Search Results for author:
Found 16 papers, 7 papers with code
Few Shot Class Incremental Learning using Vision-Language models
Our proposed framework not only empowers the model to embrace novel classes with limited data, but also ensures the preservation of performance on base classes.
Can No-reference features help in Full-reference image quality estimation?
Recent works in Full-reference IQA research perform pixelwise comparison between deep features corresponding to query and reference images for quality prediction.
Non-linear Motion Estimation for Video Frame Interpolation using Space-time Convolutions
Video frame interpolation aims to synthesize one or multiple frames between two consecutive frames in a video.
Anomaly Detection in Retinal Images using Multi-Scale Deep Feature Sparse Coding
Convolutional Neural Network models have successfully detected retinal illness from optical coherence tomography (OCT) and fundus images.
ReFIn: A Refinement Approach for Video Frame Interpolation
Video Frame Interpolation is an important video enhancement problem which aims to generate one or multiple frames between consecutive frames in video.
MSR-Net: Multi-Scale Relighting Network for One-to-One Relighting
Deep image relighting allows photo enhancement by illumination-specific retouching without human effort and so it is getting much interest lately.
Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report
To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms.
Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image
Most of the existing methods utilized additional sensor's data or pretrained network for fine depth estimation of the scene and sometimes use portrait segmentation pretrained network module to segment salient objects in the image.
Efficient Space-time Video Super Resolution using Low-Resolution Flow and Mask Upsampling
Input LR frames are super-resolved using a state-of-the-art Video Super-Resolution method.
A Heuristic-driven Uncertainty based Ensemble Framework for Fake News Detection in Tweets and News Articles
We have evaluated our results on the COVID-19 Fake News dataset and FakeNewsNet dataset to show the effectiveness of the proposed algorithm on detecting fake news in short news content as well as in news articles.
DSRN: an Efficient Deep Network for Image Relighting
Custom and natural lighting conditions can be emulated in images of the scene during post-editing.
Ranked #4 on
Image Relighting
on VIDIT’20 validation set
A Heuristic-driven Ensemble Framework for COVID-19 Fake News Detection
The significance of social media has increased manifold in the past few decades as it helps people from even the most remote corners of the world stay connected.
Ranked #1 on
Fake News Detection
on COVID-19 Fake News Dataset
AIM 2020 Challenge on Rendering Realistic Bokeh
This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results.
Depth-aware Blending of Smoothed Images for Bokeh Effect Generation
The original image and different versions of smoothed images are blended to generate Bokeh effect with the help of a monocular depth estimation network.
Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
Recently, CNN based end-to-end deep learning methods achieve superiority in Image Dehazing but they tend to fail drastically in Non-homogeneous dehazing.
Ranked #4 on
Nonhomogeneous Image Dehazing
on NH-HAZE validation
NTIRE 2020 Challenge on NonHomogeneous Dehazing
We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor.
