{"total":17,"rows":[{"id":"2308.07026","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","created":"2023-08-14","cited_by_count":103,"area":null},{"id":"2408.14180","title":"I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing","created":"2024-08-26","cited_by_count":63,"area":null},{"id":"2302.12552","title":"Deep Learning for Video-Text Retrieval: a Review","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2312.08984","title":"CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer","created":"2023-12-14","cited_by_count":10,"area":null},{"id":"2305.10260","title":"From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2309.05451","title":"Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval","created":"2023-09-11","cited_by_count":9,"area":null},{"id":"2503.08714","title":"Versatile Multimodal Controls for Expressive Talking Human Animation","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2412.19155","title":"Referencing Where to Focus: Improving VisualGrounding with Referential Query","created":"2024-12-26","cited_by_count":2,"area":null},{"id":"2504.17990","title":"From Mapping to Composing: A Two-Stage Framework for Zero-shot Composed Image Retrieval","created":"2025-04-25","cited_by_count":2,"area":null},{"id":"2310.06879","title":"The Solution for the CVPR2023 NICE Image Captioning Challenge","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2406.18254","title":"Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2412.13510","title":"Dynamic Adapter with Semantics Disentangling for Cross-lingual Cross-modal Retrieval","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2504.17991","title":"RSRNav: Reasoning Spatial Relationship for Image-Goal Navigation","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2603.23902","title":"Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2406.01604","title":"An Empirical Study of Excitation and Aggregation Design Adaptions in CLIP4Clip for Video-Text Retrieval","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2602.14488","title":"BETA-Labeling for Multilingual Dataset Construction in Low-Resource IR","created":"2026-02-16","cited_by_count":0,"area":null}],"next_cursor":null}