Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers

Documenti analoghi

• DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer
  di: Kim, Ho-Joong, et al.
  Pubblicazione: (2025)
• Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance
  di: Hong, Jung-Ho, et al.
  Pubblicazione: (2023)
• TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
  di: Kim, Ho-Joong, et al.
  Pubblicazione: (2024)
• ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval
  di: Kim, Ji-Hyeon, et al.
  Pubblicazione: (2026)
• FIQ: Fundamental Question Generation with the Integration of Question Embeddings for Video Question Answering
  di: Oh, Ju-Young, et al.
  Pubblicazione: (2025)