Imagen de Portada

HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQA

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dibitonto, Francesco, Beyan, Cigdem, Murino, Vittorio
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MADPOT: Medical Anomaly Detection with CLIP Adaptation and Partial Optimal Transport
por: Shiri, Mahshid, et al.
Publicado: (2025)

MadCLIP: Few-shot Medical Anomaly Detection with CLIP
por: Shiri, Mahshid, et al.
Publicado: (2025)

Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions
por: Olivato, Francesco, et al.
Publicado: (2026)

Upper-Body Pose-based Gaze Estimation for Privacy-Preserving 3D Gaze Target Detection
por: Toaiari, Andrea, et al.
Publicado: (2024)

Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment
por: Yu, Fanqi, et al.
Publicado: (2026)

Anticipating Next Active Objects for Egocentric Videos
por: Thakur, Sanket, et al.
Publicado: (2023)

CLIP-VAD: Exploiting Vision-Language Models for Voice Activity Detection
por: Appiani, Andrea, et al.
Publicado: (2024)

AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation
por: Fang, Qingqing, et al.
Publicado: (2025)

Geometry-Conditioned Diffusion for Occlusion-Robust In-Bed Pose Estimation
por: Khameneh, Navid Aslankhani, et al.
Publicado: (2026)

Towards Unconstrained Human-Object Interaction
por: Tonini, Francesco, et al.
Publicado: (2026)

Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection
por: Tonini, Francesco, et al.
Publicado: (2025)

CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition
por: Alyami, Sarah, et al.
Publicado: (2025)

AL-GTD: Deep Active Learning for Gaze Target Detection
por: Tonini, Francesco, et al.
Publicado: (2024)

Model Debiasing by Learnable Data Augmentation
por: Morerio, Pietro, et al.
Publicado: (2024)

Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
por: Zhao, Shuai, et al.
Publicado: (2023)

Transductive Zero-Shot and Few-Shot CLIP
por: Martin, Ségolène, et al.
Publicado: (2024)

VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving
por: Liu, Yibo, et al.
Publicado: (2024)

Zero-Shot Class Unlearning in CLIP with Synthetic Samples
por: Kravets, A., et al.
Publicado: (2024)

CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation
por: Ali, Muhammad, et al.
Publicado: (2024)

AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection
por: Cao, Yunkang, et al.
Publicado: (2024)

Exploring Fine-grained Retail Product Discrimination with Zero-shot Object Classification Using Vision-Language Models
por: Tur, Anil Osman, et al.
Publicado: (2024)

Online Zero-Shot Classification with CLIP
por: Qian, Qi, et al.
Publicado: (2024)

Rethinking Visual Content Refinement in Low-Shot CLIP Adaptation
por: Lu, Jinda, et al.
Publicado: (2024)

Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
por: Zhang, Zhaoxiang, et al.
Publicado: (2024)

Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation
por: Li, Lin, et al.
Publicado: (2026)

CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression
por: Zhang, Kangjie, et al.
Publicado: (2026)

Erasing CLIP Memories: Non-Destructive, Data-Free Zero-Shot class Unlearning in CLIP Models
por: Mishra, Ashish, et al.
Publicado: (2025)

MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition
por: Xing, Jiazheng, et al.
Publicado: (2023)

MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning
por: Wang, Yue, et al.
Publicado: (2025)

TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification
por: Munir, Ans, et al.
Publicado: (2025)

Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks
por: Serez, Dario, et al.
Publicado: (2024)

A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation
por: Serez, Dario, et al.
Publicado: (2025)

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
por: Dehdashtian, Sepehr, et al.
Publicado: (2024)

Infrared Domain Adaptation with Zero-Shot Quantization
por: Sevsay, Burak, et al.
Publicado: (2024)

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance
por: Zhuang, Jiedong, et al.
Publicado: (2024)

Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
por: Sammani, Fawaz, et al.
Publicado: (2024)

Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts
por: Hou, Yanning, et al.
Publicado: (2025)

SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels
por: Singh, Darshan, et al.
Publicado: (2024)

Zero-Shot Styled Text Image Generation, but Make It Autoregressive
por: Pippi, Vittorio, et al.
Publicado: (2025)

PERL: Parameter Efficient Reasoning in CLIP Latent Space
por: Carnemolla, Simone, et al.
Publicado: (2026)