Image de couverture de livre

Dissecting Query-Key Interaction in Vision Transformers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pan, Xu, Philip, Aaron, Xie, Ziqian, Schwartz, Odelia
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Enhancing Vision Transformer Explainability Using Artificial Astrocytes
par: Echevarrieta-Catalan, Nicolas, et autres
Publié: (2025)

Category Query Learning for Human-Object Interaction Classification
par: Xie, Chi, et autres
Publié: (2023)

QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
par: Zhang, Yudong, et autres
Publié: (2025)

EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers
par: Liao, Wenwen, et autres
Publié: (2026)

STARFISH: faST Accuracy Recovery in pruned networks From Internal State Healing
par: Maon, Shir, et autres
Publié: (2026)

Hybrid Spiking Vision Transformer for Object Detection with Event Cameras
par: Xu, Qi, et autres
Publié: (2025)

Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion
par: Rawal, Ishaan Singh, et autres
Publié: (2023)

SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision
par: Vani, Ankit, et autres
Publié: (2024)

Representation Separation for Semantic Segmentation with Vision Transformers
par: Hong, Yuanduo, et autres
Publié: (2022)

PDZSeg: Adapting the Foundation Model for Dissection Zone Segmentation with Visual Prompts in Robot-assisted Endoscopic Submucosal Dissection
par: Xu, Mengya, et autres
Publié: (2024)

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
par: Tan, Haoyue, et autres
Publié: (2026)

GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values
par: Javadi, Farnoosh, et autres
Publié: (2023)

Improving Skeleton-based Action Recognition with Interactive Object Information
par: Wen, Hao, et autres
Publié: (2025)

Dynamic Object Queries for Transformer-based Incremental Object Detection
par: Zhang, Jichuan, et autres
Publié: (2024)

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models
par: Wang, Zhiqiang, et autres
Publié: (2026)

AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
par: Yuan, Kaishen, et autres
Publié: (2024)

VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models
par: Gao, Chongkai, et autres
Publié: (2025)

Structured Click Control in Transformer-based Interactive Segmentation
par: Xu, Long, et autres
Publié: (2024)

Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models
par: Im, Eun Woo, et autres
Publié: (2025)

Towards Robust Vision Transformer via Masked Adaptive Ensemble
par: Lin, Fudong, et autres
Publié: (2024)

See then Tell: Enhancing Key Information Extraction with Vision Grounding
par: Liu, Shuhang, et autres
Publié: (2024)

IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning
par: Yin, Qian, et autres
Publié: (2026)

MADTempo: An Interactive System for Multi-Event Temporal Video Retrieval with Query Augmentation
par: Vu, Huu-An, et autres
Publié: (2025)

Benchmarking Unlearning for Vision Transformers
par: Zhao, Kairan, et autres
Publié: (2026)

Vision Bridge Transformer at Scale
par: Tan, Zhenxiong, et autres
Publié: (2025)

Localizing Events in Videos with Multimodal Queries
par: Zhang, Gengyuan, et autres
Publié: (2024)

Heatmap Guided Query Transformers for Robust Astrocyte Detection across Immunostains and Resolutions
par: Zhang, Xizhe, et autres
Publié: (2025)

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models
par: Choi, Dasol, et autres
Publié: (2026)

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
par: Xie, Yuxi, et autres
Publié: (2024)

Sensitive Image Classification by Vision Transformers
par: He, Hanxian, et autres
Publié: (2024)

The Linear Attention Resurrection in Vision Transformer
par: Zheng, Chuanyang
Publié: (2025)

Weierstrass Positional Encoding for Vision Transformers
par: Xin, Zhihang, et autres
Publié: (2026)

Spiking Vision Transformer with Saccadic Attention
par: Wang, Shuai, et autres
Publié: (2025)

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference
par: Kang, Beomseok, et autres
Publié: (2026)

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
par: Xu, Xuwei, et autres
Publié: (2023)

Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
par: Dong, Wei, et autres
Publié: (2024)

3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
par: Oh, Gyeongrok, et autres
Publié: (2025)

3D Motion Perception of Binocular Vision Target with PID-CNN
par: Shi, Jiazhao, et autres
Publié: (2025)

Cross-Layer Vision Smoothing: Enhancing Visual Understanding via Sustained Focus on Key Objects in Large Vision-Language Models
par: Zhao, Jianfei, et autres
Publié: (2025)

Mixed Non-linear Quantization for Vision Transformers
par: Kim, Gihwan, et autres
Publié: (2024)