Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?
Comments Accepted at 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Corresponding author - prakash.chandra.chhipa@ltu.se
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection
Comments Accepted to ICCV 2023. Code: https://github.com/AIR-DISCOVER/DQS3D
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
Comments Accepted by ICCV 2023
Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution
Comments Accepted by ICCV 2023
PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs
Comments To Appear in ICCV 2023. The first three authors contributed equally to this work. The project page is at https://manycore-research.github.io/PlankAssembly
FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models
Comments Accepted to ICCV 2023. Project webpage is at: https://aim-uofa.github.io/FrozenRecon/
Is there progress in activity progress prediction?
Comments Accepted at ICCVw-2023 (AI for Creative Video Editing and Understanding, ICCV workshop 2023)
Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation
Comments Accepted to ICCV 2023
SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data
Comments This paper has been accepted in International Conference on Computer Vision (ICCV) 2023. For code and data, please refer to the following GitHub page: https://github.com/IITPAVIS/SC3K
Guarding the Guardians: Automated Analysis of Online Child Sexual Abuse
Comments Artificial Intelligence (AI) and Humanitarian Assistance and Disaster Recovery (HADR) workshop, ICCV 2023 in Paris, France
InFusion: Inject and Attention Fusion for Multi Concept Zero-Shot Text-based Video Editing
Comments 10 pages, 8 figures, 1 Table, accepted at ICCVW 2023 (ICCV 2023 Workshop on AI for Creative Video Editing and Understanding)
TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer
Comments Accepted to ICCV 2023
Pseudo-label Alignment for Semi-supervised Instance Segmentation
Comments ICCV 2023
Data-Free Model Extraction Attacks in the Context of Object Detection
Comments Submitted to The 14th International Conference on Computer Vision Systems (ICVS 2023), to be published in Springer, Lecture Notes in Computer Science
Scaling Data Generation in Vision-and-Language Navigation
Comments ICCV 2023
Multi-metrics adaptively identifies backdoors in Federated learning
Comments 14 pages, 8 figures and 7 tables; 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Will Large-scale Generative Models Corrupt Future Datasets?
Comments ICCV 2023
Volumetric Fast Fourier Convolution for Detecting Ink on the Carbonized Herculaneum Papyri
Comments Accepted at the 4th ICCV Workshop on e-Heritage (in conjunction with ICCV 2023)
Foreground Object Search by Distilling Composite Image Feature
Comments Accepted by ICCV 2023
SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation
Comments Accepted to ICCV Workshop
JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition
Comments Accepted in ICCV 2023 Workshops
HyperCoil-Recon: A Hypernetwork-based Adaptive Coil Configuration Task Switching Network for MRI Reconstruction
Comments Accepted at the ICCV 2023 Workshop on Computer Vision for Automated Medical Diagnosis (CVAMD), 8 pages, 2 columns
PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration
Comments Accepted to the ICCV 2023
Objects do not disappear: Video object detection by single-frame object location anticipation
Comments Accepted by ICCV 2023
Which Tokens to Use? Investigating Token Reduction in Vision Transformers
Comments ICCV 2023 NIVT Workshop. Project webpage https://vap.aau.dk/tokens
Rendering Humans from Object-Occluded Monocular Videos
Comments ICCV 2023, project page: https://cs.stanford.edu/~xtiange/projects/occnerf/
FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
Comments Accepted by ICCV 2023
Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation
Comments ICCV 2023 camera ready
Estimation of Human Condition at Disaster Site Using Aerial Drone Images
Comments In submission to the ICCV 2023 Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop
Unsupervised Camouflaged Object Segmentation as Domain Adaptation
Comments 12 pages, 6 figures, 3 tables; Project Page: https://github.com/Jun-Pu/UCOS-DA ; Accepted to ICCV 2023 Workshop on OOD-CV
