Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
Comments Camera-ready version for CVPR 2025 (with Supp.Mat.)
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration
Comments CVPR 2025
Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection
Comments accepted by CVPR 2025
Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation
Comments Accepted by CVPR 2025
From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech
Comments CVPR 2025, demo page: https://mm.kaist.ac.kr/projects/faces2voices/
Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks
Comments CVPR 2025
Temporal Action Detection Model Compression by Progressive Block Drop
Comments Accepted to CVPR 2025
Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification
Comments CVPR 2025 Accepted
LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models
Comments Accepted by CVPR 2025
QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
Comments Accepted by CVPR 2025
SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
Comments CVPR 2025
When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach
Comments Accepted at CVPR 2025 (Main Conference)
A General Adaptive Dual-level Weighting Mechanism for Remote Sensing Pansharpening
Comments This paper is accepted at the CVPR Conference on Computer Vision and Pattern Recognition 2025
HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views
Comments 16 pages, 13 figures, 10 tables, Accepted to CVPR 2025
Matrix3D: Large Photogrammetry Model All-in-One
Comments CVPR 2025 camera ready. Project Page: https://nju-3dv.github.io/projects/matrix3d
EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
Comments Accepted by CVPR 2025
VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification
Comments Accepted by CVPR 2025
Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization
Comments CVPR 2025
You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
Comments Accepted by CVPR 2025, Project Page: https://vision.baai.ac.cn/see3d
Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection
Comments Accepted by CVPR 2025. Project page: https://zhoues.github.io/Code-as-Monitor/
SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning
Comments CVPR 2025 Project page: https://ysj9909.github.io/SoRA.github.io/
Number it: Temporal Grounding Videos like Flipping Manga
Comments Accepted by CVPR 2025
3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination
Comments CVPR 2025. Project website: https://3d-grand.github.io
GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Comments CVPR 2025
Sonata: Self-Supervised Learning of Reliable Point Representations
Comments CVPR 2025, produced by Pointcept x Meta, project page: https://xywu.me/sonata/
VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness
Comments Accepted at CVPR 2025, code : https://github.com/SeungJuCha/VerbDiff.git
From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning
Comments Accepted to CVPR 2025
Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing
Comments Accepted by CVPR 2025
Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection
Comments Accepted by CVPR 2025
Probabilistic Prompt Distribution Learning for Animal Pose Estimation
Comments Accepted by CVPR 2025
