EarlyView.
Abstract In many applications, retrieval‐augmented generation (RAG) drives tool use and function calling by embedding the (user) queries and matching them to prespecified tool/function descriptions. In this article, we address an embedding misalignment issue that often arises in practical applications due to imperfect embedding models or noisy ...
Yu Pan, Xiaocheng Li, Hanzhao Wang
wiley   +1 more source

Home - About - Disclaimer - Privacy