Gemini: A Family of Highly Capable Multimodal Models

Gemini Robotics Team, Rohan Anil, Sebastian Borgeaud, +741

arXiv (Cornell University)

Artificial IntelligenceNatural Language ProcessingNew FamilyLarge Ai ModelImage Analysis +13

Deep Extreme Cut: From Extreme Points to Object Segmentation

Kevis-Kokitsi Maninis, Sergi Caelles, Jordi Pont-Tuset, +1

Scene AnalysisImage AnalysisMachine LearningMachine VisionData Science +13

The 2018 DAVIS Challenge on Video Object Segmentation

Sergi Caelles, Alberto Montes, Kevis-Kokitsi Maninis, +4

arXiv (Cornell University)

Artificial IntelligenceScene AnalysisEngineeringMachine LearningDavis Challenge +15

The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation

Sergi Caelles, Jordi Pont-Tuset, Federico Perazzi, +3

arXiv (Cornell University)

Artificial IntelligenceScene AnalysisEngineeringMachine LearningDavis Challenge +15

VCT: A Video Compression Transformer

Fabian Mentzer, George Toderici, David Minnen, +4

arXiv (Cornell University)

Lossy CompressionMachine VisionMachine LearningData ScienceImage Analysis +13

First real-time coherent MIMO-DSP for six coupled mode transmission

Sebastian Randel, S. Corteselli, Damiano Badini, +8

Polarization ModesWireless CommunicationsMimo SystemFree-space Optical NetworkCustom Receiver Board +12

Video Object Segmentation without Temporal Information

Kevis-Kokitsi Maninis, Sergi Caelles, Yuhua Chen, +4

IEEE Transactions on Pattern Analysis and Machine Intelligence

Scene AnalysisEngineeringMachine LearningVideo ProcessingVideo Summarization +14

One-Shot Video Object Segmentation

Sergi Caelles, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, +3

Foreground SegmentationScene AnalysisImage AnalysisMachine LearningMachine Vision +13

Deep Extreme Cut: From Extreme Points to Object Segmentation

Kevis-Kokitsi Maninis, Sergi Caelles, Jordi Pont-Tuset, +1

arXiv (Cornell University)

Scene AnalysisImage AnalysisMachine LearningMachine VisionData Science +13

Iterative Deep Learning for Road Topology Extraction

Carles Ventura, Jordi Pont-Tuset, Sergi Caelles, +2

arXiv (Cornell University)

Geometric LearningConvolutional Neural NetworkRoad NetworkMachine VisionMachine Learning +11