Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token Operators
Pengcheng Fang, Hongli Chen, Yuxia Chen +3
Spectral token mixers based on Fourier transforms provide an efficient way to model global interactions in visual feature maps. Existing designs often either apply filter-wise spec…
cs.CV2025
Diffusion-grounded VideoLLM for Entity-aware temoporal grounding
Pengcheng Fang, Yuxia Chen, Yong Wang +3
Precise temporal grounding requires distinguishing when a queried event occurs from when its participating entities are merely visible. We propose Diffusion-Grounded VideoLLM, whic…