FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312749754> ?p ?o ?g. }

• W4312749754 abstract "Cross language-image modality retrieval in E-commerce is a fundamental problem for product search, recommendation, and marketing services. Extensive efforts have been made to conquer the cross-modal retrieval problem in the general domain. When it comes to E-commerce, a com-mon practice is to adopt the pretrained model and finetune on E-commerce data. Despite its simplicity, the performance is sub-optimal due to overlooking the uniqueness of E-commerce multimodal data. A few recent efforts [10], [72] have shown significant improvements over generic methods with customized designs for handling product images. Unfortunately, to the best of our knowledge, no existing method has addressed the unique challenges in the e-commerce language. This work studies the outstanding one, where it has a large collection of special meaning entities, e.g., “Di s s e l (brand)”, “Top (category)”, “relaxed (fit)” in the fashion clothing business. By formulating such out-of-distribution finetuning process in the Causal Inference paradigm, we view the erroneous semantics of these special entities as confounders to cause the retrieval failure. To rectify these semantics for aligning with e-commerce do-main knowledge, we propose an intervention-based entity-aware contrastive learning framework with two modules, i.e., the Confounding Entity Selection Module and Entity-Aware Learning Module. Our method achieves competitive performance on the E-commerce benchmark Fashion-Gen. Particularly, in top-1 accuracy (R@l), we observe 10.3% and 10.5% relative improvements over the closest baseline in image-to-text and text-to-image retrievals, respectively." @default.
• W4312749754 created "2023-01-05" @default.
• W4312749754 creator A5005119482 @default.
• W4312749754 creator A5016127250 @default.
• W4312749754 creator A5024078415 @default.
• W4312749754 creator A5024437999 @default.
• W4312749754 creator A5024456511 @default.
• W4312749754 creator A5048522863 @default.
• W4312749754 creator A5064726544 @default.
• W4312749754 creator A5082659796 @default.
• W4312749754 creator A5084618257 @default.
• W4312749754 date "2022-06-01" @default.
• W4312749754 modified "2023-10-09" @default.
• W4312749754 title "EI-CLIP: Entity-aware Interventional Contrastive Learning for E-commerce Cross-modal Retrieval" @default.
• W4312749754 cites W1536680647 @default.
• W4312749754 cites W1905882502 @default.
• W4312749754 cites W1949478088 @default.
• W4312749754 cites W2064675550 @default.
• W4312749754 cites W2100235303 @default.
• W4312749754 cites W2143891888 @default.
• W4312749754 cites W2150600350 @default.
• W4312749754 cites W2474425175 @default.
• W4312749754 cites W2605146283 @default.
• W4312749754 cites W2801567109 @default.
• W4312749754 cites W2962784628 @default.
• W4312749754 cites W2963138277 @default.
• W4312749754 cites W2963419548 @default.
• W4312749754 cites W2963528347 @default.
• W4312749754 cites W2965848243 @default.
• W4312749754 cites W2970231061 @default.
• W4312749754 cites W2971196067 @default.
• W4312749754 cites W2981851019 @default.
• W4312749754 cites W2988823324 @default.
• W4312749754 cites W2998356391 @default.
• W4312749754 cites W3010277541 @default.
• W4312749754 cites W3035485997 @default.
• W4312749754 cites W3035651653 @default.
• W4312749754 cites W3036148046 @default.
• W4312749754 cites W3081170586 @default.
• W4312749754 cites W3121523901 @default.
• W4312749754 cites W3138516171 @default.
• W4312749754 cites W3152619510 @default.
• W4312749754 cites W3171353004 @default.
• W4312749754 cites W3175136611 @default.
• W4312749754 cites W3182120198 @default.
• W4312749754 cites W3194662286 @default.
• W4312749754 cites W3197032408 @default.
• W4312749754 cites W3205572000 @default.
• W4312749754 cites W3206685025 @default.
• W4312749754 cites W4225620527 @default.
• W4312749754 cites W4297971002 @default.
• W4312749754 doi "https://doi.org/10.1109/cvpr52688.2022.01752" @default.
• W4312749754 hasPublicationYear "2022" @default.
• W4312749754 type Work @default.
• W4312749754 citedByCount "5" @default.
• W4312749754 countsByYear W43127497542023 @default.
• W4312749754 crossrefType "proceedings-article" @default.
• W4312749754 hasAuthorship W4312749754A5005119482 @default.
• W4312749754 hasAuthorship W4312749754A5016127250 @default.
• W4312749754 hasAuthorship W4312749754A5024078415 @default.
• W4312749754 hasAuthorship W4312749754A5024437999 @default.
• W4312749754 hasAuthorship W4312749754A5024456511 @default.
• W4312749754 hasAuthorship W4312749754A5048522863 @default.
• W4312749754 hasAuthorship W4312749754A5064726544 @default.
• W4312749754 hasAuthorship W4312749754A5082659796 @default.
• W4312749754 hasAuthorship W4312749754A5084618257 @default.
• W4312749754 hasConcept C136764020 @default.
• W4312749754 hasConcept C154945302 @default.
• W4312749754 hasConcept C184337299 @default.
• W4312749754 hasConcept C199360897 @default.
• W4312749754 hasConcept C204321447 @default.
• W4312749754 hasConcept C23123220 @default.
• W4312749754 hasConcept C2524010 @default.
• W4312749754 hasConcept C2776436953 @default.
• W4312749754 hasConcept C33923547 @default.
• W4312749754 hasConcept C41008148 @default.
• W4312749754 hasConcept C4554734 @default.
• W4312749754 hasConcept C78597825 @default.
• W4312749754 hasConcept C90673727 @default.
• W4312749754 hasConcept C96711827 @default.
• W4312749754 hasConceptScore W4312749754C136764020 @default.
• W4312749754 hasConceptScore W4312749754C154945302 @default.
• W4312749754 hasConceptScore W4312749754C184337299 @default.
• W4312749754 hasConceptScore W4312749754C199360897 @default.
• W4312749754 hasConceptScore W4312749754C204321447 @default.
• W4312749754 hasConceptScore W4312749754C23123220 @default.
• W4312749754 hasConceptScore W4312749754C2524010 @default.
• W4312749754 hasConceptScore W4312749754C2776436953 @default.
• W4312749754 hasConceptScore W4312749754C33923547 @default.
• W4312749754 hasConceptScore W4312749754C41008148 @default.
• W4312749754 hasConceptScore W4312749754C4554734 @default.
• W4312749754 hasConceptScore W4312749754C78597825 @default.
• W4312749754 hasConceptScore W4312749754C90673727 @default.
• W4312749754 hasConceptScore W4312749754C96711827 @default.
• W4312749754 hasLocation W43127497541 @default.
• W4312749754 hasOpenAccess W4312749754 @default.
• W4312749754 hasPrimaryLocation W43127497541 @default.
• W4312749754 hasRelatedWork W2086064646 @default.
• W4312749754 hasRelatedWork W2115485936 @default.
• W4312749754 hasRelatedWork W2119135658 @default.

• next