188 citations · 271 across the 15 of their papers we have counts for
7 papers · 1 filter
Cross-modal Learning for Multi-modal Video Categorization
Palash Goyal, Saurabh Sahu, Shalini Ghosh +1
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.…
Exploiting Temporal Coherence for Multi-modal Video Categorization
Palash Goyal, Saurabh Sahu, Shalini Ghosh +1
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 det…
RILOD: Near Real-Time Incremental Learning for Object Detection at the Edge
Dawei Li, Serafettin Tasci, Shalini Ghosh +3
Object detection models shipped with camera-equipped edge devices cannot cover the objects of interest for every user. Therefore, the incremental learning capability is a critical…
Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
Jie Zhang, Junting Zhang, Shalini Ghosh +4
Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community. The aim of lifelong…
Class-incremental Learning via Deep Model Consolidation
Junting Zhang, Jie Zhang, Shalini Ghosh +5
Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes whe…
MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression
Jie Zhang, Xiaolong Wang, Dawei Li +3
State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer. However, they pr…
Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation
Heming Zhang, Shalini Ghosh, Larry Heck +4
The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow. Traditional Maximu…