Improving Multimodal Speech Recognition by Data Augmentation and Speech Representations
Comments Accepted at the Multimodal Learning and Applications Workshop (MULA) from CVPR 2022
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Few-Shot Head Swapping in the Wild
Comments Accepted to CVPR 2022 as Oral. Demo videos and code are available at https://jmliu88.github.io/HeSer
Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution
Comments Accepted to CVPR 2022
Towards assessing agricultural land suitability with causal machine learning
Comments This work has been accepted for publication in EARTHVISION 2022, in conjunction with the Computer Vision and Pattern Recognition (CVPR) 2022 Conference
Conformer and Blind Noisy Students for Improved Image Quality Assessment
Comments CVPR NTIRE 2022
A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching
Comments CVPR 2022
Density-preserving Deep Point Cloud Compression
Comments Accepted by CVPR 2022. Project page is available at https://yunhe20.github.io/D-PCC
MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
Comments CVPR 2022
Leveraging Unlabeled Data for Sketch-based Understanding
Comments SketchDL at CVPR 2022
Coupled Iterative Refinement for 6D Multi-Object Pose Estimation
Comments Accepted to CVPR 2022
Identity Preserving Loss for Learned Image Compression
Comments Accepted by CVPR 2022 Workshop on New Trends in Image Restoration and Enhancement and Challenges
Integrative Few-Shot Learning for Classification and Segmentation
Comments Accepted at CVPR 2022; Code available at https://github.com/dahyun-kang/ifsl ; Project page: https://cvlab.postech.ac.kr/research/iFSL/
UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
Comments Accepted at IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022
Learning-by-Novel-View-Synthesis for Full-Face Appearance-Based 3D Gaze Estimation
Comments Camera-ready version for CVPR 2022 Workshop (GAZE 2022)
Self-Supervised Keypoint Discovery in Behavioral Videos
Comments CVPR 2022. Code: https://github.com/neuroethology/BKinD Project page: https://sites.google.com/view/b-kind
HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation
Comments CVPR 2021
Focal Sparse Convolutional Networks for 3D Object Detection
Comments CVPR 2022 Oral. Code is at http://github.com/dvlab-research/FocalsConv
Context-Aware Sequence Alignment using 4D Skeletal Augmentation
Comments Project page: http://www.taeinkwon.com/projects/casa. Accepted to CVPR 2022 Oral
Transfer Learning from Synthetic In-vitro Soybean Pods Dataset for In-situ Segmentation of On-branch Soybean Pod
Comments Accepted by CVPR 2022 Vision for Agriculture Workshop
Modular Action Concept Grounding in Semantic Video Prediction
Comments To appear in CVPR 2022
Global Tracking Transformers
Comments CVPR 2022. Code is available at https://github.com/xingyizhou/GTR
Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation
Comments Published at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 Workshop on Continual Learning
Multi-Layer Modeling of Dense Vegetation from Aerial LiDAR Scans
Comments Earth Vision Workshop, CVPR 2022
Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction
Comments Accepted to CVPR 2022 Precognition Workshop
IMDeception: Grouped Information Distilling Super-Resolution Network
Comments Accepted for publication in NTIRE 2022 @ CVPR 2022
Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning
Comments Accepted in IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2022
Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers
Comments In CVPR 2022. Webpage & Code: https://twke18.github.io/projects/hsg.html
EMOCA: Emotion Driven Monocular Face Capture and Animation
Comments Conference on Computer Vision and Pattern Recognition (CVPR) 2022
Can domain adaptation make object recognition work for everyone?
Comments Published at the L3D-IVU workshop at CVPR 2022
VISTA: Vision Transformer enhanced by U-Net and Image Colorfulness Frame Filtration for Automatic Retail Checkout
Comments accepted at AI City Challenge workshop - CVPR 2022
