Roozbeh Mottaghi
Computer Vision and Pattern Recognition · 2012–2022
A researcher in the Science corpus: 34 papers; trusts 3,423 researchers and is trusted by 9,806 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 985 citations into it; #280 of 21,973 by trust here, #338 by citations
- Artificial Intelligence — 795 citations into it; #1,733 of 36,961 by trust here, #1,126 by citations
- Reinforcement Learning — 284 citations into it; #399 of 2,250 by trust here, #160 by citations
- Natural Language Processing — 203 citations into it; #4,559 of 5,725 by trust here, #1,363 by citations
- Evaluation & Benchmarks — 171 citations into it; #306 of 3,155 by trust here, #537 by citations
- Multimodal Learning — 168 citations into it; #817 of 1,215 by trust here, #369 by citations
- Aerospace Engineering — 165 citations into it; #119 of 6,431 by trust here, #136 by citations
- Control and Systems Engineering — 151 citations into it; #4,874 of 8,519 by trust here, #624 by citations
Whom Roozbeh Mottaghi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Ross B. Girshick
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Pedro F. Felzenszwalb
- Ilya Sutskever
- Diederik P. Kingma
- Yoshua Bengio
- Yann LeCun
- Andrew Zisserman
Who trusts Roozbeh Mottaghi overall
- Alan L. Yuille
- Jitendra Malik
- Iasonas Kokkinos
- Bharath Hariharan
- Abhinav Kumar Gupta
- Liang-Chieh Chen
- Chunhua Shen
- Sergey Levine
- Bolei Zhou
- Andrea Vedaldi
Papers from Roozbeh Mottaghi's perspective
Ordered by how strongly the researchers Roozbeh Mottaghi trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- 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
- The Role of Context for Object Detection and Semantic Segmentation in the Wild (2014) — 1,654 citations
- AI2-THOR: An Interactive 3D Environment for Visual AI (2017) — 1,486 citations
- Target-driven visual navigation in indoor scenes using deep reinforcement learning (2016) — 1,723 citations
- Beyond PASCAL: A benchmark for 3D object detection in the wild (2014) — 846 citations
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (2019) — 1,612 citations
- Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts (2014) — 748 citations
- On Evaluation of Embodied Navigation Agents (2018) — 1,027 citations
- ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks (2019) — 1,140 citations
- Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images (2015) — 157 citations
- Visual Semantic Planning Using Deep Successor Representations (2017) — 145 citations
- Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks (2022) — 530 citations
- Bottom-Up Segmentation for Top-Down Detection (2013) — 146 citations
- "What Happens If..." Learning to Predict the Effect of Forces in Images (2016) — 129 citations
- Visual Semantic Navigation using Scene Priors (2018) — 379 citations
- ObjectNet3D: A Large Scale Database for 3D Object Recognition (2016) — 302 citations
- A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge (2022) — 950 citations
- ManipulaTHOR: A Framework for Visual Object Manipulation (2021) — 164 citations
- Rearrangement: A Challenge for Embodied AI (2020) — 245 citations
- ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects (2020) — 371 citations
- Simple but Effective: CLIP Embeddings for Embodied AI (2021) — 294 citations