Davide Modolo

object detection (5) self-supervised learning (3) convolutional neural network (3) video understanding (3) semi-supervised learning (2) multi-object tracking (2) multimodal large language model (2) action recognition (2) activity recognition (2) human pose estimation (2) vision transformer (1) model calibration (1) contrastive learning (1) ensemble learning (1) transfer learning (1) semantic segmentation (1) pseudo labeling (1) visual grounding (1) object tracking (1) domain generalization (1)