Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos
Comments CVPR 2022, Project page: https://stevenlsw.github.io/hoi-forecast
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
LISA: Learning Implicit Shape and Appearance of Hands
Comments Published at CVPR 2022
FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation
Comments Accepted to CVPR 2022 (Oral)
Unsupervised Learning of Accurate Siamese Tracking
Comments 13 pages, 7 figures, to appear in CVPR 2022
Correlation Verification for Image Retrieval
Comments Accepted to CVPR 2022 (Oral Presentation)
WildNet: Learning Domain Generalized Semantic Segmentation from the Wild
Comments Accepted to CVPR 2022
Degradation-agnostic Correspondence from Resolution-asymmetric Stereo
Comments Accepted to CVPR 2022
RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo
Comments cvpr 2022, 11 pages
Exploiting Temporal Relations on Radar Perception for Autonomous Driving
Comments To appear in CVPR 2022
BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion
Comments Accepted at CVPR 2022
ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework
Comments Accepted by CVPR 2022
Style-Based Global Appearance Flow for Virtual Try-On
Comments CVPR 2022
TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting
Comments (Revised) CVPR 2022 Oral. RepCount dataset: https://svip-lab.github.io/dataset/RepCount_dataset.html , Code: https://github.com/SvipRepetitionCounting/TransRAC
Matching Feature Sets for Few-Shot Image Classification
Comments International Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation
Comments CVPR 2022
Online Convolutional Re-parameterization
Comments Accepted by CVPR 2022
Semantic-Aware Domain Generalized Segmentation
Comments 16 pages, 7 figures, accepted at CVPR 2022 (Oral Presentation)
Homography Loss for Monocular 3D Object Detection
Comments 8 pages, 5 figures. Accepted to CVPR 2022
Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes
Comments Accepted to CVPR 2022
Robust Neonatal Face Detection in Real-world Clinical Settings
Comments Accepted at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Workshops 2021)
SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks
Comments Accepted to CVPR 2022. Project page: https://simbarv1.github.io
CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection
Comments Accepted to CVPR 2022
Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification
Comments 11 pages, 9 figures, accepted by CVPR 2022
Rethinking Semantic Segmentation: A Prototype View
Comments Accepted to CVPR 2022 (Oral); Code: https://github.com/tfzhou/ProtoSeg
Federated Learning with Position-Aware Neurons
Comments Accepted/to be published on CVPR 2022
Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation
Comments Accepted by CVPR 2022, the code is available at https://github.com/dongxingning/SHA-GCL-for-SGG
Rethinking Minimal Sufficient Representation in Contrastive Learning
Comments Accepted by CVPR 2022 as Oral presentation
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
Comments Accepted by CVPR 2022
Learning Distinctive Margin toward Active Domain Adaptation
Comments To appear in CVPR 2022
Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language
Comments CVPR 2022
