Showing 21–40 of 52 results
/ Date/ Name
Sep 4, 2021Semantics-Guided Contrastive Network for Zero-Shot Object detectionJan 25, 2025Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line DetectionOct 27, 2024Historical Test-time Prompt Tuning for Vision Foundation ModelsMay 13, 2024MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked AutoencodersMar 7, 2025Data-Efficient Generalization for Zero-shot Composed Image RetrievalDec 8, 2025MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale AdaptationFeb 25, 2026GeoMotion: Rethinking Motion Segmentation via Latent 4D GeometrySep 24, 2020Self-Weighted Robust LDA for Multiclass Classification with Edge ClassesFeb 9, 2021Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkJun 30, 2022UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask CalibrationMar 12, 2024Masked AutoDecoder is Effective Multi-Task Vision GeneralistAug 29, 2023Pose-Free Neural Radiance Fields via Implicit Pose RegularizationApr 18, 2024An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-TrainingMay 22, 2024One-shot Training for Video Object SegmentationOct 13, 2024LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language ModelsApr 30, 2016Constructive neural network learningMay 24, 2025ToDRE: Effective Visual Token Pruning via Token Diversity and Task RelevanceOct 16, 2025Spatial Preference Rewarding for MLLMs Spatial UnderstandingSep 15, 2025From Evaluation to Enhancement: Large Language Models for Zero-Knowledge Proof Code GenerationJun 9, 2024Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-training