Intelligent Human Computer Interaction
8th International Conference, IHCI 2016, Pilani, India, December 12-13, 2016, Proceedings
Page
%P
-
Article
Am I readable? Transfer learning based document image rectification
Document image rectification is a commonly explored problem in computer vision. However, in recent works, the improvements made on a distorted document page are mostly confined to a few specific and limited ty...
-
Chapter and Conference Paper
Conditioning Covert Geo-Location (CGL) Detection on Semantic Class Information
To incorporate knowledge about non-object image regions (hideouts, turns, and other obscured regions) in machines, recently, a task for identification of potential hideouts termed Covert Geo-Location (CGL) det...
-
Chapter and Conference Paper
Catch Me if You Can: A Novel Task for Detection of Covert Geo-Locations (CGL)
Most of the visual scene understanding tasks in the field of computer vision involve the identification of the objects present in the scene. Image regions like hideouts, turns, and other obscured regions of th...
-
Chapter and Conference Paper
SACIC: A Semantics-Aware Convolutional Image Captioner Using Multi-level Pervasive Attention
Attention mechanisms alongside encoder-decoder architectures have become integral components for solving the image captioning problem. The attention mechanism recombines an encoding of the image depending on t...
-
Chapter and Conference Paper
Visual Saliency Detection via Convolutional Gated Recurrent Units
Context is an important aspect for accurate saliency detection. However, the question of how to formally model image context within saliency detection frameworks is still an open problem. Recent saliency detec...
-
Chapter and Conference Paper
GreenWarps: A Two-Stage War** Model for Stitching Images Using Diffeomorphic Meshes and Green Coordinates
Image Stitching is a hard task to solve in the presence of large parallax in the images. Specifically, for a sequence of frames from unconstrained videos which are considerably shaky, recent works fail to alig...
-
Chapter and Conference Paper
Panorama from Representative Frames of Unconstrained Videos Using DiffeoMeshes
Panorama creation from unconstrained hand-held videos is a challenging task due to the presence of large parallax, moving objects and motion blur. Alignment of the frames taken from a hand-held video is often ...
-
Chapter and Conference Paper
Predicting Video Frames Using Feature Based Locally Guided Objectives
This paper presents feature reconstruction based approach using Generative Adversarial Networks (GAN) to solve the problem of predicting future frames from natural video scenes. Recent GAN based methods often ...
-
Chapter and Conference Paper
Context Graph Based Video Frame Prediction Using Locally Guided Objective
This paper proposes a feature reconstruction based approach using pixel-graph and Generative Adversarial Networks (GAN) for solving the problem of synthesizing future frames from video scenes. Recent methods o...
-
Chapter and Conference Paper
PosIX-GAN: Generating Multiple Poses Using GAN for Pose-Invariant Face Recognition
Pose-Invariant Face Recognition (PIFR) has been a serious challenge in the general field of face recognition (FR). The performance of face recognition algorithms deteriorate due to various degradations such as...
-
Chapter and Conference Paper
Motion-Based Occlusion-Aware Pixel Graph Network for Video Object Segmentation
This paper proposes a dual-channel based Graph Convolutional Network (GCN) for the Video Object Segmentation (VOS) task. The main contribution lies in formulating two pixel graphs based on the raw RGB and opti...
-
Chapter and Conference Paper
Dynamic Class Learning Approach for Smart CBIR
Smart Content Based Image Retrieval (CBIR) helps to simultaneously localize and recognize all object(s) present in a scene, for image retrieval task. The major drawbacks in such kind of system are: (a) overhea...
-
Chapter and Conference Paper
Large Parallax Image Stitching Using an Edge-Preserving Diffeomorphic War** Process
Image Stitching is a hard task to solve in the presence of large parallax in video frames. In many cases, video frames shot using hand-held cameras have low resolution, blur and large parallax errors. Most rec...
-
Book and Conference Proceedings
-
Chapter and Conference Paper
Eigen Domain Transformation for Soft-Margin Multiple Feature-Kernel Learning for Surveillance Face Recognition
Face Recognition (FR) is the most accepted method of biometric authentication due to its inherent passive nature. This has attracted a lot of researchers over past few decades to achieve an moderately high acc...
-
Chapter and Conference Paper
Simultaneous Reconstruction of Multiple Hand Shredded Content-Less Pages Using Graph-Based Global Reassembly
Hand shredded content-less pages reassembly is a challenging task. This has applications in forensics and fun games. The process is even more tedious when the number of pages from which the fragments are obtai...
-
Chapter and Conference Paper
Two-Stream Convolutional Network with Multi-level Feature Fusion for Categorization of Human Action from Videos
This paper presents the results of the exploration of a two-stream Convolutional Neural Network (2S-CNN) architecture, with a novel feature fusion technique at multiple levels, to categorize events in videos. ...
-
Chapter and Conference Paper
Graph-Based Clustering for Apictorial Jigsaw Puzzles of Hand Shredded Content-less Pages
Reassembling hand shredded content-less pages is a challenging task, with applications in forensics and fun games. This paper proposes an efficient iterative framework to solve apictorial jigsaw puzzles of han...
-
Chapter and Conference Paper
Performance of Deep Learning Algorithms vs. Shallow Models, in Extreme Conditions - Some Empirical Studies
Deep convolutional neural networks (DCNN) successfully exhibit exceptionally good classification performance, despite their massive size. The effect of a large value of noise term, as irreducible error in Expe...
-
Article
Detecting aircrafts from satellite images using saliency and conical pyramid based template representation
Automatic target localization in satellite images still remains as a challenging problem in the field of computer vision. The issues involved in locating targets in satellite images are viewpoint, spectral (in...
