BestHub
Sign in
Tag

video grounding

0 views collected around this technical thread.

DataFunSummit
DataFunSummit
Aug 3, 2022 · Artificial Intelligence

AliMe MKG: Multimodal Knowledge Graph for Live E‑commerce and Its Technical Exploration

This report presents AliMe MKG, a multimodal knowledge graph designed for live e‑commerce, detailing its business background, construction and application, the three types of multimodal knowledge (triples, sentences, and visual media), the underlying extraction techniques, and its deployment in digital‑human anchors and intelligent live‑room assistants.

AIDigital Humane-commerce
0 likes · 19 min read
AliMe MKG: Multimodal Knowledge Graph for Live E‑commerce and Its Technical Exploration
DataFunTalk
DataFunTalk
Jul 20, 2022 · Artificial Intelligence

AliMe MKG: Building and Applying a Multimodal Knowledge Graph for Live E‑commerce

This report details the design, construction, and deployment of AliMe MKG, a multimodal knowledge graph that powers digital‑human anchors and smart assistants in live‑stream e‑commerce by integrating triple‑level, sentence‑level, and visual knowledge through advanced AI techniques such as image‑text matching, video grounding, multimodal NER, and entity linking.

AIe-commerce live streamingentity linking
0 likes · 17 min read
AliMe MKG: Building and Applying a Multimodal Knowledge Graph for Live E‑commerce