亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Detecting and Grounding Multi-Modal Media Manipulation and Beyond

计算机科学 情态动词 人工智能 计算机视觉 化学 高分子化学
作者
Rui Shao,Tianxing Wu,Jianlong Wu,Liqiang Nie,Ziwei Liu
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:46 (8): 5556-5574 被引量:22
标识
DOI:10.1109/tpami.2024.3367749
摘要

Misinformation has become a pressing issue. Fake media, in both visual and textual forms, is widespread on the web. While various DeepFake detection and text fake news detection methods have been proposed, they are only designed for single-modality forgery based on binary classification, let alone analyzing and reasoning subtle forgery traces across different modalities. In this paper, we highlight a new research problem for multi-modal fake media, namely Detecting and Grounding Multi-Modal Media Manipulation (DGM 4). DGM 4 aims to not only detect the authenticity of multi-modal media, but also ground the manipulated content (i.e., image bounding boxes and text tokens), which requires deeper reasoning of multi-modal media manipulation. To support a large-scale investigation, we construct the first DGM 4 dataset, where image-text pairs are manipulated by various approaches, with rich annotation of diverse manipulations. Moreover, we propose a novel HierArchical Multi-modal Manipulation rEasoning tRansformer (HAMMER) to fully capture the fine-grained interaction between different modalities. HAMMER performs: 1) manipulation-aware contrastive learning between two uni-modal encoders as shallow manipulation reasoning and 2) modality-aware cross-attention by multi-modal aggregator as deep manipulation reasoning. Dedicated manipulation detection and grounding heads are integrated from shallow to deep levels based on the interacted multi-modal information. To exploit more fine-grained contrastive learning for cross-modal semantic alignment, we further integrate Manipulation-Aware Contrastive Loss with Local View and construct a more advanced model HAMMER++. Finally, we build an extensive benchmark and set up rigorous evaluation metrics for this new research problem. Comprehensive experiments demonstrate the superiority of HAMMER and HAMMER++; several valuable observations are also revealed to facilitate future research in multi-modal media manipulation.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
田様的应助被浮云采纳,获得10
3秒前
酷波er的应助被00hello00采纳,获得10
5秒前
6秒前
11秒前
13秒前
浮云发布了新的文献求助10
16秒前
芒果完成签到,获得积分20
17秒前
25秒前
29秒前
浮云发布了新的文献求助10
33秒前
33秒前
44秒前
50秒前
复杂曼荷完成签到,获得积分10
52秒前
may完成签到 ,获得积分10
54秒前
1分钟前
1分钟前
英俊的铭的应助被邓倩采纳,获得10
1分钟前
Maestro_S的应助被呵呵采纳,获得10
1分钟前
00hello00发布了新的文献求助10
1分钟前
1分钟前
1分钟前
仁爱的鞋子完成签到,获得积分10
1分钟前
安详老鼠完成签到,获得积分10
1分钟前
1分钟前
1分钟前
Shu完成签到,获得积分10
1分钟前
刻苦的煎蛋完成签到,获得积分10
1分钟前
庾傀斗发布了新的文献求助10
1分钟前
ssgg完成签到,获得积分10
1分钟前
辛勤诗兰完成签到,获得积分10
2分钟前
2分钟前
不爱写论文完成签到,获得积分10
2分钟前
HaoZhang发布了新的文献求助10
2分钟前
2分钟前
Lynee完成签到,获得积分10
2分钟前
清脆妙梦完成签到,获得积分10
2分钟前
sugar发布了新的文献求助10
2分钟前
小辣椒完成签到,获得积分10
2分钟前
HaoZhang完成签到,获得积分20
2分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8195111
求助须知:如何正确求助?哪些是违规求助? 9580886
关于积分的说明 21872823
捐赠科研通 7794997
什么是DOI,文献DOI怎么找? 3437934
关于科研通互助平台的介绍 2561228
邀请新用户注册赠送积分活动 2484609