Search papers, labs, and topics across Lattice.
Shandong University, Jinan, Shandong, China
8
10
8
15
FashionAM revolutionizes fashion image retrieval by directly linking multimodal queries to visual embeddings, eliminating the pitfalls of textification.
RankVR achieves a significant leap in Composed Image Retrieval by effectively managing noisy data, outperforming state-of-the-art methods in challenging scenarios.
Selective multimodal correction can dramatically enhance document parsing accuracy without compromising the integrity of reliable outputs.
ChartLens combines data correction and summary refinement to achieve state-of-the-art performance in chart understanding, outperforming existing solutions.
Multi-modification image retrieval is now possible: TEMA handles complex, real-world instructions that go beyond simple changes, outperforming existing methods on new datasets M-FashionIQ and M-CIRR.
Over 20 teams vied to decode human attention in video, revealing new insights into saliency prediction techniques.
Achieve state-of-the-art hybrid nearest neighbor search by explicitly modeling and mitigating data heterogeneity, a problem often overlooked in existing approaches.
Fine-grained context modeling boosts MLLM retrieval performance, achieving superior results in complex tasks with a lightweight architecture.
