Correlates of Image Memorability in Vision Encoders: Activations, Attention Entropy, Patch Uniformity and Autoencoder Losses

Documenti analoghi

• Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models
  di: Takmaz, Ece, et al.
  Pubblicazione: (2025)
• Common Objects Out of Context (COOCo): Investigating Multimodal Context and Semantic Scene Violations in Referential Communication
  di: Merlo, Filippo, et al.
  Pubblicazione: (2025)
• Decoding Emotions in Abstract Art: Cognitive Plausibility of CLIP in Recognizing Color-Emotion Associations
  di: Widhoelzl, Hanna-Sophia, et al.
  Pubblicazione: (2024)
• Describing Images $\textit{Fast and Slow}$: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes
  di: Takmaz, Ece, et al.
  Pubblicazione: (2024)
• Localizing Memorization in SSL Vision Encoders
  di: Wang, Wenhao, et al.
  Pubblicazione: (2024)