Profiles2019-2026
Shiming Xiang
Chinese Academy of Sciences
19Papers
7Last author
44Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers19
- WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question AnsweringAuthor 5 of 5ACL Findings 2026
- EvoVLMA: Evolutionary Vision-Language Model AdaptationAuthor 3 of 3ACM MM 2025 · 1 citation
- UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic SegmentationAuthor 5 of 6ICLR 2025
- Defying Imbalanced Forgetting in Class Incremental LearningAuthor 6 of 6AAAI 2024 · 8 citations
- Enhancing Visual Continual Learning with Language-Guided SupervisionAuthor 7 of 7CVPR 2024 · 8 citations
- Weak Distribution Detectors Lead to Stronger Generalizability of Vision-Language Prompt TuningAuthor 5 of 6AAAI 2024 · 8 citations
- Dual Critic Reinforcement Learning under Partial ObservabilityAuthor 5 of 5NeurIPS 2024 · 3 citations
- Domain Decorrelation with Potential Energy RankingAuthor 5 of 6AAAI 2023 · 4 citations
- Robust Feature Rectification of Pretrained Vision Models for Object RecognitionAuthor 6 of 6AAAI 2023 · 1 citation
- Bilateral Memory Consolidation for Continual LearningAuthor 6 of 6CVPR 2023
- Learning from the Target: Dual Prototype Network for Few Shot Semantic SegmentationAuthor 5 of 6AAAI 2022 · 23 citations
- Adversarial Gradient Driven Exploration for Deep Click-Through Rate PredictionAuthor 5 of 8KDD 2022 · 11 citations
- AME: Attention and Memory Enhancement in Hyper-Parameter OptimizationAuthor 5 of 6CVPR 2022 · 6 citations
- Knowledge Mining and Transferring for Domain Adaptive Object DetectionAuthor 4 of 5ICCV 2021 · 54 citations
- Spatio-Temporal Graph Structure Learning for Traffic ForecastingAuthor 4 of 5AAAI 2020 · 290 citations
- AugFPN: Improving Multi-Scale Feature Learning for Object DetectionAuthor 4 of 5CVPR 2020
- Decoupled Representation Learning for Skeleton-Based Gesture RecognitionAuthor 5 of 6CVPR 2020
- DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud ProcessingAuthor 5 of 6ICCV 2019 · 295 citations
- Progressive Sparse Local Attention for Video Object DetectionAuthor 5 of 7ICCV 2019 · 95 citations
