Search Results for author:
Found 19 papers, 10 papers with code
When in Doubt: Improving Classification Performance with Alternating Normalization
We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification.
Cross-Modal Retrieval Augmentation for Multi-Modal Classification
Recent advances in using retrieval components over external knowledge sources have shown impressive results for a variety of downstream tasks in natural language processing.
Exploring Visual Engagement Signals for Representation Learning
Visual engagement in social media platforms comprises interactions with photo posts including comments, shares, and likes.
Intentonomy: a Dataset and Study towards Human Intent Understanding
Based on our findings, we conduct further study to quantify the effect of attending to object and context classes as well as textual information in the form of hashtags when training an intent classifier.
Deep Multi-Modal Sets
Most deep learning-based methods rely on a late fusion technique whereby multiple feature types are encoded and concatenated and then a multi layer perceptron (MLP) combines the fused embedding to make predictions.
Action Recognition Using Volumetric Motion Representations
In this work, we introduce a novel representation of motion as a voxelized 3D vector field and demonstrate how it can be used to improve performance of action recognition networks.
Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning Methods
We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading.
Learning to See Forces: Surgical Force Prediction with RGB-Point Cloud Temporal Convolutional Networks
Our method results in a mean absolute error of 0. 814 N in the ex vivo study, suggesting that it may be a promising alternative to hardware based surgical force feedback in endoscopic procedures.
Towards automatic initialization of registration algorithms using simulated endoscopy images
Several registration algorithms have been developed, many of which achieve high accuracy.
Self-supervised Learning for Dense Depth Estimation in Monocular Endoscopy
We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading.
Endoscopic navigation in the absence of CT imaging
Clinical examinations that involve endoscopic exploration of the nasal cavity and sinuses often do not have a reference image to provide structural context to the clinician.
Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition
Based on the findings from the model interpretation analysis, we propose a targeted refinement technique, which can generalize to various other recognition models.
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
In this work, we propose to use a new class of models known as Temporal Convolutional Neural Networks (TCN) for 3D human action recognition.
Ranked #1 on
Multimodal Activity Recognition
on EV-Action
Regularizing Face Verification Nets For Pain Intensity Regression
In this way, the expression intensity regression task can benefit from the rich feature representations trained on a huge amount of data for face verification.
Temporal Convolutional Networks for Action Segmentation and Detection
The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond.
Anatomically Constrained Video-CT Registration via the V-IMLOP Algorithm
Functional endoscopic sinus surgery (FESS) is a surgical procedure used to treat acute cases of sinusitis and other sinus diseases.
Temporal Convolutional Networks: A Unified Approach to Action Segmentation
The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally, and second, input these features into a classifier that captures high-level temporal relationships, such as a Recurrent Neural Network (RNN).
Ranked #6 on
Action Segmentation
on JIGSAWS
Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation
We propose a model for action segmentation which combines low-level spatiotemporal features with a high-level segmental classifier.
Ranked #7 on
Action Segmentation
on JIGSAWS
Beyond Spatial Pooling: Fine-Grained Representation Learning in Multiple Domains
In this paper, we formulate a probabilistic framework for analyzing the performance of pooling.
