Profiles2020-2026ORCID 0000-0001-8307-7107
Weiyao Lin
Shanghai Jiao Tong University
25Papers
17Last author
44Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers25
- PCGS: Progressive Compression of 3D Gaussian SplattingAuthor 4 of 6AAAI 2026 · 15 citations
- Head-Aware KV Cache Compression for Efficient Visual Autoregressive ModelingAuthor 7 of 9AAAI 2026 · 10 citations
- CogStream: Context-guided Streaming Video Question AnsweringAuthor 5 of 6AAAI 2026 · 3 citations
- VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video UnderstandingAuthor 9 of 9ICML 2026 · 3 citations
- Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive ActivationsAuthor 7 of 7NeurIPS 2025 · 22 citations
- Neural Compression for 3D Geometry SetsAuthor 3 of 4ICCV 2025 · 5 citations
- Fast Feedforward 3D Gaussian Splatting CompressionAuthor 4 of 6ICLR 2025 · 1 citation
- MECD: Unlocking Multi-Event Causal Discovery in Video ReasoningAuthor 11 of 11NeurIPS 2024 · 36 citations
- FRIH: Fine-Grained Region-Aware Image HarmonizationAuthor 9 of 9AAAI 2024 · 18 citations
- Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video AnalysisAuthor 7 of 7AAAI 2024 · 8 citations
- DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and CorrectionAuthor 4 of 4ACM MM 2024 · 2 citations
- Density Matters: Improved Core-Set for Active Domain Adaptive SegmentationAuthor 6 of 6AAAI 2024 · 2 citations
- BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable BasisAuthor 5 of 5NeurIPS 2023 · 90 citations
- TA2N: Two-Stage Action Alignment Network for Few-Shot Action RecognitionAuthor 8 of 8AAAI 2022 · 98 citations
- Speed up Object Detection on Gigapixel-level Images with Patch ArrangementAuthor 6 of 6CVPR 2022 · 13 citations
- Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action RecognitionAuthor 4 of 4ACM MM 2022 · 11 citations
- Enhancing Self-supervised Video Representation Learning via Multi-level Feature OptimizationAuthor 8 of 8ICCV 2021 · 43 citations
- End-to-End Video Instance Segmentation via Spatial-Temporal Graph Neural NetworksAuthor 4 of 4ICCV 2021 · 30 citations
- Multi-Level Curriculum for Training A Distortion-Aware Barrel Distortion Rectification ModelAuthor 5 of 5ICCV 2021 · 13 citations
- LSTC: Boosting Atomic Action Detection with Long-Short-Term ContextAuthor 4 of 7ACM MM 2021 · 7 citations
- Variational Pedestrian DetectionAuthor 6 of 6CVPR 2021
- Discriminative Sounding Objects Localization via Self-supervised Audiovisual MatchingAuthor 7 of 8NeurIPS 2020 · 156 citations
- ATRW: A Benchmark for Amur Tiger Re-identification in the WildAuthor 5 of 5ACM MM 2020 · 116 citations
- Delving into the Cyclic Mechanism in Semi-supervised Video Object SegmentationAuthor 5 of 5NeurIPS 2020 · 32 citations
- Finding Action Tubes with a Sparse-to-Dense FrameworkAuthor 2 of 8AAAI 2020 · 18 citations
