LAS-AT: Adversarial Training with Learnable Attack Strategy
Journal ref CVPR 2022
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Spatial Commonsense Graph for Object Localisation in Partial Scenes
Comments Accepted to CVPR 2022, project website: http://fgiuliari.github.io/projects/SpatialCommonsenseGraph/
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
Comments Accepted to CVPR 2022. Project: https://haochen-wang409.github.io/U2PL/
Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation
Comments Accepted by CVPR 2022. Code is available at https://github.com/LeonHLJ/RSKP
Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs
Comments Accepted by CVPR 2022. Code is available at https://github.com/Dawn-LX/VidSGG-BIG. We also won the 1st place of Video Relation Understanding (VRU) Grand Challenge in ACM Multimedia 2021, with a simplified version of our model.(The code for object tracklets generation is available at https://github.com/Dawn-LX/VidVRD-tracklets)
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
Comments Accepted at CVPR 2022. Paper + supplementary (14 pages, 9 figures)
Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast
Comments 10 pages, 5 figures. Accepted by CVPR'22
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
Comments Accepted by CVPR 2022
Ego4D: Around the World in 3,000 Hours of Egocentric Video
Comments To appear in the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. This version updates the baseline result numbers for the Hands and Objects benchmark (appendix)
Hyperbolic Image Segmentation
Comments accepted to CVPR 2022
FLAG: Flow-based 3D Avatar Generation from Sparse Observations
Comments Accepted at CVPR 2022
Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation
Comments CVPR 2022 Accepted
Restormer: Efficient Transformer for High-Resolution Image Restoration
Comments Accepted at CVPR 2022. #CVPR2022
RAMA: A Rapid Multicut Algorithm on GPU
Comments Published in CVPR 2022
Style Normalization and Restitution for Domain Generalization and Adaptation
Comments Published on IEEE Transactions on Multimedia. This paper extended SNR (CVPR'20) for domain generalization and adaptation to various computer vision tasks, e.g., image classification, object detection, semantic segmentation
Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data
Comments Accepted by CVPR 2020
Representation Compensation Networks for Continual Semantic Segmentation
Comments Accepted by CVPR 2022
Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects
Comments Accepted to CVPR 2022
OpenTAL: Towards Open Set Temporal Action Localization
Comments CVPR 2022 [camera ready with supplement]
NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
Comments Accepted to CVPR 2022
Hierarchical Modular Network for Video Captioning
Comments Accepted by CVPR 2022
What Matters For Meta-Learning Vision Regression Tasks?
Comments Accepted at CVPR 2022
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting
Comments Accepted by CVPR 2022
FlexIT: Towards Flexible Semantic Image Translation
Comments accepted at CVPR 2022
Autoregressive Image Generation using Residual Quantization
Comments 30 pages, 24 figures, accepted by CVPR 2022, the code is available at https://github.com/kakaobrain/rq-vae-transformer
Focal and Global Knowledge Distillation for Detectors
Comments Accept by CVPR 2022
Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
Comments To Appear in CVPR 2022. The project page is at https://manycore-research.github.io/faceformer
Selective-Supervised Contrastive Learning with Noisy Labels
Comments Accepted to CVPR 2022. 12 pages, 5 figure, and 10 tables
Forecasting Characteristic 3D Poses of Human Actions
Comments CVPR 2022; Project Page: https://charposes.christian-diller.de/; Paper Video: https://youtu.be/kVhn8OWMgME
On Generalizing Beyond Domains in Cross-Domain Continual Learning
Comments Accepted to CVPR 2022
