Polygonal Building Segmentation by Frame Field Learning
Comments CVPR 2021 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2021, Pittsburg / Virtual, United States
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey
Comments Accepted to TPAMI. Paper version of our CVPR 2019 tutorial: "Learning-based depth estimation from stereo and monocular images: successes, limitations and future challenges" (https://sites.google.com/view/cvpr-2019-depth-from-image/home)
ReMix: Towards Image-to-Image Translation with Limited Data
Comments CVPR 2021
Online Learning of a Probabilistic and Adaptive Scene Representation
Comments CVPR 2021
Convolutional Hough Matching Networks
Comments Accepted to CVPR 2021 (oral presentation)
Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
Comments CVPR 2021
Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
Comments Accepted by CVPR 2021
Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging
Comments CVPR 2021. Project page and code: https://light.princeton.edu/publication/mask-tof
Denoise and Contrast for Category Agnostic Shape Completion
Comments Accepted at CVPR 2021
DAP: Detection-Aware Pre-training with Weak Supervision
Comments To appear in CVPR 2021
Unsupervised Disentanglement of Linear-Encoded Facial Semantics
Comments Accepted in IEEE Conference on Computer Vision and Pattern Recognition 2021 (CVPR2021)
Rectification-based Knowledge Retention for Continual Learning
Comments Accepted in CVPR 2021
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Comments Accepted at CVPR 2021
ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Media
Comments 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), project page available at https://light.princeton.edu/publication/zeroscatter/
KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment
Comments The first two authors contributed equally to this work. Accepted to CVPR 2021 (camera-ready version)
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
Comments Accepted at CVPR 2021; Code and models are available in the TensorFlow Object Detection API: https://github.com/tensorflow/models/tree/master/research/object_detection
On Feature Normalization and Data Augmentation
Comments CVPR 2021. Code is available at https://github.com/Boyiliee/MoEx
Explaining Classifiers using Adversarial Perturbations on the Perceptual Ball
Comments CVPR 2021
Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
Comments CVPR 2021, project page: https://bowenc0221.github.io/boundary-iou
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
Comments Accepted to CVPR 2021
Visual Room Rearrangement
Comments CVPR 2021 - Oral Presentation
Recognizing Actions in Videos from Unseen Viewpoints
Journal ref CVPR 2021
Read and Attend: Temporal Localisation in Sign Language Videos
Comments Appears in: 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2021). 14 pages
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
Comments CVPR 2021. Code at https://github.com/fudan-zvg/DDMP
Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction
Comments CVPR 2021, the project page: https://sites.google.com/view/humanmeshboa
Dynamic Domain Adaptation for Efficient Inference
Comments Accepted by CVPR 2021
Graph Stacked Hourglass Networks for 3D Human Pose Estimation
Comments Accepted to CVPR 2021
Source-Free Domain Adaptation for Semantic Segmentation
Comments CVPR 2021, 10 pages
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Comments Accepted by CVPR 2021
Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
Comments Accepted by CVPR 2021
