Author

J. Katto

h-index 26 View on Semantic Scholar

We have 2 of 422 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Streamable Neural Video Compression: A Mixed Precision Approach for Cross-Platform Deployment

This paper proposes a streamable, client-server NVC architecture featuring a novel Mixed Precision (FP16/FP32) strategy, and demonstrates that this approach successfully eliminates intra-generation fragmentation and substantially broadens cross-die interoperability, achieving seamless cross-generation decodability for...

Kasidis Arunruangsirilert, He-Ming Sun, J. Katto · 0 citations

Open access Sep 2026

Benchmarking token mixers for efficient transformer-based learned video compression

This study establishes a clear lower bound and optimal trade-off points for context modeling in ATEM, provides critical insights into the redundancy of context module designs in video compression and establishes a new efficiency benchmark for future lightweight framework designs.

Chun Zhang, He-Ming Sun, J. Katto · APSIPA Transactions on Signa... · 0 citations