Zekai Ji — accepted AI-conference papers

2026

Learning Heterogeneous Global Local Frequency Dependencies in Diffusion-Based Image Compression

YuBing Luo, Zekai Ji, Jia Qin, Zhihang Chen, Tengyue Guo, Pinle Qin +2

IJCAI 2026

Diffusion-based image compression has exhibited robust performance. However, most existing methods primarily emphasize spatial domain, causing frequency dependencies to be learned only implicitly. We revisit this problem from a frequency perspective, and observe pronounced heterogeneity between glob

Cited by 0 Scholar ↗

2026

Revisiting Downsampling in Semantic Segmentation: Fighting Aliasing with Dynamic Gaussian and Gabor Frequency Filters

Yu Bing Luo, Nian Shi, Jia Qin, Zekai Ji, Pinle Qin, Jianchao Zeng +1

AAAI 2026technical

Downsampling is essential in semantic segmentation for reducing computational cost and guiding the learning of class-discriminative features. Existing models typically rely on strided convolutions or patch splitting to obtain features with lower resolution. However, we observe that such operations o

Cited by 0 Source ↗PDF ↗Scholar ↗