Gabriel Thiem
@gthiem.bsky.social
Student @ TU Darmstadt - Informatik M.Sc.
www.linkedin.com/in/gabriel-thiem
www.linkedin.com/in/gabriel-thiem
Reposted by Gabriel Thiem
Debunking out-of-context misinformation requires both contextualizing the image and detecting inconsistencies in false captions🕵️
Meet COVE, the first method to tackle both tasks🤝achieving SOTA on real-world data🔥#NAACL2025
🧵(1/7)
📄Paper: arxiv.org/abs/2502.01194
Meet COVE, the first method to tackle both tasks🤝achieving SOTA on real-world data🔥#NAACL2025
🧵(1/7)
📄Paper: arxiv.org/abs/2502.01194
April 14, 2025 at 9:38 AM
Debunking out-of-context misinformation requires both contextualizing the image and detecting inconsistencies in false captions🕵️
Meet COVE, the first method to tackle both tasks🤝achieving SOTA on real-world data🔥#NAACL2025
🧵(1/7)
📄Paper: arxiv.org/abs/2502.01194
Meet COVE, the first method to tackle both tasks🤝achieving SOTA on real-world data🔥#NAACL2025
🧵(1/7)
📄Paper: arxiv.org/abs/2502.01194
Reposted by Gabriel Thiem
»COVE: COntext and VEracity prediction for out-of-context images« by Jonathan Tonglet (@tongletj.bsky.social), Gabriel Thiem (@gthiem.bsky.social), Iryna Gurevych (@igurevych.bsky.social)
📄 arxiv.org/abs/2502.01194 (2/🧵)
📄 arxiv.org/abs/2502.01194 (2/🧵)
COVE: COntext and VEracity prediction for out-of-context images
Images taken out of their context are the most prevalent form of multimodal misinformation. Debunking them requires (1) providing the true context of the image and (2) checking the veracity of the ima...
arxiv.org
April 11, 2025 at 10:34 AM
»COVE: COntext and VEracity prediction for out-of-context images« by Jonathan Tonglet (@tongletj.bsky.social), Gabriel Thiem (@gthiem.bsky.social), Iryna Gurevych (@igurevych.bsky.social)
📄 arxiv.org/abs/2502.01194 (2/🧵)
📄 arxiv.org/abs/2502.01194 (2/🧵)
Reposted by Gabriel Thiem
One more paper at #NAACL:
»COVE: COntext and VEracity prediction for out-of-context images« by Jonathan Tonglet (@tongletj.bsky.social), Gabriel Thiem (@gthiem.bsky.social) & Iryna Gurevych (@igurevych.bsky.social)
»COVE: COntext and VEracity prediction for out-of-context images« by Jonathan Tonglet (@tongletj.bsky.social), Gabriel Thiem (@gthiem.bsky.social) & Iryna Gurevych (@igurevych.bsky.social)
February 1, 2025 at 9:31 AM
One more paper at #NAACL:
»COVE: COntext and VEracity prediction for out-of-context images« by Jonathan Tonglet (@tongletj.bsky.social), Gabriel Thiem (@gthiem.bsky.social) & Iryna Gurevych (@igurevych.bsky.social)
»COVE: COntext and VEracity prediction for out-of-context images« by Jonathan Tonglet (@tongletj.bsky.social), Gabriel Thiem (@gthiem.bsky.social) & Iryna Gurevych (@igurevych.bsky.social)