Description: Salient Object Detection for Point Clouds.- Learning Semantic Segmentation from Multiple Datasets with Label Shifts.- Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination.- Towards Open-Vocabulary Scene Graph Generation with Prompt-Based Finetuning.- Variance-Aware Weight Initialization for Point Convolutional Neural Networks.- Break and Make: Interactive Structural Understanding Using LEGO Bricks.- Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation.- 3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching.- Video Restoration Framework and Its Meta-Adaptations to Data-Poor Conditions.- MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud.- Scene Text Recognition with Permuted Autoregressive Sequence Models.- When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition.- Detecting Tampered Scene Text in the Wild.- Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning.- GLASS: Global to Local Attention for Scene-Text Spotting.- COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts.- Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting.- Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition.- Levenshtein OCR.- Multi-Granularity Prediction for Scene Text Recognition.- Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting.- Contextual Text Block Detection towards Scene Text Understanding.- CoMER: Modeling Coverage for Transformer-Based Handwritten Mathematical Expression Recognition.- Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context.- TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers.- Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features.- SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition.- Pure Transformer with Integrated Experts for Scene Text Recognition.- OCR-Free Document Understanding Transformer.- CAR: Class-Aware Regularizations for Semantic Segmentation.- Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation.- SeqFormer: Sequential Transformer for Video Instance Segmentation.- Saliency Hierarchy Modeling via Generative Kernels for Salient Object Detection.- In Defense of Online Models for Video Instance Segmentation.- Active Pointly-Supervised Instance Segmentation.- A Transformer-Based Decoder for Semantic Segmentation with Multi-level Context Mining.- XMem: Long-Term Video Object Segmentation with an Atkinson- Shiffrin Memory Model.- Self-Distillation for Robust LiDAR Semantic Segmentation in Autonomous Driving.- 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds.- Extract Free Dense Labels from CLIP.- 3D Compositional Zero-Shot Learning with DeCompositional Consensus.- Video Mask Transfiner for High-Quality Video Instance Segmentation.

Please Wait