Papers Scene Recognition
“Scene Recognition” 태그가 달린 논문 222편 · 필터 해제
A Comparative Study of Label-free Representation Quality Metrics in Deep Learning
We present a comparative study of label-free metrics for assessing the quality of representations in deep neural networks to understand their reliability under a wide variety of configurations. We group existing label-fr…
Scene RecognitionRethinking Text-to-Image as Semantic-Aware Data Augmentation for Indoor Scene Recognition
In the realm of computer vision, indoor image recognition presents challenges due to the intricate interplay of lighting conditions, occlusions, and diverse object arrangements within confined spaces. To address the lack…
Data AugmentationScene RecognitionPairWise Image Finder: An Open-source Tool for Finding Visually Aligned Street-Level Image Pairs for Urban Perception Studies
Change detection and scene recognition techniques have been widely applied to Street View Imagery (SVI) to understand changes in scenes across the years. However, metadata alone is often insufficient to reliably find vis…
Semantic SegmentationScene RecognitionChange DetectionClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison
Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be bot…
Reinforcement LearningScene RecognitionImage CaptioningObject CountingBeyond Logit Adjustment: A Residual Decomposition Framework for Long-Tailed Reranking
Long-tailed classification, where a small number of frequent classes dominate many rare ones, remains challenging because models systematically favor frequent classes at inference time. Existing post-hoc methods such as …
Image ClassificationScene RecognitionDynamic Graph Neural Network with Adaptive Features Selection for RGB-D Based Indoor Scene Recognition
Multi-modality of color and depth, i.e., RGB-D, is of great importance in recent research of indoor scene recognition. In this kind of data representation, depth map is able to describe the 3D structure of scenes and geo…
Graph Neural NetworkScene RecognitionHow Class Ontology and Data Scale Affect Audio Transfer Learning
Transfer learning is a crucial concept within deep learning that allows artificial neural networks to benefit from a large pre-training data basis when confronted with a task of limited data. Despite its ubiquitous use a…
Activity RecognitionTransfer LearningScene RecognitionReal Eyes Realize Faster: Gaze Stability and Pupil Novelty for Efficient Egocentric Learning
Always-on egocentric cameras are increasingly used as demonstrations for embodied robotics, imitation learning, and assistive AR, but the resulting video streams are dominated by redundant and low-quality frames. Under t…
Activity RecognitionScene RecognitionA Case Study on Concept Induction for Neuron-Level Interpretability in CNN
Deep Neural Networks (DNNs) have advanced applications in domains such as healthcare, autonomous systems, and scene understanding, yet the internal semantics of their hidden neurons remain poorly understood. Prior work i…
Scene UnderstandingScene RecognitionLLM-Driven Scenario-Aware Planning for Autonomous Driving
Hybrid planner switching framework (HPSF) for autonomous driving needs to reconcile high-speed driving efficiency with safe maneuvering in dense traffic. Existing HPSF methods often fail to make reliable mode transitions…
Scene UnderstandingAutonomous DrivingScene RecognitionMotion PlanningTIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment
While visual-language models have profoundly linked features between texts and images, the incorporation of 3D modality data, such as point clouds and 3D Gaussians, further enables pretraining for 3D-related tasks, e.g.,…
Cross-Modal RetrievalScene RecognitionPoint CloudsHierarchical Fusion of Local and Global Visual Features with Mixture-of-Experts for Remote Sensing Image Scene Classification
Remote sensing image scene classification remains a challenging task, primarily due to the complex spatial structures and multi-scale characteristics of ground objects. Although CNN-based methods excel at extracting loca…
Scene ClassificationScene RecognitionA Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation
Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific …
Semantic SegmentationScene UnderstandingScene RecognitionEnhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
Recent advances in vision foundation models, such as the Segment Anything Model (SAM) and its successor SAM2, have achieved state-of-the-art performance on general image segmentation benchmarks. However, these models str…
Medical Image SegmentationAutonomous DrivingScene RecognitionLMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving
Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existing methods primarily fine-tune VLMs on o…
Scene UnderstandingAutonomous DrivingScene RecognitionOpen-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments
The global rise in the number of people with physical disabilities, in part due to improvements in post-trauma survivorship and longevity, has amplified the demand for advanced assistive technologies to improve mobility …
NavigateOpen Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationScene Classification+4Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition
Maritime Multi-Scene Recognition is crucial for enhancing the capabilities of intelligent marine robotics, particularly in applications such as marine conservation, environmental monitoring, and disaster response. Howeve…
Disaster ResponseLarge Language ModelMultimodal Large Language ModelQuantization+1Contrastive Visual Data Augmentation
Large multimodal models (LMMs) often struggle to recognize novel concepts, as they rely on pre-trained knowledge and have limited ability to capture subtle visual details. Domain-specific knowledge gaps in training also …
Data AugmentationNovel ConceptsScene RecognitionAdvancing ALS Applications with Large-Scale Pre-training: Dataset Development and Downstream Assessment
The pre-training and fine-tuning paradigm has revolutionized satellite remote sensing applications. However, this approach remains largely underexplored for airborne laser scanning (ALS), an important technology for appl…
Scene RecognitionSelf-Supervised LearningSemantic SegmentationSeeing with Partial Certainty: Conformal Prediction for Robotic Scene Recognition in Built Environments
In assistive robotics serving people with disabilities (PWD), accurate place recognition in built environments is crucial to ensure that robots navigate and interact safely within diverse indoor spaces. Language interfac…
Conformal PredictionHallucinationNavigateScene Recognition