3 papers
cs.CV2026
TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models
Zeyi Shao, Haowen Hua, Jiaxin Zhang +3
Prompt learning adapts vision-language models, such as CLIP, by adjusting a small set of context tokens. However, under few-shot supervision, even moderate label noise can disrupt…
cs.CV2023
Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks
Cong Yang, Bipin Indurkhya, John See +5
Skeleton Ground Truth (GT) is critical to the success of supervised skeleton extraction methods, especially with the popularity of deep learning techniques. Furthermore, we see ske…
cs.MM2023
Scene Graph Lossless Compression with Adaptive Prediction for Objects and Relations
Yufeng Zhang, Weiyao Lin, Wenrui Dai +2
The scene graph is a new data structure describing objects and their pairwise relationship within image scenes. As the size of scene graph in vision applications grows, how to loss…