2 papers
cs.CV2026
Event ActivityNet: A Large-Scale Simulated-Event Benchmark for Untrimmed Action Understanding
Cheng-Yao Hong, Ting-Wei Lin, Yun-Chung Lai +3
Long-horizon event-based action understanding remains underexplored because existing datasets largely comprise short, trimmed clips, while collecting native event streams with dens…
cs.CV2026
Test-Time Registers as Global Priors for Tokenized Image Generation
Cheng-Yao Hong, Yifan Wang, Yuewei Lin +1
Attention-based models often develop attention sinks, where a small number of tokens repeatedly attract attention and accumulate unusually large activations. In vision transformers…