Výsledky vyhledávání

Report

DrVideo: Document Retrieval Based Long Video Understanding

Autor: Ma, Ziyu, Gou, Chenhui, Shi, Hengcan, Sun, Bin, Li, Shutao, Rezatofighi, Hamid, Cai, Jianfei

Existing methods for long video understanding primarily focus on videos only lasting tens of seconds, with limited exploration of techniques for handling longer videos. The increased number of frames in longer videos presents two main challenges: dif

Externí odkaz: http://arxiv.org/abs/2406.12846

Zobrazit plný text záznamu

Report

GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering

Autor: Ma, Ziyu, Li, Shutao, Sun, Bin, Cai, Jianfei, Long, Zuxiang, Ma, Fuyan

Knowledge-based visual question answering (VQA) requires world knowledge beyond the image for accurate answer. Recently, instead of extra knowledge bases, a large language model (LLM) like GPT-3 is activated as an implicit knowledge engine to jointly

Externí odkaz: http://arxiv.org/abs/2402.02503

Zobrazit plný text záznamu

Report

Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation

Autor: Li, Bin, Weng, Yixuan, Ma, Ziyu, Sun, Bin, Li, Shutao

This paper introduces the schemes of Team LingJing's experiments in NLPCC-2022-Shared-Task-4 Multi-modal Dialogue Understanding and Generation (MDUG). The MDUG task can be divided into two phases: multi-modal context understanding and response genera

Externí odkaz: http://arxiv.org/abs/2207.01823

Zobrazit plný text záznamu

Akademický článek

The measurement of China's provincial physical capital stock based on the improved method and indicators.

Autor: Wang, Qi¹ (AUTHOR), Ma, Ziyu¹ (AUTHOR) maziyu_0804@163.com

Publikováno v: PLoS ONE. 8/13/2024, Vol. 19 Issue 8, p1-31. 31p.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

Hybrid Mutimodal Fusion for Dimensional Emotion Recognition

Autor: Ma, Ziyu, Ma, Fuyan, Sun, Bin, Li, Shutao

In this paper, we extensively present our solutions for the MuSe-Stress sub-challenge and the MuSe-Physio sub-challenge of Multimodal Sentiment Challenge (MuSe) 2021. The goal of MuSe-Stress sub-challenge is to predict the level of emotional arousal

Externí odkaz: http://arxiv.org/abs/2110.08495

Zobrazit plný text záznamu