Publications

(2020). Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors. arXiv preprint.

PDF arXiv Webpage Video

(2020). Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings. ICML.

PDF

(2020). An Exploration of Embodied Visual Exploration. In arXiv.

PDF arXiv Webpage

(2019). SMIRL: Surprise Minimizing RL in Dynamic Environments. In arXiv.

PDF arXiv Webpage

(2019). MAVRIC: Morphology-Agnostic Visual Robotic Control. In ICRA and RA-L.

PDF arXiv Webpage

(2019). DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation. In ICRA and RA-L.

PDF RA-L Webpage

(2019). Causal Confusion in Imitation Learning. NeurIPS (Oral).

PDF arXiv NIPS 2018 Workshop on Causal Learning (oral spotlight), NIPS 2018 Workshop on Imitation Learning (oral spotlight)

(2019). Time-Agnostic Prediction: Predicting Predictable Video Frames. In ICLR.

PDF arXiv Webpage

(2019). REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning. In ICRA.

PDF arXiv Webpage

(2019). REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning. arXiv preprint (extended version of earlier ICRA publication).

PDF arXiv Webpage

(2019). Manipulation by Feel: Touch-Based Control with Deep Predictive Models. In ICRA.

PDF arXiv BAIR blog post Webpage

(2019). Emergence of Exploratory Look-Around Behaviors Through Active Observation Completion. In Science Robotics.

PDF Online article Webpage

(2018). Techniques for Rectification of Camera Arrays.

PDF Google Patents

(2018). ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids. In ECCV.

PDF arXiv

(2018). More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch. In IROS and RAL (RAL Best Paper Runner-Up).

PDF arXiv Project Page

(2018). Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks. In CVPR.

PDF Supplementary material arXiv

(2018). End-to-End Policy Learning For Active Visual Categorization. In IEEE TPAMI.

PDF Preprint

(2017). Techniques for Improved Focusing of Camera Arrays.

PDF Google Patents

(2017). Learning Image Representations Tied to Egomotion from Unlabeled Video. In IJCV Special Issue of Best Papers from ICCV 2015.

PDF Downloadable Preprint Webpage

(2017). Embodied Learning for Visual Recognition. The University of Texas at Austin.

PDF

(2017). Divide, Share, and Conquer: Multi-Task Attribute Learning With Selective Sharing. In Springer Book on Visual Attributes.

PDF Book

(2016). Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video. In CVPR (Oral Spotlight).

PDF Supplementary pdf Webpage arXiv Spotlight video

(2016). Pano2Vid: Automatic Cinematography For Watching 360-degree Videos. In ACCV (Songde Ma Best Application Paper Award).

PDF Supplementary pdf Webpage arXiv

(2016). Object-Centric Representation Learning from Unlabeled Videos. In ACCV.

PDF arXiv Webpage

(2016). Look-Ahead Before You Leap: End-to-End Active Recognition By Forecasting the Effect of Motion. In ECCV (Oral).

PDF Supplementary pdf Webpage arXiv Oral Video

(2015). Learning Image Representations Tied to Egomotion. In ICCV (Oral).

PDF Supplementary pdf Webpage arXiv Oral video

(2014). Zero-Shot Recognition With Unreliable Attributes. In NIPS.

PDF Supplementary materials Webpage arXiv

(2014). Decorrelating Semantic Visual Attributes by Resisting the Urge to Share. In CVPR (Oral).

PDF Supplementary pdf Webpage Oral video

(2012). Objective Quality Assessment of Multiply Distorted Images. In ASILOMAR Conference on Signals, Systems and Computers.

PDF Webpage