Imagen de Portada

TMCIR: Token Merge Benefits Composed Image Retrieval

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Chaoyang, Zhang, Zeyu, Teng, Long, Li, Zijun, Kan, Shichao
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Dual Relation Alignment for Composed Image Retrieval
por: Jiang, Xintong, et al.
Publicado: (2023)

FBCIR: Balancing Cross-Modal Focuses in Composed Image Retrieval
por: Zhao, Chenchen, et al.
Publicado: (2026)

Enhancing Supervised Composed Image Retrieval via Reasoning-Augmented Representation Engineering
por: Li, Jun, et al.
Publicado: (2025)

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
por: Hu, Taihang, et al.
Publicado: (2024)

Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
por: Feng, Zhangchi, et al.
Publicado: (2024)

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
por: Li, Siyuan, et al.
Publicado: (2025)

Local Representative Token Guided Merging for Text-to-Image Generation
por: Lee, Min-Jeong, et al.
Publicado: (2025)

Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
por: Liu, Mingyu, et al.
Publicado: (2026)

FashionMV: Product-Level Composed Image Retrieval with Multi-View Fashion Data
por: Yuan, Peng, et al.
Publicado: (2026)

CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval
por: Qian, Zhipeng, et al.
Publicado: (2026)

Composing Concepts from Images and Videos via Concept-prompt Binding
por: Kong, Xianghao, et al.
Publicado: (2025)

QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
por: Kwak, Jaehyun, et al.
Publicado: (2025)

FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval
por: Li, Zixu, et al.
Publicado: (2025)

MELT: Improve Composed Image Retrieval via the Modification Frequentation-Rarity Balance Network
por: Qiu, Guozhi, et al.
Publicado: (2026)

good4cir: Generating Detailed Synthetic Captions for Composed Image Retrieval
por: Kolouju, Pranavi, et al.
Publicado: (2025)

Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval
por: Jang, Young Kyun, et al.
Publicado: (2024)

CFIR: Fast and Effective Long-Text To Image Retrieval for Large Corpora
por: Long, Zijun, et al.
Publicado: (2024)

CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval
por: Jiang, Xintong, et al.
Publicado: (2024)

Diffusion Augmented Retrieval: A Training-Free Approach to Interactive Text-to-Image Retrieval
por: Long, Zijun, et al.
Publicado: (2025)

Scale Up Composed Image Retrieval Learning via Modification Text Generation
por: Zhou, Yinan, et al.
Publicado: (2025)

Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval
por: Jang, Young Kyun, et al.
Publicado: (2024)

Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation
por: Li, Yongqi, et al.
Publicado: (2024)

A Comprehensive Survey on Composed Image Retrieval
por: Song, Xuemeng, et al.
Publicado: (2025)

DeepMerge: Deep-Learning-Based Region-Merging for Image Segmentation
por: Lv, Xianwei, et al.
Publicado: (2023)

DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval
por: Yang, Yuxin, et al.
Publicado: (2025)

PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering
por: Wang, Yibin, et al.
Publicado: (2024)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
por: Zhong, Yiwu, et al.
Publicado: (2024)

Negative Token Merging: Image-based Adversarial Feature Guidance
por: Singh, Jaskirat, et al.
Publicado: (2024)

Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
por: Lee, Dong Hoon, et al.
Publicado: (2024)

MaMe & MaRe: Matrix-Based Token Merging and Restoration for Efficient Visual Perception and Synthesis
por: Huo, Simin, et al.
Publicado: (2026)

Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
por: Shao, Run, et al.
Publicado: (2024)

What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
por: Kang, Inha, et al.
Publicado: (2025)

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
por: Chen, Dongyang, et al.
Publicado: (2026)

Composed Vision-Language Retrieval for Skin Cancer Case Search via Joint Alignment of Global and Local Representations
por: Wang, Yuheng, et al.
Publicado: (2026)

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
por: Qu, Liao, et al.
Publicado: (2024)

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
por: Hyun, Jeongseok, et al.
Publicado: (2025)

RoboEye: Enhancing 2D Robotic Object Identification with Selective 3D Geometric Keypoint Matching
por: Zhang, Xingwu, et al.
Publicado: (2025)

Hita: Holistic Tokenizer for Autoregressive Image Generation
por: Zheng, Anlin, et al.
Publicado: (2025)

ProMerge: Prompt and Merge for Unsupervised Instance Segmentation
por: Li, Dylan, et al.
Publicado: (2024)

ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
por: Li, Lingen, et al.
Publicado: (2025)