Ankur Handa
Computer Vision and Pattern Recognition · 2014–2021
A researcher in the Science corpus: 14 papers; trusts 1,364 researchers and is trusted by 1,177 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 246 citations into it; #1,692 of 21,973 by trust here, #2,437 by citations
- Artificial Intelligence — 122 citations into it; #36,556 of 36,961 by trust here, #12,082 by citations
- Control and Systems Engineering — 90 citations into it; #6,374 of 8,519 by trust here, #2,459 by citations
- Aerospace Engineering — 76 citations into it; #291 of 6,431 by trust here, #405 by citations
- Reinforcement Learning — 53 citations into it
- Robotics & Control — 40 citations into it; #87 of 612 by trust here, #116 by citations
- Evaluation & Benchmarks — 39 citations into it
- 3D Vision & Pose — 37 citations into it; #159 of 689 by trust here, #161 by citations
Whom Ankur Handa trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Karen Simonyan
- Yann LeCun
- Ross B. Girshick
- Yoshua Bengio
- Ilya Sutskever
- Diederik P. Kingma
- Rob Fergus
Who trusts Ankur Handa overall
- Andrew J. Davison
- Sergey I. Nikolenko
- Mike Roberts
- Vladlen Koltun
- John McCormac
- Stephan R. Richter
- Stefan Leutenegger
- Michael Firman
- Gabriella Csurka
- Nan Yang
Papers from Ankur Handa's perspective
Ordered by how strongly the researchers Ankur Handa trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Spatio-temporal video autoencoder with differentiable memory (2015) — 312 citations
- A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM (2014) — 937 citations
- Understanding RealWorld Indoor Scenes with Synthetic Data (2015) — 237 citations
- SemanticFusion: Dense 3D semantic mapping with convolutional neural networks (2016) — 615 citations
- SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth (2016) — 135 citations
- SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-training on Indoor Segmentation? (2017) — 320 citations
- Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience (2018) — 623 citations
- Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning (2021) — 1,851 citations
- SceneNet: An annotated model generator for indoor scene understanding (2016) — 111 citations
- DexYCB: A Benchmark for Capturing Hand Grasping of Objects (2021) — 463 citations
- GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning (2018) — 245 citations
- ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact (2019) — 164 citations
- DexPilot: Vision-Based Teleoperation of Dexterous Robotic Hand-Arm System (2019) — 316 citations
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling (2015) — 836 citations