Showing 1–20 of 45 results
/ Date/ Name
Sep 15, 2019Scaling Object Detection by Transferring Classification WeightsApr 12, 2016Recurrent Attentional Networks for Saliency DetectionNov 17, 2016DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information InflowsJul 29, 2021Open-World Entity SegmentationJan 29, 2018Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional NetworksApr 14, 2016Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principleApr 26, 2021Multimodal Contrastive Training for Visual Representation LearningJul 23, 2022Meta Spatio-Temporal Debiasing for Video Scene Graph GenerationMar 31, 2022GALA: Toward Geometry-and-Lighting-Aware Object Search for CompositingOct 13, 2022Improving the Reliability for Confidence EstimationDec 22, 2015Recent Advances in Convolutional Neural NetworksNov 6, 2023SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img SynthesisJun 14, 2024ControlVAR: Exploring Controllable Visual Autoregressive ModelingNov 29, 2021High Quality Segmentation for Ultra High-resolution ImagesFeb 6, 2026Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and OrchestrationNov 21, 2022SceneComposer: Any-Level Semantic Image SynthesisMay 28, 2023AIMS: All-Inclusive Multi-Level SegmentationOct 2, 2024ImageFolder: Autoregressive Image Generation with Folded TokensMay 22, 2025LaViDa: A Large Diffusion Language Model for Multimodal UnderstandingSep 23, 2025Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation