Researchers have constructed a benchmark for webly supervised multi-label recognition (WS-MLR) including Web-COCO and Web-Pascal datasets, each containing about 300 thousand web images covering 80 and…
Researchers introduced the Semantic-Enhanced Patch Slimming (SEPS) framework to improve vision-language alignment by reducing patch redundancy and ambiguity, outperforming existing methods by 23% to 8…
Researchers propose EmCom-Diffusion, a framework that measures visual reflection in emergent languages by reconstructing images from emergent messages using a finetuned diffusion model and comparing t…
Researchers have developed IN2R, a new framework that corrects mismatched image-text pairs in large web-harvested datasets by synthesizing continuous supervision signals from intra-modal data relation…