Search Results for author:
Found 5 papers, 1 papers with code
Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking
This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a lightweight full-precision network.
Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning.
Real-Time MDNet
We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet).
MarioQA: Answering Questions by Watching Gameplay Videos
To address this objective, we automatically generate a customized synthetic VideoQA dataset using {\em Super Mario Bros.} gameplay videos so that it contains events with different levels of reasoning complexity.
Tracking-by-Segmentation With Online Gradient Boosting Decision Tree
We evaluate the performance of our tracking algorithm based on the measures for segmentation masks, where our algorithm illustrates superior accuracy compared to the state-of-the-art segmentation-based tracking methods.
