4 papers
Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
Jung-Ho Hong, Ho-Joong Kim, Kyu-Sung Jeon +1
The feature attribution method reveals the contribution of input variables to the decision-making process to provide an attribution map for explanation. Existing methods grounded o…
DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer
Ho-Joong Kim, Yearang Lee, Jung-Ho Hong +1
In this paper, we examine a key limitation in query-based detectors for temporal action detection (TAD), which arises from their direct adaptation of originally designed architectu…
TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
Ho-Joong Kim, Jung-Ho Hong, Heejo Kong +1
In this paper, we investigate that the normalized coordinate expression is a key factor as reliance on hand-crafted components in query-based detectors for temporal action detectio…
Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance
Jung-Ho Hong, Woo-Jeoung Nam, Kyu-Sung Jeon +1
Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures. In this paper, we propose a novel…