Locate then Segment: A Strong Pipeline for Referring Image Segmentation
Comments CVPR 2021
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Model-Contrastive Federated Learning
Comments Accepted by CVPR 2021
Delving into Localization Errors for Monocular 3D Object Detection
Comments CVPR'2021, code will be made available
Repopulating Street Scenes
Comments CVPR 2021
Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
Comments CVPR 2021 camera-ready version
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation
Comments CVPR 2021
Fully Convolutional Scene Graph Generation
Comments CVPR 2021 Oral
Face Forensics in the Wild
Comments CVPR 2021 (Oral). https://github.com/tfzhou/FFIW
AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
Comments 8 pages, 15 pages supplementary, 12 figures. To be published in CVPR 2021
Domain-robust VQA with diverse datasets and methods but no target labels
Comments To appear in CVPR 2021
High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
Comments The paper is accepted to CVPR 2021
Adaptive Methods for Real-World Domain Generalization
Comments To appear as an oral presentation in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. v2 corrects double printing of appendix
Zero-shot Adversarial Quantization
Comments CVPR 2021 Oral
Bridging the Visual Gap: Wide-Range Image Blending
Comments Accepted to CVPR 2021. Project page: http://github.com/julia0607/Wide-Range-Image-Blending
I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
Comments Accepted by CVPR 2021
Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
Comments Accepted at CVPR 2021, 16 pages, 8 figures
Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
Comments 10 pages, 8 figures, CVPR 2021
Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map
Journal ref CVPR 2021
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
Comments IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2021). Our dataset is available at https://github.com/google-research-datasets/conceptual-12m
Open World Compositional Zero-Shot Learning
Comments Accepted in IEEE CVPR 2021
Binary Graph Neural Networks
Comments CVPR 2021 Camera-Ready Version
A Second-Order Approach to Learning with Instance-Dependent Label Noise
Comments Learning with label noise. Accepted as an oral paper by CVPR 2021
Joint Generative and Contrastive Learning for Unsupervised Person Re-identification
Comments CVPR 2021. Source code: https://github.com/chenhao2345/GCL
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Comments CVPR 2021
Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
Comments CVPR 2021. Code available at https://github.com/mboudiaf/RePRI-for-Few-Shot-Segmentation
CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
Comments CVPR 2021 oral presentation
How Robust are Randomized Smoothing based Defenses to Data Poisoning?
Comments CVPR 2021
Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution
Comments CVPR 2021, 10 pages, 10 figures
Improved Handling of Motion Blur in Online Object Detection
Comments Mirroring accepted CVPR paper. Added results for other real-world blur datasets. Main paper: 8 pages + 3 references. Supplemental: 9 pages
SLADE: A Self-Training Framework For Distance Metric Learning
Comments Accepted by CVPR 2021
