Ian Reid

50

Papers

838

Total Citations

Papers (50)

Deep Subspace Clustering Networks

NeurIPS 2017arXiv

A Bayesian Data Augmentation Approach for Learning Deep Models

NeurIPS 2017arXiv

3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer

Joint Tracking and Segmentation of Multiple Targets

Joint Probabilistic Matching Using m-Best Solutions

Efficient Point Process Inference for Large-Scale Object Detection

Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation

Learning Local Image Descriptors With Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions

Fast Training of Triplet-Based Deep Binary Embedding Networks

Attend in Groups: A Weakly-Supervised Deep Learning Framework for Learning From Web Data

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur

Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction

Bootstrapping the Performance of Webly Supervised Semantic Segmentation

Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments

Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries

Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning

Visual Question Answering With Memory-Augmented Networks

Towards Effective Low-Bitwidth Convolutional Neural Networks

TopNet: Structural Point Cloud Decoder

Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation

Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

Attention-Guided Network for Ghost-Free High Dynamic Range Imaging

RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion

Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells

A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning

Reconstruct Locally, Localize Globally: A Model Free Method for Object Pose Estimation

Training Quantized Neural Networks With a Full-Precision Auxiliary Module

FroDO: From Detections to 3D Objects

Rotation Coordinate Descent for Fast Globally Optimal Rotation Averaging

JRDB-Act: A Large-Scale Dataset for Spatio-Temporal Action, Social Group and Activity Detection

Hierarchical Higher-Order Regression Forest Fields: An Application to 3D Indoor Scene Labelling

Joint Probabilistic Data Association Revisited

Towards Context-Aware Interaction Recognition for Visual Relationship Detection

"Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction From Multiple Perspective Views

Smart Mining for Deep Metric Learning

DeepSetNet: Predicting Sets With Deep Neural Networks

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild

ODAM: Object Detection, Association, and Mapping Using Posed RGB Video

Residual Pattern Learning for Pixel-Wise Out-of-Distribution Detection in Semantic Segmentation

Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos

NeuRoRA: Neural Robust Rotation Averaging

SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes

Deeply Learning the Messages in Message Passing Inference

NeurIPS 2015arXiv

Scalable Place Recognition Under Appearance Change for Autonomous Driving

JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments

The k-Support Norm and Convex Envelopes of Cardinality and Rank

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks

Bayesian Generative Active Deep Learning