Scene Understanding

Mask-Homo: Pseudo Plane Mask-Guided Unsupervised Multi-Homography Estimation AAAI 2024 MemoNav: Working Memory Model for Visual Navigation CVPR 2024 Memorize What Matters: Emergent Scene Decomposition from Multitraverse NeurIPS 2024 Memory-based Adapters for Online 3D Scene Perception CVPR 2024 MESA: Matching Everything by Segmenting Anything CVPR 2024 MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding CVPR 2024 Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation CVPR 2024 Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers ICML 2024 Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding EMNLP 2024 Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition NeurIPS 2024 Multi-Dimensional Hyena for Spatial Inductive Bias AISTATS 2024 Multimodal Event Causality Reasoning with Scene Graph Enhanced Interaction Network AAAI 2024 Multi-Modal Prompting for Open-Vocabulary Video Visual Relationship Detection AAAI 2024 Multi-Prototype Space Learning for Commonsense-Based Scene Graph Generation AAAI 2024 Multi-View Dynamic Reflection Prior for Video Glass Surface Detection AAAI 2024 Multiview Scene Graph NeurIPS 2024 MVP-Bench: Can Large Vision-Language Models Conduct Multi-level Visual Perception Like Humans? EMNLP 2024 Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes AAAI 2024 Neighbor Relations Matter in Video Scene Detection CVPR 2024 NightCC: Nighttime Color Constancy via Adaptive Channel Masking CVPR 2024 NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interaction WACV 2024 Noisy One-point Homographies are Surprisingly Good CVPR 2024 No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation CVPR 2024 Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling CVPR 2024 Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition EMNLP 2024