Visual object tracking requires effective temporal integration, yet most Transformer trackers still rely on predominantly feed-forward feature extraction. Existing temporal mechanisms typically update templates, prompts, queries, or prediction states, while intermediate representations are rarely reused to modulate cor...
Yueyang Cang, Xiao-Teng Zhang, Zhiyuan Ning et al.· 0 citations
Overall, RATL shifts the retrieved object from historical target values to base-model-specific historical forecast errors, providing a plug-in, residual-memory-based paradigm for learned feedback correction in continuous-output forecasting.
Yu-Chen He, Yueyang Cang, Zhi-Yuan Ning et al.· 0 citations
This work introduces Polarity-Prompt Contrastive Decoding (PopCD), a test-time behavior control method that generalizes contrastive decoding to broader enhancement settings and is applicable to both LLMs and Vision-Language Models without additional training.
Bao-Long Bi, Yuyao Ge, Shenghua Liu et al.· IEEE Transactions on Pattern...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.