Bhiksha Raj

Computer Vision and Pattern Recognition · 2004–2022

A researcher in the Science corpus: 22 papers; trusts 987 researchers and is trusted by 67 researchers here, as inferred from the citation graph.

Subfields

Computer Vision and Pattern Recognition — 269 citations into it; #4,868 of 21,575 by trust here, #2,832 by citations
Artificial Intelligence — 229 citations into it; #21,531 of 35,345 by trust here, #7,657 by citations
Signal Processing — 121 citations into it; #987 of 7,572 by trust here, #333 by citations
Representation & Self-Supervised Learning — 72 citations into it
Model Architectures — 71 citations into it
Optimization & Training — 59 citations into it
Speech & Audio — 40 citations into it
Evaluation & Benchmarks — 35 citations into it

Whom Bhiksha Raj trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

Who trusts Bhiksha Raj overall

Papers from Bhiksha Raj's perspective

Ordered by how strongly the researchers Bhiksha Raj 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)
Long Short-Term Memory
Gradient-based learning applied to document recognition
Attention is All you Need (Neural Information Processing Systems)
ImageNet: A large-scale hierarchical image database
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

SphereFace: Deep Hypersphere Embedding for Face Recognition (2017) — 3,098 citations
Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition (2014) — 301 citations
Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery (2017) — 47 citations
Cross Modal Audio Search and Retrieval with Joint Embeddings Based on Text and Audio (2019) — 65 citations
Audio event and scene recognition: A unified approach using strongly and weakly labeled data (2016) — 41 citations
On the Origin of Deep Learning (2017) — 243 citations
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning (2022) — 477 citations
SphereFace Revived: Unifying Hyperspherical Face Recognition (2021) — 60 citations
Is normalization indispensable for training deep neural network? (2020) — 68 citations
Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks (2020) — 48 citations
A Closer Look at Weak Label Learning for Audio Events (2018) — 70 citations
Voice Impersonation Using Generative Adversarial Networks (2018) — 108 citations
DCASE2017 Challenge Setup: Tasks, Datasets and Baseline System (2017) — 506 citations
A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research (2016) — 398 citations
Large Margin Gaussian Mixture Models with Differential Privacy (2012) — 17 citations
Microphone array processing for distant speech recognition: Towards real-world deployment (2012) — 59 citations
Privacy preserving probabilistic inference with Hidden Markov Models (2011) — 50 citations
Latent-variable decomposition based dereverberation of monaural and multi-channel signals (2010) — 21 citations
Multiparty Differential Privacy via Aggregation of Locally Trained Classifiers (2010) — 206 citations
Regularized non-negative matrix factorization with temporal dependencies for speech denoising (2008) — 101 citations