Towards Open-World Segmentation of Parts
Comments Accepted to CVPR 2023
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Batch Model Consolidation: A Multi-Task Model Consolidation Framework
Comments Published at CVPR 2023
GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds
Comments CVPR 2023. Code and data are available at: https://github.com/vLAR-group/GrowSP
Instance-Aware Image Completion
Comments AI for Content Creation (AI4CC) CVPR workshop, 2023
Scaling Novel Object Detection with Weakly Supervised Detection Transformers
Comments WACV 2023. Preliminary version appeared in CVPR 2022 Workshop on Transformers for Vision
HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning
Comments Paper accepted in CVPR-23; Project page and code available here: https://sites.google.com/view/chiawen-kuo/home/haav
NVTC: Nonlinear Vector Transform Coding
Comments Accepted by CVPR 2023
HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
Comments Accepted by CVPR 2023
A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation
Comments 24 pages, 14 figures, 5 tables, accepted by the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. The proposed new synthetic-to-real benchmark S2RDA is available at https://pan.baidu.com/s/1fHHaqrEHbUZLXEg9XKpgSg?pwd=w9wa. The project page is available at https://huitangtang.github.io/On_the_Utility_of_Synthetic_Data/
Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
Comments Accepted by CVPR 2023. 12 pages, 7 figures, 11 tables
Improving Zero-shot Generalization and Robustness of Multi-modal Models
Comments CVPR 2023
Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models
Comments CVPR 2023 AI4CC Workshop
Recurrent Vision Transformers for Object Detection with Event Cameras
Journal ref IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 2023
Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup
Comments CVPR 2023 camera-ready
Enhancing Transformer Backbone for Egocentric Video Action Segmentation
Comments Joint 3rd Ego4D and 11th EPIC Workshop on Egocentric Vision at CVPR 2023
Exploring Compositional Visual Generation with Latent Classifier Guidance
Comments Accepted to CVPR Workshop 2023
POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo
Comments Accepted by CVPR 2023. (v2 fix typos)
CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language
Comments Accepted at Conference on Computer Vision and Pattern Recognition 2023(CVPR2023)
Pareto-Optimal Quantized ResNet Is Mostly 4-bit
Comments 8 pages. Accepted at the Efficient Deep Learning for Computer Vision Workshop at CVPR 2021
The Best Defense is a Good Offense: Adversarial Augmentation against Adversarial Attacks
Journal ref CVPR 2023
Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses
Comments CVPR 2023 Highlight
MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation
Comments Accepted to CVPR 2023
MIPI 2023 Challenge on Nighttime Flare Removal: Methods and Results
Comments CVPR 2023 Mobile Intelligent Photography and Imaging (MIPI) Workshop--Nighttime Flare Removal Challenge Report. Website: https://mipi-challenge.org/MIPI2023/
A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation
Comments CVPR 2023
Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation
Comments accepted by CVPR 2023
Learning Emotion Representations from Verbal and Nonverbal Communication
Comments CVPR 2023
Learning Action Changes by Measuring Verb-Adverb Textual Relationships
Comments CVPR 23. Version 2 updates some results due to an errata (see code repository for more details). Code and dataset available at https://github.com/dmoltisanti/air-cvpr23
EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization
Comments Accepted to CVPR 2023, Project page: https://sites.google.com/view/junha/ecotta
Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments
Comments Accepted at CVPR 2023 Workshop: Deep Learning for Geometric Computing
Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids
Comments CVPR 2023
