Profiles2019-2023
Jianzhuang Liu
Huawei Noah's Ark Lab
36Papers
7Last author
90Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers36
- PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video RetrievalAuthor 3 of 9ICCV 2023 · 25 citations
- MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic SegmentationAuthor 5 of 8ICCV 2023 · 22 citations
- ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic ConsistencyAuthor 6 of 8ICLR 2023 · 16 citations
- Actional Atomic-Concept Learning for Demystifying Vision-Language NavigationAuthor 5 of 5AAAI 2023 · 7 citations
- HiVLP: Hierarchical Interactive Video-Language Pre-TrainingAuthor 2 of 8ICCV 2023 · 6 citations
- Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot ClassificationAuthor 3 of 4ICLR 2023 · 3 citations
- CLIPPING: Distilling CLIP-Based Models with a Student Base for Video-Language RetrievalAuthor 2 of 8CVPR 2023
- SmartAssign: Learning A Smart Knowledge Assignment Strategy for Deraining and DesnowingAuthor 3 of 3CVPR 2023
- Prompt Distribution LearningAuthor 2 of 5CVPR 2022 · 212 citations
- IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network QuantizationAuthor 4 of 7CVPR 2022 · 79 citations
- Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object DetectionAuthor 4 of 6CVPR 2022 · 74 citations
- Uncertainty-Driven Dehazing NetworkAuthor 2 of 4AAAI 2022 · 57 citations
- CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image SegmentationAuthor 3 of 5NeurIPS 2022 · 48 citations
- ADAPT: Vision-Language Navigation with Modality-Aligned Action PromptsAuthor 5 of 6CVPR 2022 · 45 citations
- Neural Architecture Search with Representation Mutual InformationAuthor 6 of 9CVPR 2022 · 17 citations
- SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-trained Siamese TransformersAuthor 3 of 6AAAI 2022 · 17 citations
- RelCLIP: Adapting Language-Image Pretraining for Visual Relationship Detection via Relational Contrastive LearningAuthor 6 of 6EMNLP 2022 · 8 citations
- Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-IDAuthor 4 of 8ICCV 2021 · 131 citations
- TRAR: Routing the Attention Spans in Transformer for Visual Question AnsweringAuthor 5 of 8ICCV 2021 · 128 citations
- Motion Deblurring with Real EventsAuthor 8 of 8ICCV 2021 · 108 citations
- Dual Distribution Alignment Network for Generalizable Person Re-IdentificationAuthor 3 of 5AAAI 2021 · 51 citations
- Active Learning for Lane Detection: A Knowledge Distillation ApproachAuthor 3 of 4ICCV 2021 · 18 citations
- Multi-Source Domain Adaptation With Collaborative Learning for Semantic SegmentationAuthor 4 of 4CVPR 2021
- Multi-Target Domain Adaptation With Collaborative Consistency LearningAuthor 6 of 8CVPR 2021
- Multiple Instance Active Learning for Object DetectionAuthor 3 of 5CVPR 2021
- Neighbor2Neighbor: Self-Supervised Denoising From Single Noisy ImagesAuthor 5 of 5CVPR 2021
- Semi-Supervised Domain Adaptation Based on Dual-Level Domain Mixing for Semantic SegmentationAuthor 5 of 5CVPR 2021
- Towards Compact CNNs via Collaborative CompressionAuthor 3 of 10CVPR 2021
- Context-Transformer: Tackling Object Confusion for Few-Shot DetectionAuthor 4 of 5AAAI 2020 · 91 citations
- High-Order Residual Network for Light Field Super-ResolutionAuthor 3 of 4AAAI 2020 · 43 citations
Showing the 30 most recent indexed papers.
