Search Results for author:
Found 2 papers, 1 papers with code
Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions
After that, grounding is accomplished by calculating the structural similarity matrix between visual and textual triplets with a VLA model, and subsequently propagate it to an instance-level similarity matrix.
Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels
To reject noisy labels, recent works regard large loss samples as noise but ignore the semantic correlation different multi-label images.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
