Search Results for author:
Found 19 papers, 9 papers with code
Leveraging Local Temporal Information for Multimodal Scene Classification
In this paper, we propose a novel self-attention block that leverages both local and global temporal relationships between the video frames to obtain better contextualized representations for the individual frames.
Can't Fool Me: Adversarially Robust Transformer for Video Understanding
To address this, several techniques have been proposed to increase robustness of a model for image classification tasks.
Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training
GAT uses a multi-level attention gate to model the relevance of a frame based on local and global contexts.
Hierarchical Class-Based Curriculum Loss
We theoretically show that the proposed loss function is a tighter bound of 0-1 loss compared to any other loss satisfying the hierarchical constraints.
Cross-modal Learning for Multi-modal Video Categorization
Multi-modal machine learning (ML) models can process data in multiple modalities (e. g., video, audio, text) and are useful for video content analysis in a variety of problems (e. g., object detection, scene understanding, activity recognition).
Exploiting Temporal Coherence for Multi-modal Video Categorization
Multimodal ML models can process data in multiple modalities (e. g., video, images, audio, text) and are useful for video content analysis in a variety of problems (e. g., object detection, scene understanding).
ArduCode: Predictive Framework for Automation Engineering
We show that machine learning can be leveraged to assist the automation engineer in classifying automation, finding similar code snippets, and reasoning about the hardware selection of sensors and actuators.
Graph Representation Ensemble Learning
In this work, we introduce the problem of graph representation ensemble learning and provide a first of its kind framework to aggregate multiple graph embedding methods efficiently.
Benchmarks for Graph Embedding Evaluation
We use the comparisons on our 100 benchmark graphs to define GFS-score, that can be applied to any embedding method to quantify its performance.
Tracking Temporal Evolution of Graphs using Non-Timestamped Data
Datasets to study the temporal evolution of graphs are scarce.
Social and Information Networks
Pykg2vec: A Python Library for Knowledge Graph Embedding
Python library for knowledge graph embedding and representation learning.
DynamicGEM: A Library for Dynamic Graph Embedding Methods
DynamicGEM is an open-source Python library for learning node representations of dynamic graphs.
dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
Capturing such evolution is key to predicting the properties of unseen networks.
Ranked #5 on
Dynamic Link Prediction
on Enron Email Dataset
Future Automation Engineering using Structural Graph Convolutional Neural Networks
The digitalization of automation engineering generates large quantities of engineering data that is interlinked in knowledge graphs.
Discovering Signals from Web Sources to Predict Cyber Attacks
Cyber attacks are growing in frequency and severity.
DynGEM: Deep Embedding Method for Dynamic Graphs
The major advantages of DynGEM include: (1) the embedding is stable over time, (2) it can handle growing dynamic graphs, and (3) it has better running time than using static embedding methods on each snapshot of a dynamic graph.
Social and Information Networks
Capturing Edge Attributes via Network Embedding
Here we propose a novel embedding method that uses both network structure and edge attributes to learn better network representations.
Social and Information Networks
Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach
We also derive a novel lower bound on mutual information, used as a model-selection criterion favoring representations with better alignment between the utterances of participants in a collaborative dialogue setting, as well as higher predictability of the generated responses.
Graph Embedding Techniques, Applications, and Performance: A Survey
Graphs, such as social networks, word co-occurrence networks, and communication networks, occur naturally in various real-world applications.
