Profiles2022-2026ORCID 0000-0001-7677-4772
Weimin Tan
Fudan University Shanghai
16Papers
0Last author
16Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers16
- Hi3Doc: Hierarchical Tri-Level Representations for Multimodal Long-Document UnderstandingAuthor 5 of 6CVPR Findings 2026
- Efficient Online Training for Zero-Shot Time-Lapse Microscopy Denoising and Super-ResolutionAuthor 4 of 5AAAI 2025
- SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything ModelAuthor 3 of 4AAAI 2024 · 25 citations
- MGQFormer: Mask-Guided Query-Based Transformer for Image Manipulation LocalizationAuthor 3 of 4AAAI 2024 · 23 citations
- Addressing Imbalance for Class Incremental Learning in Medical Image ClassificationAuthor 4 of 5ACM MM 2024 · 7 citations
- Low-Latency Space-Time Supersampling for Real-Time RenderingAuthor 5 of 6AAAI 2024 · 5 citations
- A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation ModelsAuthor 2 of 4ACM MM 2024 · 4 citations
- FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed ModelAuthor 4 of 5ACM MM 2024 · 4 citations
- Context-Aware Iteration Policy Network for Efficient Optical Flow EstimationAuthor 5 of 6AAAI 2024 · 1 citation
- Multi-Modality Deep Network for Extreme Learned Image CompressionAuthor 2 of 5AAAI 2023 · 27 citations
- MVFlow: Deep Optical Flow Estimation of Compressed Videos with Motion Vector PriorAuthor 3 of 5ACM MM 2023 · 8 citations
- Uncertainty-Guided Spatial Pruning Architecture for Efficient Frame InterpolationAuthor 5 of 6ACM MM 2023 · 1 citation
- Promoting Single-Modal Optical Flow Network for Diverse Cross-Modal Flow EstimationAuthor 2 of 3AAAI 2022 · 33 citations
- Learning Parallax Transformer Network for Stereo Image JPEG Artifacts RemovalAuthor 2 of 5ACM MM 2022 · 7 citations
- Geometry-Aware Reference Synthesis for Multi-View Image Super-ResolutionAuthor 4 of 5ACM MM 2022 · 4 citations
- Learning Robust Image-Based Rendering on Sparse Scene Geometry via Depth CompletionAuthor 4 of 6CVPR 2022 · 3 citations
