Image de couverture de livre

Cross-Stage Coherence in Hierarchical Driving VQA: Explicit Baselines and Learned Gated Context Projectors

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jain, Gautam Kumar, Markgraf, Carsten, Stähler, Julian
Format:	Preprint
Publié:	2026
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

VQA-Levels: A Hierarchical Approach for Classifying Questions in VQA
par: Madaka, Madhuri Latha, et autres
Publié: (2025)

Box-QAymo: Box-Referring VQA Dataset for Autonomous Driving
par: Etchegaray, Djamahl, et autres
Publié: (2025)

DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents
par: Chen, Yixiong, et autres
Publié: (2026)

Understanding the Role of the Projector in Knowledge Distillation
par: Miles, Roy, et autres
Publié: (2023)

Kvasir-VQA: A Text-Image Pair GI Tract Dataset
par: Gautam, Sushant, et autres
Publié: (2024)

A Multimodal-Multitask Framework with Cross-modal Relation and Hierarchical Interactive Attention for Semantic Comprehension
par: Rehman, Mohammad Zia Ur, et autres
Publié: (2025)

Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection
par: Yu, Cai, et autres
Publié: (2024)

Context-Gated Cross-Modal Perception with Visual Mamba for PET-CT Lung Tumor Segmentation
par: Ayllón, Elena Mulero, et autres
Publié: (2025)

HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification
par: Stoimchev, Marjan, et autres
Publié: (2026)

Caption First, VQA Second: Knowledge Density, Not Task Format, Drives Multimodal Scaling
par: Zou, Hongjian, et autres
Publié: (2026)

Improving VQA Reliability: A Dual-Assessment Approach with Self-Reflection and Cross-Model Verification
par: Wu, Xixian, et autres
Publié: (2025)

Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector
par: Zu, Wenqiang, et autres
Publié: (2026)

Device-aware Optical Adversarial Attack for a Portable Projector-camera System
par: Jiang, Ning, et autres
Publié: (2025)

QMoP: Query Guided Mixture-of-Projector for Efficient Visual Token Compression
par: Li, Zhongyang, et autres
Publié: (2026)

LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
par: Sun, Boyuan, et autres
Publié: (2025)

Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation
par: Yang, Xiaobo, et autres
Publié: (2025)

Hyperspectral Imaging-Based Perception in Autonomous Driving Scenarios: Benchmarking Baseline Semantic Segmentation Models
par: Shah, Imad Ali, et autres
Publié: (2024)

Is ChatGPT-5 Ready for Mammogram VQA?
par: Li, Qiang, et autres
Publié: (2025)

Advancing Surgical VQA with Scene Graph Knowledge
par: Yuan, Kun, et autres
Publié: (2023)

Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru
par: Cusipuma, Dunant, et autres
Publié: (2025)

Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA
par: Xu, Zibo, et autres
Publié: (2026)

Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA
par: Pandey, Ayush, et autres
Publié: (2025)

DriveGenVLM: Real-world Video Generation for Vision Language Model based Autonomous Driving
par: Fu, Yongjie, et autres
Publié: (2024)

An Evaluation of GPT-4V and Gemini in Online VQA
par: Liu, Mengchen, et autres
Publié: (2023)

KNVQA: A Benchmark for evaluation knowledge-based VQA
par: Cheng, Sirui, et autres
Publié: (2023)

SkeleGuide: Explicit Skeleton Reasoning for Context-Aware Human-in-Place Image Synthesis
par: Wu, Chuqiao, et autres
Publié: (2026)

Back to the Baseline: Examining Baseline Effects on Explainability Metrics
par: Picard, Agustin Martin, et autres
Publié: (2025)

Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning
par: Wang, Xiao, et autres
Publié: (2025)

A Framework for Cross-Domain Generalization in Coronary Artery Calcium Scoring Across Gated and Non-Gated Computed Tomography
par: Gokmen, Mahmut S., et autres
Publié: (2026)

ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization
par: Mohammadshirazi, Ahmad, et autres
Publié: (2025)

R^3-VQA: "Read the Room" by Video Social Reasoning
par: Niu, Lixing, et autres
Publié: (2025)

MISS: A Generative Pretraining and Finetuning Approach for Med-VQA
par: Chen, Jiawei, et autres
Publié: (2024)

Better Supervised Fine-tuning for VQA: Integer-Only Loss
par: Qian, Baihong, et autres
Publié: (2025)

VQA$^2$: Visual Question Answering for Video Quality Assessment
par: Jia, Ziheng, et autres
Publié: (2024)

AID4AD: Aerial Image Data for Automated Driving Perception
par: Lengerer, Daniel, et autres
Publié: (2025)

A Data-Centric Vision Transformer Baseline for SAR Sea Ice Classification
par: Mike-Ewewie, David, et autres
Publié: (2026)

Fast globally optimal Truncated Least Squares point cloud registration with fixed rotation axis
par: Ivanov, Ivo, et autres
Publié: (2025)

LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering
par: Zhu, Wenkai, et autres
Publié: (2025)

${C}^{3}$-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting
par: Hu, Yuxi, et autres
Publié: (2025)

GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting
par: Wu, Yuzhe, et autres
Publié: (2024)