Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
Youngrae Kim, Qixin Hu, C. -C. Jay Kuo +1
Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagna…
cs.CV2025
Green Video Camouflaged Object Detection
Xinyu Wang, Hong-Shuo Chen, Zhiruo Zhou +3
Camouflaged object detection (COD) aims to distinguish hidden objects embedded in an environment highly similar to the object. Conventional video-based COD (VCOD) methods explicitl…
cs.CV2024
GreenCOD: A Green Camouflaged Object Detection Method
Hong-Shuo Chen, Yao Zhu, Suya You +2
We introduce GreenCOD, a green method for detecting camouflaged objects, distinct in its avoidance of backpropagation techniques. GreenCOD leverages gradient boosting and deep feat…