Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation
Comments Accepted to CVPR 2025 (Highlight)
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach
Journal ref Computer Vision and Pattern Recognition Conference (CVPR) 2025
InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception
Comments 14 pages, accepted by CVPR 2025 as poster
Reference-Based 3D-Aware Image Editing with Triplanes
Comments CVPR 2025 Highlight. Includes supplementary material
Uncertainty Quantification for Gradient-based Explanations in Neural Networks
Comments 13 pages, 11 figures, UNCV @ CVPR 2025 Camera ready
GarmentTracking: Category-Level Garment Pose Tracking
Comments CVPR 2023
MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data
Comments Accepted at CVPR 2025 Workshop MORSE
LMFormer: Lane based Motion Prediction Transformer
Comments Accepted: Autonomous Driving Workshop, CVPR 2025
Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models
Journal ref The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
Comments Accepted to CVPR 2025, codes in process
Efficient 2D to Full 3D Human Pose Uplifting including Joint Rotations
Comments accepted at CVSports@CVPR'25
Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimization
Comments Accepted to CVPR 2025 Workshop on 2nd MEIS
Improving Multimodal Hateful Meme Detection Exploiting LMM-Generated Knowledge
Comments Accepted for publication, Multimodal Learning and Applications Workshop (MULA 2025) @ IEEE/CVF CVPR 2025, Nashville, TN, USA, June 2025. This is the authors' "accepted version"
VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents
Comments Accepted by CVPR 2025; project page: https://vdocrag.github.io
Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding
Comments Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images
Comments Accepted by CVPR 2025
Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training
Comments 10 pages, 5 figures. Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025
Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation
Comments Accepted to CVPR 2025 workshop
DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
Comments Accepted by CVPR 2025
AerOSeg: Harnessing SAM for Open-Vocabulary Segmentation in Remote Sensing Images
Comments Accepted at EarthVision workshop, CVPR 2025
ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking
Comments Accepted CVPR 2025 Workshop on Distillation of Foundation Models for Autonomous Driving
SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow
Comments Accepted by CVPR 2025
BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting
Comments Accepted to CVPR 2025
RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection
Comments CVPR 2025
Segment Any Motion in Videos
Comments CVPR 2025. Website: https://motion-seg.github.io/
Detecting Localized Deepfake Manipulations Using Action Unit-Guided Video Representations
Comments Accepted to CVPR-W 2025
Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models
Comments CVPR 2025
Ref-GS: Directional Factorization for 2D Gaussian Splatting
Comments CVPR 2025. Project page: https://ref-gs.github.io/
Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes
Comments accepted for CVSports@CVPR'25
MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training
Comments CVPR 2025 HuMoGen Workshop
