Joao Carreira

A Mixed Diet Makes DINO An Omnivorous Vision Encoder CVPR 2026 Recurrent Video Masked Autoencoders CVPR 2026 Unique Lives, Shared World: Learning from Single-Life Videos CVPR 2026 Direct Motion Models for Assessing Generated Videos ICML 2025 LayerLock: Non-collapsing Representation Learning with Progressive Freezing ICCV 2025 Learning from Streaming Video with Orthogonal Gradients CVPR 2025 Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video ICLR 2024 Learning from One Continuous Video Stream CVPR 2024 Moving Off-the-Grid: Scene-Grounded Video Representations NeurIPS 2024 TAPVid-3D: A Benchmark for Tracking Any Point in 3D NeurIPS 2024 Perception Test: A Diagnostic Benchmark for Multimodal Video Models NeurIPS 2023 Self-supervised video pretraining yields robust and more human-aligned visual representations NeurIPS 2023 TAPIR: Tracking Any Point with Per-Frame Initialization and Temporal Refinement ICCV 2023 General-purpose, long-context autoregressive modeling with Perceiver AR ICML 2022 Input-Level Inductive Biases for 3D Reconstruction CVPR 2022 Object Discovery and Representation Networks ECCV 2022 Perceiver IO: A General Architecture for Structured Inputs & Outputs ICLR 2022 TAP-Vid: A Benchmark for Tracking Any Point in a Video NeurIPS 2022 Efficient Visual Pretraining With Contrastive Detection ICCV 2021 Gradient Forward-Propagation for Large-Scale Temporal Video Modelling CVPR 2021 Perceiver: General Perception with Iterative Attention ICML 2021 Sideways: Depth-Parallel Training of Video Models CVPR 2020 Visual Grounding in Video for Unsupervised Word Translation CVPR 2020 Controllable Attention for Structured Layered Video Decomposition ICCV 2019 The Visual Centrifuge: Model-Free Layered Video Representations CVPR 2019 Video Action Transformer Network CVPR 2019 Massively Parallel Video Networks ECCV 2018 Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset CVPR 2017 Human Pose Estimation With Iterative Error Feedback CVPR 2016 Network Requirements for Resource Disaggregation OSDI 2016 Amodal Completion and Size Constancy in Natural Scenes ICCV 2015 Category-Specific Object Reconstruction From a Single Image CVPR 2015 Learning to See by Moving ICCV 2015 Pose Induction for Novel Object Categories ICCV 2015 Virtual View Networks for Object Reconstruction CVPR 2015 Iterated Second-Order Label Sensitive Pooling for 3D Human Pose Estimation CVPR 2014 Reconstructing PASCAL VOC CVPR 2014 Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition ICCV 2013 Composite Statistical Inference for Semantic Segmentation CVPR 2013 Probabilistic Joint Image Segmentation and Labeling NeurIPS 2011