Search Results for author:
Found 8 papers, 2 papers with code
VQA with Cascade of Self- and Co-Attention Blocks
The use of complex attention modules has improved the performance of the Visual Question Answering (VQA) task.
Facial Keypoint Sequence Generation from Audio
To the best of our knowledge, this is the first work that proposes an audio-keypoint dataset and learns a model to output the plausible keypoint sequence to go with audio of any arbitrary length.
IQ-VQA: Intelligent Visual Question Answering
As a part of the cyclic framework, we propose a novel implication generator which can generate implied questions from any question-answer pair.
CQ-VQA: Visual Question Answering on Categorized Questions
The second level, referred to as answer predictor (AP), comprises of a set of distinct classifiers corresponding to each question category.
Reinforcement Learning via Recurrent Convolutional Neural Networks
Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks.
Overlay Text Extraction From TV News Broadcast
In this paper, we present a contrast enhancement based preprocessing stage for overlay text detection and a parameter free edge density based scheme for efficient text band detection.
TV News Commercials Detection using Success based Locally Weighted Kernel Combination
We adopt a intermediate fusion approach where, a SVM is trained with a weighted linear combination of different kernel functions instead of single kernel function.
An Occlusion Reasoning Scheme for Monocular Pedestrian Tracking in Dynamic Scenes
This paper looks into the problem of pedestrian tracking using a monocular, potentially moving, uncalibrated camera.
