 Segment This Thing: Foveated Tokenization for Efficient Point-Prompted SegmentationComputer Vision and Pattern Recognition (CVPR), 2025 |
 LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point CloudsComputer Vision and Pattern Recognition (CVPR), 2025 |
Track Any Anomalous Object: A Granular Video Anomaly Detection PipelineComputer Vision and Pattern Recognition (CVPR), 2025 |
 SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training CostComputer Vision and Pattern Recognition (CVPR), 2025 |
 Depth-Aware Scoring and Hierarchical Alignment for Multiple Object TrackingInternational Conference on Information Photonics (ICIP), 2025 |
