| TMCIR: Token Merge Benefits Composed Image Retrieval | | 83.46 | 91.06 | TMCIR | 2025-04-15 |
| WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval | | 82.96 | | WRF4CIR | 2026-04-07 |
| ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval | ✓ Link | 82.81 | | ReCALL | 2026-02-02 |
| Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives | ✓ Link | 82.69 | 90.87 | SPN4CIR (SPRC) | 2024-04-17 |
| Sentence-level Prompts Benefit Composed Image Retrieval | ✓ Link | 82.66 | 90.39 | SPRC2 | 2023-10-09 |
| CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval | ✓ Link | 82.58 | | CSMCIR | 2026-01-07 |
| OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval | | 81.99 | | OFFSET | 2025-07-08 |
| Heterogeneous Uncertainty-Guided Composed Image Retrieval with Fine-Grained Probabilistic Learning | | 81.93 | | HUG | 2026-01-16 |
| FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval | | 81.92 | | FAR-Net | 2025-07-17 |
| COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations | | 81.92 | | COMBINER | 2026-06-03 |
| Sentence-level Prompts Benefit Composed Image Retrieval | ✓ Link | 81.39 | 89.74 | SPRC | 2023-10-09 |
| Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder | ✓ Link | 80.9 | 89.78 | Candidate Set Re-ranking | 2023-05-25 |
| CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval | ✓ Link | 78.74 | 89.59 | CaLa | 2024-05-29 |
| Data Roaming and Quality Assessment for Composed Image Retrieval | ✓ Link | 78.25 | 88.75 | CASE (Pre-trained on LaSCo.Ca) | 2023-03-16 |
| Data Roaming and Quality Assessment for Composed Image Retrieval | ✓ Link | 77.5 | 87.25 | CASE | 2023-03-16 |
| VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval | ✓ Link | 75.9 | | VISTA (base) | 2024-06-06 |
| MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval | ✓ Link | 75.7 | 85.1 | MMRet-MLLM | 2024-12-19 |
| Target-Guided Composed Image Retrieval | | 75.6 | 87.16 | TG-CIR (Wen et al., 2023) | 2023-09-04 |
| Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features | ✓ Link | 75.10 | | CLIP4Cir (v3) | 2023-08-22 |
| Bi-directional Training for Composed Image Retrieval via Text Prompt Learning | ✓ Link | 72.59 | 83.88 | BLIP4CIR+Bi | 2023-03-29 |
| Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features | ✓ Link | 69.09 | | CLIP4Cir (v2) | 2022-06-19 |
| Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features | ✓ Link | 63.87 | | CLIP4Cir | 2022-01-01 |
| Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models | ✓ Link | 45.88 | | CIRPLANT | 2021-08-09 |
| ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity | ✓ Link | 43.05 | 61.31 | ARTEMIS | 2022-03-15 |