arXiv subjects

Ankit Yadav

Publications and source records attributed to Ankit Yadav.

25 records · Page 2Linked to original sources

arXiv2024

Towards Effective Image Forensics via A Novel Computationally Efficient Framework and A New Image Splice Dataset

Splice detection models are the need of the hour since splice manipulations can be used to mislead, spread rumors and create disharmony in society. However, there is a severe lack of image splicing datasets, which restricts the capabilities of deep learning models to extract discriminative features without overfitting. This manuscript presents two-fold contributions toward splice detection. Firstly, a novel splice detection dataset is proposed having two variants. The two variants include spliced samples generated from code and through manual editing. Spliced images in both variants have corresponding binary masks to aid localization approaches. Secondly, a novel Spatio-Compression Lightweight Splice Detection Framework is proposed for accurate splice detection with minimum computational cost. The proposed dual-branch framework extracts discriminative spatial features from a lightweight spatial branch. It uses original resolution compression data to extract double compression artifacts from the second branch, thereby making it 'information preserving.' Several CNNs are tested in combination with the proposed framework on a composite dataset of images from the proposed dataset and the CASIA v2.0 dataset. The best model accuracy of 0.9382 is achieved and compared with similar state-of-the-art methods, demonstrating the superiority of the proposed framework.

cs.CV↗

arXiv2024

Datasets, Clues and State-of-the-Arts for Multimedia Forensics: An Extensive Review

With the large chunks of social media data being created daily and the parallel rise of realistic multimedia tampering methods, detecting and localising tampering in images and videos has become essential. This survey focusses on approaches for tampering detection in multimedia data using deep learning models. Specifically, it presents a detailed analysis of benchmark datasets for malicious manipulation detection that are publicly available. It also offers a comprehensive list of tampering clues and commonly used deep learning architectures. Next, it discusses the current state-of-the-art tampering detection methods, categorizing them into meaningful types such as deepfake detection methods, splice tampering detection methods, copy-move tampering detection methods, etc. and discussing their strengths and weaknesses. Top results achieved on benchmark datasets, comparison of deep learning approaches against traditional methods and critical insights from the recent tampering detection methods are also discussed. Lastly, the research gaps, future direction and conclusion are discussed to provide an in-depth understanding of the tampering detection research arena.

cs.CV↗

arXiv2023

Bifurcation cascade, self-similarity and duality in the 3-rotor problem

The three-rotor system concerns equally massive point particles moving on a circle subject to attractive cosine potentials of strength $g$. The quantum theory models chains of coupled Josephson junctions. Classically, it displays order-chaos-order behavior with increasing energy $E$ along with a seemingly globally chaotic phase for $5.33g \lesssim E \lesssim 5.6g$. It is also known to admit pendulum and isosceles breather families of periodic orbits at all energies. While pendula display a doubly infinite sequence of stability transitions accumulating at their libration to rotation threshold at $E = 4g$, breathers undergo only one stability transition. Here, we show that these stability transitions are associated to forward and reverse fork-like isochronous and period-doubling bifurcations. The new family of periodic orbits born at each of these bifurcations is found using an efficient search algorithm starting from a transverse perturbation to the parent orbit. The graphs of stability indices of various classes of orbits born at pendulum bifurcations meet at $E = 4g$ forming `fans'. The transitions in the librational and rotational phases are related by an asymptotic duality between bifurcation energies and shapes of newly born periodic orbits. The latter are captured by solutions to a Lamé equation. We also find and numerically validate values of scaling constants for self-similarity in (a) stability indices of librational and rotational pendula and (b) shapes of newly born orbits as $E \to 4g$. Finally, we argue that none of the infinitely many families of periodic orbits we have found is stable for $5.33g \lesssim E \lesssim 5.6g$, providing further evidence for global chaos in this energy band.

nlin.CD↗

arXiv2023

LAHM : Large Annotated Dataset for Multi-Domain and Multilingual Hate Speech Identification

Current research on hate speech analysis is typically oriented towards monolingual and single classification tasks. In this paper, we present a new multilingual hate speech analysis dataset for English, Hindi, Arabic, French, German and Spanish languages for multiple domains across hate speech - Abuse, Racism, Sexism, Religious Hate and Extremism. To the best of our knowledge, this paper is the first to address the problem of identifying various types of hate speech in these five wide domains in these six languages. In this work, we describe how we created the dataset, created annotations at high level and low level for different domains and how we use it to test the current state-of-the-art multilingual and multitask learning approaches. We evaluate our dataset in various monolingual, cross-lingual and machine translation classification settings and compare it against open source English datasets that we aggregated and merged for this task. Then we discuss how this approach can be used to create large scale hate-speech datasets and how to leverage our annotations in order to improve hate speech detection and classification in general.

cs.CL↗

arXiv2021

Interaction of Active Janus Particles with Passive Tracers

In this study, we investigated the motion of active SiO2-Pt Janus particles in the 2D bath of smaller silica tracers dispersed in varying areal densities. The effect on the organization of the tracer particles around the active JPs was also explored. Our experiments indicate that the interaction between the tracers and the active JPs mainly depend on the nature of collision marked by the duration of contact. For all the concentration regimes, we have shown that the short time collisions do not have significant impact on the motion of active JPs, however, during moderate/long-time collisions tracer(s) can lead to a significant change in active JPs motion and even cause them to rotate. In the concentrated regime, our experiments reveal the emergence of a novel organizational behavior of the passive tracers on the trailing Pt and the leading SiO2 with a strong dependence on the nature of collision.

cond-mat.soft↗

arXiv2020

Person Re-Identification using Deep Learning Networks: A Systematic Review

Person re-identification has received a lot of attention from the research community in recent times. Due to its vital role in security based applications, person re-identification lies at the heart of research relevant to tracking robberies, preventing terrorist attacks and other security critical events. While the last decade has seen tremendous growth in re-id approaches, very little review literature exists to comprehend and summarize this progress. This review deals with the latest state-of-the-art deep learning based approaches for person re-identification. While the few existing re-id review works have analysed re-id techniques from a singular aspect, this review evaluates numerous re-id techniques from multiple deep learning aspects such as deep architecture types, common Re-Id challenges (variation in pose, lightning, view, scale, partial or complete occlusion, background clutter), multi-modal Re-Id, cross-domain Re-Id challenges, metric learning approaches and video Re-Id contributions. This review also includes several re-id benchmarks collected over the years, describing their characteristics, specifications and top re-id results obtained on them. The inclusion of the latest deep re-id works makes this a significant contribution to the re-id literature. Lastly, the conclusion and future directions are included.

cs.CV↗

arXiv2018

Distributed Learning Algorithms for Opportunistic Spectrum Access in Infrastructure-less Networks

An opportunistic spectrum access (OSA) for the infrastructure-less (or cognitive ad-hoc) network has received significant attention thanks to emerging paradigms such as the Internet of Things (IoTs) and smart grids. Research in this area has evolved from the \r{ho}rand algorithm requiring prior knowledge of the number of active secondary users (SUs) to the musical chair (MC) algorithm where the number of SUs are unknown and estimated independently at each SU. These works ignore the number of collisions in the network leading to wastage of power and bring down the effective life of battery operated SUs. In this paper, we develop algorithms for OSA that learn faster and incurs fewer number of collisions i.e. energy efficient. We consider two types of infrastructure-less decentralized networks: 1) static network where the number of SUs are fixed but unknown, and 2) dynamic network where SUs can independently enter or leave the network. We set up the problem as a multi-player mult-armed bandit and develop two distributed algorithms. The analysis shows that when all the SUs independently implement the proposed algorithms, the loss in throughput compared to the optimal throughput, i.e. regret, is a constant with high probability and significantly outperforms existing algorithms both in terms of regret and number of collisions. Fewer collisions make them ideally suitable for battery operated SU terminals. We validate our claims through exhaustive simulated experiments as well as through a realistic USRP based experiments in a real radio environment.

eess.SP↗