Leonid Sigal
Computer Vision and Pattern Recognition · 2002–2021
A researcher in the Science corpus: 22 papers; trusts 2,733 researchers and is trusted by 4,378 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 489 citations into it; #709 of 21,973 by trust here, #1,419 by citations
- Artificial Intelligence — 302 citations into it; #2,913 of 36,961 by trust here, #4,946 by citations
- Multimodal Learning — 88 citations into it; #347 of 1,215 by trust here, #639 by citations
- Representation & Self-Supervised Learning — 59 citations into it
- Generative Models — 57 citations into it; #1,122 of 1,963 by trust here, #1,226 by citations
- Natural Language Processing — 48 citations into it; #1,168 of 5,725 by trust here, #2,548 by citations
- Evaluation & Benchmarks — 39 citations into it; #544 of 3,155 by trust here, #1,182 by citations
- Model Architectures — 32 citations into it
Whom Leonid Sigal trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Kaiming He
- Alex Krizhevsky
- Diederik P. Kingma
- Karen Simonyan
- Yoshua Bengio
- Ross B. Girshick
- Andrew Zisserman
- Yann LeCun
- Ilya Sutskever
Who trusts Leonid Sigal overall
- Mykhaylo Andriluka
- Michael J. Black
- Ronald Poppe
- Juergen Gall
- Bernt Schiele
- Yi Yang
- Jitendra Malik
- Catalin Ionescu
- Cristian Sminchisescu
- Gerard Pons-Moll
Papers from Leonid Sigal's perspective
Ordered by how strongly the researchers Leonid Sigal 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
- Attention is All you Need (Neural Information Processing Systems)
- 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
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion (2010) — 1,365 citations
- Learning Activity Progression in LSTMs for Activity Detection and Early Detection (2016) — 392 citations
- Semi-supervised Vocabulary-Informed Learning (2016) — 135 citations
- Implicit Probabilistic Models of Human Motion for Synthesis and Tracking (2002) — 398 citations
- Detailed Human Shape and Pose from Images (2007) — 363 citations
- Learning Language-Visual Embedding for Movie Understanding with Natural-Language (2016) — 110 citations
- Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation (2006) — 259 citations
- Dynamical binary latent variable models for 3D human pose tracking (2010) — 161 citations
- Poselet Key-Framing: A Model for Human Activity Recognition (2013) — 244 citations
- Image Generation From Layout (2018) — 241 citations
- Visual Reference Resolution using Attention Memory for Visual Dialog (2017) — 125 citations
- Estimating contact dynamics (2009) — 117 citations
- Multilevel Language and Vision Integration for Text-to-Clip Retrieval (2018) — 369 citations
- Expanding object detector's Horizon: Incremental learning framework for object detection in videos (2015) — 49 citations
- Improved Few-Shot Visual Classification (2019) — 272 citations
- High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso (2012) — 344 citations
- Referring Transformer: A One-step Approach to Multi-task Visual Grounding (2021) — 262 citations
- Layout2image: Image Generation from Layout (2020) — 45 citations
- Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder (2015) — 43 citations
- HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion (2006) — 453 citations