Profiles2020-2023
Kui Jia
South China University of Technology
23Papers
17Last author
26Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers23
- A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain AdaptationAuthor 2 of 2CVPR 2023
- RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion ModelsAuthor 3 of 3CVPR 2023
- Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain GeneralizationAuthor 4 of 5CVPR 2022 · 217 citations
- TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting DecompositionAuthor 5 of 5NeurIPS 2022 · 112 citations
- VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial AttentionAuthor 4 of 4CVPR 2022 · 92 citations
- Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored ClusteringAuthor 3 of 3NeurIPS 2022 · 73 citations
- Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised LearningAuthor 2 of 2CVPR 2022 · 11 citations
- Instance Segmentation in 3D Scenes using Semantic Superpoint Tree NetworksAuthor 5 of 5ICCV 2021 · 170 citations
- DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose ConsistencyAuthor 5 of 6ICCV 2021 · 169 citations
- Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic SegmentationAuthor 5 of 7ICCV 2021 · 129 citations
- Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point CloudsAuthor 4 of 4ICCV 2021 · 75 citations
- Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D SpaceAuthor 5 of 5NeurIPS 2021 · 28 citations
- 3D AffordanceNet: A Benchmark for Visual Object Affordance UnderstandingAuthor 5 of 5CVPR 2021
- Deep Optimized Priors for 3D Shape Modeling and ReconstructionAuthor 5 of 5CVPR 2021
- Learning Parallel Dense Correspondence From Spatio-Temporal Descriptors for Efficient and Robust 4D ReconstructionAuthor 3 of 4CVPR 2021
- Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction From Raw Point CloudsAuthor 5 of 6CVPR 2021
- Discriminative Adversarial Domain AdaptationAuthor 2 of 2AAAI 2020 · 229 citations
- Cascading Convolutional Color ConstancyAuthor 6 of 6AAAI 2020 · 76 citations
- Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic GraspsAuthor 7 of 7NeurIPS 2020 · 66 citations
- Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface NetworksAuthor 2 of 2ICML 2020 · 25 citations
- Towards Understanding the Regularization of Adversarial Robustness on Neural NetworksAuthor 3 of 3ICML 2020 · 25 citations
- MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task LearningAuthor 5 of 6CVPR 2020
- Unsupervised Domain Adaptation via Structurally Regularized Deep ClusteringAuthor 3 of 3CVPR 2020
