{"total":14,"rows":[{"id":"2204.03972","title":"Contrastive language and vision learning of general fashion concepts","created":"2022-04-08","cited_by_count":42,"area":null},{"id":"2402.16928","title":"CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision","created":"2024-02-26","cited_by_count":17,"area":null},{"id":"2305.09299","title":"UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning","created":"2023-05-16","cited_by_count":13,"area":null},{"id":"2306.00379","title":"Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributes","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2409.11624","title":"Multimodal Generalized Category Discovery","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2401.12972","title":"On the Efficacy of Text-Based Input Modalities for Action Anticipation","created":"2024-01-23","cited_by_count":6,"area":null},{"id":"2308.05550","title":"Cross-Domain Product Representation Learning for Rich-Content E-Commerce","created":"2023-08-10","cited_by_count":3,"area":null},{"id":"2311.18420","title":"TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2409.17777","title":"Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2304.13765","title":"Towards ethical multimodal systems","created":"2023-04-26","cited_by_count":1,"area":null},{"id":"2407.16248","title":"Spatiotemporal Graph Guided Multi-modal Network for Livestreaming Product Retrieval","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2408.14698","title":"Smart Multi-Modal Search: Contextual Sparse and Dense Embedding Integration in Adobe Express","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2503.00054","title":"Deciphering the complaint aspects: Towards an aspect-based complaint identification model with video complaint dataset in finance","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2509.19952","title":"When Words Can't Capture It All: Towards Video-Based User Complaint Text Generation with Multimodal Video Complaint Dataset","created":"2025-09-24","cited_by_count":0,"area":null}],"next_cursor":null}