Transaction

e7feb75abfdc6b086fd20bd7fa06dfa547efc55cbe68e0a05cffecb64b86d833
Timestamp (utc)
2024-08-30 07:11:55
Fee Paid
0.00000006 BSV
(
0.00311524 BSV
-
0.00311518 BSV
)
Fee Rate
2.683 sat/KB
Version
1
Confirmations
74,181
Size Stats
2,236 B

3 Outputs

Total Output:
0.00311518 BSV
  • jmetaB03b3bf293069810678f90be1c30ad4debac98cfa7fe61b13c0a434b4b450659fd1@104e04f4dc7bbb58b675a0be8ec8a2392cd828cadc0c1b85347e2d4ab003150erss.item metarss.netM-<item> <title>FastForensics: Efficient Two-Stream Design for Real-Time Image Manipulation Detection</title> <link>https://arxiv.org/abs/2408.16582</link> <description>arXiv:2408.16582v1 Announce Type: cross Abstract: With the rise in popularity of portable devices, the spread of falsified media on social platforms has become rampant. This necessitates the timely identification of authentic content. However, most advanced detection methods are computationally heavy, hindering their real-time application. In this paper, we describe an efficient two-stream architecture for real-time image manipulation detection. Our method consists of two-stream branches targeting the cognitive and inspective perspectives. In the cognitive branch, we propose efficient wavelet-guided Transformer blocks to capture the global manipulation traces related to frequency. This block contains an interactive wavelet-guided self-attention module that integrates wavelet transformation with efficient attention design, interacting with the knowledge from the inspective branch. The inspective branch consists of simple convolutions that capture fine-grained traces and interact bidirectionally with Transformer blocks to provide mutual support. Our method is lightweight ($\sim$ 8M) but achieves competitive performance compared to many other counterparts, demonstrating its efficacy in image manipulation detection and its potential for portable integration.</description> <guid isPermaLink="false">oai:arXiv.org:2408.16582v1</guid> <category>cs.CV</category> <category>cs.CR</category> <pubDate>Fri, 30 Aug 2024 00:00:00 -0400</pubDate> <arxiv:announce_type>cross</arxiv:announce_type> <dc:rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0/</dc:rights> <dc:creator>Yangxiang Zhang, Yuezun Li, Ao Luo, Jiaran Zhou, Junyu Dong</dc:creator> </item>
    https://whatsonchain.com/tx/e7feb75abfdc6b086fd20bd7fa06dfa547efc55cbe68e0a05cffecb64b86d833