Search papers, labs, and topics across Lattice.
5
0
6
Active decision-making in video anomaly detection leads to a significant performance boost, outperforming traditional models with just 2B parameters.
LRPO achieves superior video anomaly detection by learning from multiple reasoning trajectories without the need for extensive human annotations.
By mining cross-domain category relationships, this method significantly improves open-set object detection, enabling models to adapt to new object categories without target annotations.
Square superpixels, generated via granular ball computing, unlock efficient parallel processing and end-to-end optimization in deep learning pipelines by replacing irregular shapes with multi-scale square blocks.
Current LMMs can't reliably turn complex images into code, failing to preserve structural integrity even in relatively simple scenarios, as shown by the new Omni-I2C benchmark.
