Search Results for author:
Found 12 papers, 1 papers with code
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
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.
DASZL: Dynamic Action Signatures for Zero-shot Learning
There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large.
SAFCAR: Structured Attention Fusion for Compositional Action Recognition
We present a general framework for compositional action recognition -- i. e. action recognition where the labels are composed out of simpler components such as subjects, atomic-actions and objects.
Motion Guided Attention Fusion to Recognize Interactions from Videos
We present a dual-pathway approach for recognizing fine-grained interactions from videos.
Video-based assessment of intraoperative surgical skill
The neural network approach using attention mechanisms also showed high sensitivity and specificity.
Did You Get What You Paid For? Rethinking Annotation Cost of Deep Learning Based Computer Aided Detection in Chest Radiographs
As deep networks require large amounts of accurately labeled training data, a strategy to collect sufficiently large and accurate annotations is as important as innovations in recognition methods.
The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces
Scholarly publications are key to the transfer of knowledge from scholars to others.
LMCanvas: Object-Oriented Interaction to Personalize Large Language Model-Powered Writing Environments
However, these interfaces provide limited support for writers to create personal tools for their own unique tasks, and may not comprehensively fulfill a writer's needs -- requiring them to continuously switch between interfaces during writing.
ELVIS: Empowering Locality of Vision Language Pre-training with Intra-modal Similarity
Deep learning has shown great potential in assisting radiologists in reading chest X-ray (CXR) images, but its need for expensive annotations for improving performance prevents widespread clinical application.
EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria
By simply composing prompts, developers can prototype novel generative applications with Large Language Models (LLMs).
Interactive Children’s Story Rewriting Through Parent-Children Interaction
Storytelling in early childhood provides significant benefits in language and literacy development, relationship building, and entertainment.
