SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.12745 · CVPR · 2022

UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection

Chang Chen, Siyuan Li, Ying Shan, Xiaohu Qie, Yang Wu, Ye Liu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

A white cat with spots is playing with a feathery toy (No Query) QUERY 1: A person cuts up photos Video (Input) Audio (Input) UMT Figure 1. The proposed UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results (marked by red rectangles and golden stars, respectively). Note that different text queries lead to different outcomes from the same video. Arrows in different colors denote different input-output combinations.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.12745")
get_code_for_paper("2203.12745")
have("2203.12745")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.12745.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.12745.svg)](https://syntology.ai/paper/2203.12745)

Connect an agent — have() is free.