Oncel Tuzel

CoRR, 2024

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum.

[BibT_eX]

[DOI]

Chun-Liang Li

Jen-Hao Rick Chang

Cem Koc

Vaishaal Shankar

CoRR, 2024

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks.

[BibT_eX]

[DOI]

Fartash Faghri

Mohammad Hossein Sekhavat

CoRR, 2024

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data.

[BibT_eX]

[DOI]

Sachin Mehta

Maxwell Horton

Fartash Faghri

CoRR, 2024

Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models.

[BibT_eX]

[DOI]

Seyed-Iman Mirzadeh

Keivan Alizadeh-Vahid

Proceedings of the Twelfth International Conference on Learning Representations, 2024

TiC-CLIP: Continual Training of CLIP Models.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Corpus Synthesis for Zero-Shot ASR Domain Adaptation Using Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2024

MUSCLE: A Model Update Strategy for Compatible LLM Evolution.

[BibT_eX]

[DOI]

Jessica Maria Echterhoff

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding.

[BibT_eX]

[DOI]

Haoxiang Wang

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

HUGS: Human Gaussian Splats.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Weight subcloning: direct initialization of transformers using larger pretrained ones.

[BibT_eX]

[DOI]

CoRR, 2023

Label-efficient Training of Small Task-specific Models by Leveraging Vision Foundation Models.

[BibT_eX]

[DOI]

CoRR, 2023

Novel-View Acoustic Synthesis from 3D Reconstructed Rooms.

[BibT_eX]

[DOI]

CoRR, 2023

VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON.

[BibT_eX]

[DOI]

Haoping Bai

Shancong Mou

Tatiana Likhomanenko

Ramazan Gokberk Cinbis

CoRR, 2023

Token Pooling in Vision Transformers for Image Classification.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

FastFill: Efficient Compatible Model Update.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Text is all You Need: Personalizing ASR Models Using Controllable Speech Synthesis.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

I See What You Hear: A Vision-Inspired Method to Localize Words.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

MobileOne: An Improved One millisecond Mobile Backbone.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

FaceLit: Neural 3D Relightable Faces.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Pointersect: Neural Rendering with Cloud-Ray Intersection.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

RangeAugment: Efficient Online Augmentation with Range Learning.

[BibT_eX]

[DOI]

CoRR, 2022

I see what you hear: a vision-inspired method to localize words.

[BibT_eX]

[DOI]

CoRR, 2022

APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations.

[BibT_eX]

[DOI]

CoRR, 2022

An Improved One millisecond Mobile Backbone.

[BibT_eX]

[DOI]

CoRR, 2022

Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

SYNT++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition.

[BibT_eX]

[DOI]

Ting-Yao Hu

Mohammadreza Armandpour

Proceedings of the IEEE International Conference on Acoustics, 2022

Data Incubation - Synthesizing Missing Data for Handwriting Recognition.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2022

NeuMan: Neural Human Radiance Field from a Single Video.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Forward Compatible Training for Large-Scale Embedding Retrieval Systems.

[BibT_eX]

[DOI]

Vivek Ramanujan

Ali Farhadi

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Forward Compatible Training for Representation Learning.

[BibT_eX]

[DOI]

Vivek Ramanujan

Ali Farhadi

CoRR, 2021

Token Pooling in Vision Transformers.

[BibT_eX]

[DOI]

CoRR, 2021

Instance-Level Task Parameters: A Robust Multi-task Weighting Framework.

[BibT_eX]

[DOI]

Shreyas Saxena

CoRR, 2021

Optimize What Matters: Training DNN-Hmm Keyword Spotting Model Using End Metric.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

SapAugment: Learning A Sample Adaptive Policy for Data Augmentation.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Implicit vs. Explicit Style Transfer? A Comparison of GAN Architectures for Continuous Path Keyboard Input Modeling.

[BibT_eX]

[DOI]

Proceedings of the 29th European Signal Processing Conference, 2021

Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

2020

Subject-Aware Contrastive Learning for Biosignals.

[BibT_eX]

[DOI]

CoRR, 2020

Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution.

[BibT_eX]

[DOI]

CoRR, 2020

Least squares binary quantization of neural networks.

[BibT_eX]

[DOI]

CoRR, 2020

Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Least squares binary quantization of neural networks.

[BibT_eX]

[DOI]

Zhucheng Tu

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum.

[BibT_eX]

[DOI]

Shreyas Saxena

Dennis DeCoste

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

MVX-Net: Multimodal VoxelNet for 3D Object Detection.

[BibT_eX]

[DOI]

Vishwanath A. Sindagi

Yin Zhou

Proceedings of the International Conference on Robotics and Automation, 2019

Learning Conditional Error Model for Simulated Time-Series Data.

[BibT_eX]

[DOI]

Ashish Shrivastava

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019

2018

Nonlinear Conjugate Gradients For Scaling Synchronous Distributed DNN Training.

[BibT_eX]

[DOI]

Saurabh Adya

Vinay Palakkode

Seyed-Mohsen Moosavi-Dezfooli

CoRR, 2018

Divide, Denoise, and Defend against Adversarial Attacks.

[BibT_eX]

[DOI]

Ashish Shrivastava

CoRR, 2018

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection.

[BibT_eX]

[DOI]

Yin Zhou

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017

Attentional Network for Visual Object Detection.

[BibT_eX]

[DOI]

Kota Hara

Amir-massoud Farahmand

CoRR, 2017

Learning from Simulated and Unsupervised Images through Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

2016

Global-Local Face Upsampling Network.

[BibT_eX]

[DOI]

Yuichi Taguchi

John R. Hershey

CoRR, 2016

Unsupervised network pretraining via encoding human design.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision, 2016

Coupled Generative Adversarial Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

High-accuracy user identification using EEG biometrics.

[BibT_eX]

[DOI]

Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2016

Robust Face Alignment Using a Mixture of Invariant Experts.

[BibT_eX]

[DOI]

Tim K. Marks

Salil Tambe

Proceedings of the Computer Vision - ECCV 2016, 2016

Gaussian Conditional Random Field Network for Semantic Segmentation.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising.

[BibT_eX]

[DOI]

Raviteja Vemulapalli

Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

R-CNN for Small Object Detection.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ACCV 2016, 2016

2015

Unsupervised Deep Network Pretraining via Human Design.

[BibT_eX]

[DOI]

CoRR, 2015

Efficient Upsampling of Natural Images.

[BibT_eX]

[DOI]

Chinmay Hegde

CoRR, 2015

Layered Interpretation of Street View Images.

[BibT_eX]

[DOI]

Proceedings of the Robotics: Science and Systems XI, Sapienza University of Rome, 2015

Deep hierarchical parsing for semantic segmentation.

[BibT_eX]

[DOI]

Abhishek Sharma

David W. Jacobs

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014

Semi-Supervised Kernel Mean Shift Clustering.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2014

Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2014

Detecting 3D geometric boundaries of indoor scenes under varying lighting.

[BibT_eX]

[DOI]

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2014

Recursive Context Propagation Network for Semantic Scene Labeling.

[BibT_eX]

[DOI]

Abhishek Sharma

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Learning to Rank 3D Features.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2014, 2014

2013

Joint Geodesic Upsampling of Depth Images.

[BibT_eX]

[DOI]

Yuichi Taguchi

Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012

Fast object localization and pose estimation in heavy clutter for robotic bin picking.

[BibT_eX]

[DOI]

Int. J. Robotics Res., 2012

Voting-based pose estimation for robotic assembly using a 3D sensor.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2012

Variable focus video: Reconstructing depth and video for dynamic scenes.

[BibT_eX]

[DOI]

Proceedings of the 2012 IEEE International Conference on Computational Photography, 2012

Motion-Aware Structured Light Using Spatio-Temporal Decodable Patterns.

[BibT_eX]

[DOI]

Yuichi Taguchi

Amit K. Agrawal

Proceedings of the Computer Vision - ECCV 2012, 2012

2011

Compressed Inference for Probabilistic Sequential Models.

[BibT_eX]

[DOI]

Gungor Polatkan

Aswin C. Sankaranarayanan

Proceedings of the UAI 2011, 2011

Finding a needle in a specular haystack.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2011

Entropy rate superpixel segmentation.

[BibT_eX]

[DOI]

Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, 2011

2010

Pose estimation in heavy clutter using a multi-flash camera.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2010

Image Invariants for Smooth Reflective Surfaces.

[BibT_eX]

[DOI]

Ashok Veeraraghavan

Aswin C. Sankaranarayanan

Amit K. Agrawal

Proceedings of the Computer Vision, 2010

<i>P</i>2Pi: A Minimal Solution for Registration of 3D Points to 3D Planes.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2010, 2010

Specular surface reconstruction from sparse reflection correspondences.

[BibT_eX]

[DOI]

Ashok Veeraraghavan

Amit K. Agrawal

Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

Fast directional chamfer matching.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

2009

PathMiner: A Web-Based Tool for Computer-Assisted Diagnostics in Pathology.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Technol. Biomed., 2009

A caGrid-Enabled, Learning Based Image Segmentation Method for Histopathology Specimens.

[BibT_eX]

[DOI]

Proceedings of the 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Boston, MA, USA, June 28, 2009

Kernel methods for weakly supervised mean shift clustering.

[BibT_eX]

[DOI]

Proceedings of the IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27, 2009

2008

Pedestrian Detection via Classification on Riemannian Manifolds.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2008

Automatic Image Analysis of Histopathology Specimens Using Concave Vertex Graph.

[BibT_eX]

[DOI]

Proceedings of the Medical Image Computing and Computer-Assisted Intervention, 2008

Learning on lie groups for invariant detection and tracking.

[BibT_eX]

[DOI]

Fatih Murat Porikli

Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

2007

Classification of hematologic malignancies using texton signatures.

[BibT_eX]

[DOI]

Pattern Anal. Appl., 2007

Human Detection via Classification on Riemannian Manifolds.

[BibT_eX]

[DOI]

Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007

2006

Fast Construction of Covariance Matrices for Arbitrary Size Image Windows.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Image Processing, 2006

Region Covariance: A Fast Descriptor for Detection and Classification.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision, 2006

Covariance Tracking using Model Update Based on Lie Algebra.

[BibT_eX]

[DOI]

Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 2006

2005

Bayesian background modeling for foreground detection.

[BibT_eX]

[DOI]

Proceedings of the Third ACM International Workshop on Video Surveillance & Sensor Networks, 2005

Multi-Kernel Object Tracking.

[BibT_eX]

[DOI]

Proceedings of the 2005 IEEE International Conference on Multimedia and Expo, 2005

Simultaneous Multiple 3D Motion Estimation via Mode Finding on Lie Groups.

[BibT_eX]

[DOI]

Raghav Subbarao

Proceedings of the 10th IEEE International Conference on Computer Vision (ICCV 2005), 2005

Object tracking in low-frame-rate video.

[BibT_eX]

[DOI]

Proceedings of the Electronic Imaging: Image and Video Communications and Processing 2005, 2005

A Bayesian Approach to Background Modeling.

[BibT_eX]

[DOI]

Fatih Murat Porikli