Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
Comments Accepted by CVPR 2025
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
Comments CVPR 2025; First three authors contributed equally; Project page: https://videotree2024.github.io/
Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
Comments CVPR 2025. Project page: https://compvis.github.io/attribute-control
NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval
Comments Accepted at CVPR 2025, 18 pages, 7 figures, 13 tables
HSEmotion Team at ABAW-8 Competition: Audiovisual Ambivalence/Hesitancy, Emotional Mimicry Intensity and Facial Expression Recognition
Comments submitted to ABAW CVPR 2025 Workshop
ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
Comments Accepted at CVPR 2025
BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
Comments Accepted by CVPR 2025
Arbitrary-steps Image Super-resolution via Diffusion Inversion
Comments Accepted by CVPR 2025. Project: https://github.com/zsyOAOA/InvSR
Complexity Experts are Task-Discriminative Learners for Any Image Restoration
Comments Accepted at CVPR 2025
Towards Generalizable Scene Change Detection
Comments Camera-ready version. Accepted to CVPR 2025
Unlocking Generalization Power in LiDAR Point Cloud Registration
Comments Accepted by CVPR 2025
GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping
Comments This paper is accepted by CVPR 2025. Project page is available at https://liujf1226.github.io/GaussHDR
Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
Comments IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
MetricGrids: Arbitrary Nonlinear Approximation with Elementary Metric Grids based Implicit Neural Representation
Comments accepted by CVPR 2025
Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes
Comments Accepted by CVPR 2025
Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification
Comments CVPR 2025. Project website: https://github.com/sssaury/HAM
MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation
Comments Accepted to CVPR 2025
Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models
Comments CVPR 2025. Project page: https://silent-branding.github.io/
DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting
Comments CVPR 2025
DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
Comments [CVPR 2025] The project page is https://jianzongwu.github.io/projects/diffsensei/
Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
Comments Accepted by CVPR 2025
Enhancing Vision-Language Pre-training with Rich Supervisions
Comments Accepted to CVPR 2024
Non-autoregressive Sequence-to-Sequence Vision-Language Models
Comments Accepted to CVPR 2024
$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect
Comments CVPR 2025
SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment
Comments CVPR 2025. 1st Place @ CARLA Challenge 2024. Challenge tech report (preliminary version of SimLingo): arXiv:2406.10165
Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis
Comments Accepted at CVPR 2025, 41 pages, 37 figures, 8 tables
DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction
Comments Accepted by CVPR 2025
Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
Comments Accepted by CVPR 2025
Do computer vision foundation models learn the low-level characteristics of the human visual system?
Comments Accepted by CVPR 2025
COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
Comments CVPR 2025
