Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models
Comments CVPR 2025 camera-ready version
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
Comments Accepted by CVPR 2025
SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation
Comments CVPR 2025
StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements
Comments Accepted by CVPR 2025
Video Motion Transfer with Diffusion Transformers
Comments CVPR 2025 - Project page: https://ditflow.github.io/
Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
Comments Accepted by CVPR 2025
Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion
Comments 19 pages; First two authors contributed equally; Accepted at CVPR 2025
MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
Comments CVPR 2024; updated NExT-GQA results in Appendix
FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
Comments 14 pages, 6 figures; Accepted by CVPR 2025
The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
Comments Accepted by CVPR 2025
Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
Journal ref Published in CVPR 2025
KAC: Kolmogorov-Arnold Classifier for Continual Learning
Comments CVPR 2025
Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images
Comments Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis
Comments Accepted to CVPR 2025, Mistakenly submitted as a replacement for arXiv:2402.11057
Exploiting Temporal State Space Sharing for Video Semantic Segmentation
Comments IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025
Leveraging 3D Geometric Priors in 2D Rotation Symmetry Detection
Comments Accepted to CVPR 2025
Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
Comments Accepted to CVPR 2025, add references
WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild
Comments CVPR 2025, Project Page https://rolpotamias.github.io/WiLoR
UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines
Comments Accepted to CVPR 2025
PhysGen3D: Crafting a Miniature Interactive World from a Single Image
Comments CVPR 2025, Project page: https://by-luckk.github.io/PhysGen3D
Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
Comments CVPR 2025; Project Page: https://foundation-model-research.github.io/difflens
SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
Comments Accepted to CVPR 2025
Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability
Comments This paper has been accepted to CVPR 2025
Incremental Object Keypoint Learning
Comments The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
Guiding Human-Object Interactions with Rich Geometry and Relations
Comments CVPR 2025.Project website: https://lalalfhdh.github.io/rog_page/
EBS-EKF: Accurate and High Frequency Event-based Star Tracking
Comments Accepted into the proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) for 2025. Link to code and dataset is https://gitlab.kitware.com/nest-public/kw_ebs_star_tracking#
Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perception
Comments Accepted at CVPR 2025
Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields
Comments 15 pages, 12 figures and 3 tables; project page: https://4dqv.mpiinf.mpg.de/ThinShellSfT; CVPR 2025
AvatarArtist: Open-Domain 4D Avatarization
Comments Accepted to CVPR 2025. Project page: https://kumapowerliu.github.io/AvatarArtist
Attention IoU: Examining Biases in CelebA using Attention Maps
Comments To appear in CVPR 2025. Code and data is available at https://github.com/aaronserianni/attention-iou . 15 pages, 14 figures, including appendix
