Ho Joong Kim, Yearang Lee, Jung-Ho Hong, Seong-Whan Lee. DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025, Nashville, TN, USA, June 11-15, 2025. pages 24286-24296, Computer Vision Foundation / IEEE, 2025. [doi]
Abstract is missing.