Entities · Models
CLIP
70 articles tagged with this entity.
-
InfraQR: Edge-Placed QR-Inspired Structured Patch Attacks on Infrared Vision-Language Models
-
MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation
-
AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models
-
Repurposing CLIP to Localize at Pixel Level
-
Road-Aware Anomaly Segmentation with Query-Guided Polygons and CLIP in Autonomous Driving
-
HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
-
A Controlled Study of CLIP-Based Body-Scene Fusion for Emotion Recognition in Context
-
The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models
-
Vortex: Multi-Modal Fusion System for Intelligent Video Retrieval
-
Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP Backdoors
-
Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability
-
Zero-Shot Captioning for Cultural Heritage: Automated Image Analysis of Traditional Indonesian Clothing
-
Textual Supervision Enhances Geospatial Representations in Vision-Language Models
-
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
-
UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning
-
BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding
-
Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models
-
KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models
-
OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery
-
VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding
-
ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search
-
Planktonzilla: Multimodal dataset and models for understanding plankton ecosystems
-
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
-
Calibrating Uncertainty for Zero-Shot Adversarial CLIP
-
Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
-
Domain Adaptation with a Single Vision-Language Embedding
-
Scaling Pre-training to One Hundred Billion Data for Vision Language Models
-
CLIP-like Model as a Foundational Density Ratio Estimator
-
Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection
-
How can embedding models bind concepts?
-
IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
-
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
-
AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection
-
Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
-
BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression
-
TRACER: Persistent Regularization for Robust Multimodal Finetuning
-
DebFilter: Eradicating Biases Stashed in Value
-
Representation-Conditioned Diffusion Models for Guided Training Data Generation
-
EntroAD: Structural Entropy-Guided Prompt Adaptation for Zero-Shot Anomaly Detection
-
DiagramBank: A Quality-Audited Dataset of Scientific Schematic Diagrams with Multi-Level Document Context
-
Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
-
Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data
-
Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights
-
From Attribution to Action: A Human-Centered Application of Activation Steering
-
Once-For-All: A Train-Once and Select-Anytime Framework for Multimodal Instruction Tuning
-
SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking
-
GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning
-
Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection
-
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
-
FairJudge: Abstention-Aware Multimodal Judges for Fairness and Alignment Evaluation in Text-to-Image Models
-
Brain-to-Image Retrieval and Reconstruction via Multimodal EEG Alignment
-
Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP
-
TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
-
Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
-
R5DGS: Semantic-Aware 4D Gaussian Splatting with Rigid Body Constraints for Efficient Dynamic Scene Reconstruction
-
[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
-
CMAP: Cross-Modal Adaptive Prompting for Multi-Domain Task-Incremental Learning
-
Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference
-
CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation
-
Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
-
Semantic-Aware Guided Drone Exploration for Language-Conditioned 3D Indoor Mapping
-
On the Provable Importance of Gradients for Language-Assisted Image Clustering
-
LaCoVL-FER: Landmark-Guided Contrastive Learning Network with Vision-Language Enhancement for Facial Expression Recognition
-
Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
-
Semantic Alignment in Hyperbolic Space for Open-Vocabulary Semantic Segmentation
-
Rethinking the Global Knowledge of CLIP in Training-Free Open-Vocabulary Semantic Segmentation
-
Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition
-
Language-Conditioned Visual Grounding with CLIP Multilingual
-
Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision-Language Models
-
CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection