Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
General Hazard Detection
Stephanie Ng, CP Lim, SueJen Looi +5
Hazard, as an abstract concept, is typically defined through cognitive-level logical reasoning rather than concrete examples. In contrast, existing hazard detection systems rely on…
cs.CV2025
LLMs Are Not Yet Ready for Deepfake Image Detection
Shahroz Tariq, David Nguyen, M. A. P. Chamikara +3
The growing sophistication of deepfakes presents substantial challenges to the integrity of media and the preservation of public trust. Concurrently, vision-language models (VLMs),…
cs.CV2025
Quantum Down Sampling Filter for Variational Auto-encoder
Farina Riaz, Fakhar Zaman, Hajime Suzuki +2
Variational autoencoders (VAEs) are fundamental for generative modeling and image reconstruction, yet their performance often struggles to maintain high fidelity in reconstructions…