Brief

last 24h

[2/2] 221 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

RESEARCH · arXiv cs.CV English(EN) · 4d · [2 sources]

U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025

Researchers have developed U-CESE, a Unified Clip-based Event Search Engine designed for the AI Challenge HCMC 2025. This system aims to improve the retrieval of events from large video datasets by integrating multiple modules into a cohesive framework. Key innovations include a Unified Clipping Algorithm for efficient processing, a DAKE method for lightweight keyframe extraction using JPEG file size variations, and ReCap, a captioning framework that generates temporally consistent descriptions. AI

IMPACT Introduces novel methods for efficient video event retrieval and keyframe extraction, potentially improving AI systems that process large video datasets.
TOOL · arXiv cs.IR (Information Retrieval) English(EN) · 1w

MERVIN: A Unified Framework for Multimodal Event Retrieval in Vietnamese News Videos

Researchers have developed MERVIN, a unified multimodal framework designed for event retrieval in Vietnamese news videos. This system integrates visual features, transcripts, and video summaries, enhancing transcript quality with Gemini 1.5 Flash and using a Perception Encoder for visual data. MERVIN achieved high scores in the AI Challenge HCMC 2025, successfully retrieving all query results in the final round. AI

IMPACT This framework could improve how users search and retrieve specific events from large archives of Vietnamese news videos.