Alessandro Ferrari on LinkedIn: #AI #AI #artificialintelligence

New SOTA in video object segmentation is insane VOS aims at segment target instances in a video sequence. A high-performing #AI should be able to delineate an object from the background or other distractors (e.g., similar instances) under occlusion, appearance changes, and deformation. Frame aggregation process as a (fast) voting problem New SOTA and faster: 20 FPS for multiple objects Link to paper, project, and source code in the first comment Want to know more about #AI? Follow ARGO Vision or ping me #artificialintelligence #machinelearning #deeplearningai #deepneuralnetworks #neuralnetworks #ml #deeplearning #computervision #nvidiavgpu #nvidia #neurips2021