Imagen de Portada

Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wen, Ziqi, Madinei, Parsa, Eckstein, Miguel P.
Formato:	Preprint
Publicado:	2026
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

DReX: Pure Vision Fusion of Self-Supervised and Convolutional Representations for Image Complexity Prediction
por: Skaza, Jonathan, et al.
Publicado: (2025)

Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding
por: Murlidaran, Shravan, et al.
Publicado: (2026)

INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models
por: Madinei, Parsa, et al.
Publicado: (2025)

IRIS: Intent Resolution via Inference-time Saccades for Open-Ended VQA in Large Vision-Language Models
por: Madinei, Parsa, et al.
Publicado: (2026)

City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning
por: Sun, Penglei, et al.
Publicado: (2025)

Sim2Radar: Toward Bridging the Radar Sim-to-Real Gap with VLM-Guided Scene Reconstruction
por: Bejerano, Emily, et al.
Publicado: (2026)

Revealing the Semantic Selection Gap in DINOv3 through Training-Free Few-Shot Segmentation
por: Zakir, Hussni Mohd, et al.
Publicado: (2026)

Saliency Suppressed, Semantics Surfaced: Visual Transformations in Neural Networks and the Brain
por: Opiełka, Gustaw, et al.
Publicado: (2024)

RE-VLM: Event-Augmented Vision-Language Model for Scene Understanding
por: Liu, Hanqing, et al.
Publicado: (2026)

SUM: Saliency Unification through Mamba for Visual Attention Modeling
por: Hosseini, Alireza, et al.
Publicado: (2024)

Generalist Multimodal LLMs Gain Biometric Expertise via Human Salience
por: Piland, Jacob, et al.
Publicado: (2026)

Structure Your Data: Towards Semantic Graph Counterfactuals
por: Dimitriou, Angeliki, et al.
Publicado: (2024)

Belief-Aware VLM Model for Human-like Reasoning
por: Nayak, Anshul, et al.
Publicado: (2026)

Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps
por: Wen, Ziqi, et al.
Publicado: (2025)

Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding
por: Mao, Shunqi, et al.
Publicado: (2025)

InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement
por: Zou, Yude, et al.
Publicado: (2026)

UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception
por: Chen, Chuang, et al.
Publicado: (2024)

CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception
por: Carvalho, Miguel, et al.
Publicado: (2025)

Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning
por: Wang, Wentao, et al.
Publicado: (2025)

From Local Cues to Global Percepts: Emergent Gestalt Organization in Self-Supervised Vision Models
por: Li, Tianqin, et al.
Publicado: (2025)

Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
por: Wei, Zhihua, et al.
Publicado: (2026)

FaceSaliencyAug: Mitigating Geographic, Gender and Stereotypical Biases via Saliency-Based Data Augmentation
por: Kumar, Teerath, et al.
Publicado: (2024)

Privacy-Concealing Cooperative Perception for BEV Scene Segmentation
por: Wang, Song, et al.
Publicado: (2026)

Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
por: Wu, Qiangqiang, et al.
Publicado: (2026)

VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysis
por: Kang, Donggoo, et al.
Publicado: (2024)

SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion
por: Cho, Jungbin, et al.
Publicado: (2025)

Diffusion Counterfactual Generation with Semantic Abduction
por: Rasal, Rajat, et al.
Publicado: (2025)

Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
por: Hermosilla, Pedro, et al.
Publicado: (2025)

Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding
por: Pani, Anupam, et al.
Publicado: (2025)

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
por: Xun, Yuan, et al.
Publicado: (2024)

PerspectiveNet: Multi-View Perception for Dynamic Scene Understanding
por: Nguyen, Vinh
Publicado: (2024)

MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models
por: Wang, Kangkang, et al.
Publicado: (2026)

Salience Adjustment for Context-Based Emotion Recognition
por: Han, Bin, et al.
Publicado: (2025)

Diffusion Features to Bridge Domain Gap for Semantic Segmentation
por: Ji, Yuxiang, et al.
Publicado: (2024)

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
por: Liu, Tianhui, et al.
Publicado: (2026)

See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent
por: Tang, Tianci, et al.
Publicado: (2026)

BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion
por: Kim, Gwanghyun, et al.
Publicado: (2024)

DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
por: Singh, Aditya Kumar, et al.
Publicado: (2026)

edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer
por: Qian, Chen, et al.
Publicado: (2025)

MANTA: Cross-Modal Semantic Alignment and Information-Theoretic Optimization for Long-form Multimodal Understanding
por: Zhong, Ziqi, et al.
Publicado: (2025)