An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
Comments Accepted to CVPR Workshops - Camera Ready Version
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Modeling Missing Annotations for Incremental Learning in Object Detection
Comments Accepted in CVPR-Workshop (CLVISION) 2022
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
Comments CVPR 2022 oral
Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras
Comments Accepted at CVPR EarthVision Workshop 2022
Update Compression for Deep Neural Networks on the Edge
Comments CVPR 2022 Mobile AI Workshop
Self-supervised Video Representation Learning with Cascade Positive Retrieval
Comments To appear in CVPR 2022 L3D-IVU Workshop
Debiased Learning from Naturally Imbalanced Pseudo-Labels
Comments Accepted by CVPR 2022
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
Comments CVPR 2022, first two authors contributed equally. Project page: https://pengsongyou.github.io/nice-slam
How Well Do Sparse Imagenet Models Transfer?
Comments Accepted to CVPR'22. This version: 25 pages, 9 figures (including appendix). **Includes extended upstream training results, which are not present in the CVPR version.**
Raising context awareness in motion forecasting
Comments CVPR Workshop on Autonomous Driving - WAD 2022
Discrete Cosine Transform Network for Guided Depth Map Super-Resolution
Comments Accepted by CVPR 2022 (Oral)
GazeOnce: Real-Time Multi-Person Gaze Estimation
Comments Accepted to CVPR 2022
Hephaestus: A large scale multitask dataset towards InSAR understanding
Comments This work has been accepted for publication in EARTHVISION 2022, in conjuction with the Computer Vision and Pattern Recognition (CVPR) 2022 Conference
Self-supervised Learning for Sonar Image Classification
Comments 8 pages, 10 figures, with supplementary. LatinX in CV Workshop @ CVPR 2022 Camera Ready
SpiderNet: Hybrid Differentiable-Evolutionary Architecture Search via Train-Free Metrics
Comments Published in CVPR-NAS 2022
A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement
Comments 8 pages, 12 figures, with supplementary. LatinX in CV Workshop @ CVPR 2022 Camera Ready
Does Interference Exist When Training a Once-For-All Network?
Comments Accepted to CVPR Embedded Vision Workshop 2022
Importance is in your attention: agent importance prediction for autonomous driving
Comments Accepted at CVPR 2022 Precognition workshop
Learning Trajectory-Aware Transformer for Video Super-Resolution
Comments CVPR 2022 Oral
Domain-Agnostic Prior for Transfer Semantic Segmentation
Comments Accepted by CVPR 2022
Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectors
Comments Accepted at CVPR Workshops 2022
Shape from Polarization for Complex Scenes in the Wild
Comments Accepted to CVPR 2022; Github link: https://github.com/ChenyangLEI/sfp-wild ;Project website: https://chenyanglei.github.io/sfpwild/index.html
Putting People in their Place: Monocular Regression of 3D People in Depth
Comments CVPR 2022; Code https://github.com/Arthur151/ROMP ; Dataset https://github.com/Arthur151/Relative_Human
RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising
Comments Accepted at CVPR 2022
Towards General Purpose Vision Systems
Comments CVPR 2022 Oral; Project page: https://prior.allenai.org/projects/gpv
Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity
Comments Accepted by CVPR 2022 Workshop on Learning with Limited Labelled Data for Image and Video Understanding
Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment
Comments CVPR 2022. The source code and model are available at https://github.com/happycaoyue/JSPL
Augmentation of Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models
Comments Accepted to CVPR 2022 Perception Beyond the Visible Spectrum (PBVS) Workshop
Poisons that are learned faster are more effective
Comments 8 pages, 4 figures. Accepted to CVPR 2022 Art of Robustness Workshop
Self-Supervised Equivariant Learning for Oriented Keypoint Detection
Comments CVPR 2022 accepted paper, Project page: http://cvlab.postech.ac.kr/research/REKD/
