5 papers
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…
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…
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…
SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment
Ganning Zhao, Wenhui Cui, Suya You +1
Unsupervised image-to-image (I2I) translation learns cross-domain image mapping that transfers input from the source domain to output in the target domain while preserving its sema…
Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraints
Ganning Zhao, Tingwei Shen, Suya You +1
Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training. Due to different semantic distributions between synthetic and real-wor…