arXiv subjects

Tapas Samanta

Publications and source records attributed to Tapas Samanta.

At least 19 recordsLinked to original sources

arXiv2026

A HamNoSys-Guided Dataset and Baselines for Fine-Grained Isolated Handshape Recognition in Sign Language

Purpose: Fine-grained handshape recognition supports computational sign-language transcription, recognition, and translation, but broad, phonetically defined visual inventories with signer-aware evaluation remain limited. This work introduces a benchmark grounded in the language-independent Hamburg Notation System (HamNoSys). Methods: A balanced dataset of 144,000 RGB images was collected from 15 participants for 160 handshape classes defined by the official HamNoSys 4 Handshapes Chart. ResNet-18 and ViT-B/16 were evaluated as appearance-based models, while a graph convolutional network and XGBoost were evaluated from hand landmarks. Both a class-stratified subject-dependent split and a 15-fold leave-one-subject-out (LOSO) protocol were used. The same model families were additionally assessed on LSWH100 and ASL Fingerspelling Dataset A for external context. Results: The subject-dependent benchmarks established reproducible reference performance across all four model families, whereas LOSO evaluation exposed a substantial reduction when recognition was required to generalise to unseen participants. On ASL Fingerspelling Dataset A, mean LOSO top-1 accuracy ranged from 82.20% to 87.40%. Conclusion: The documented acquisition, curation, and complementary evaluation protocols pro-vide a reproducible resource for fine-grained isolated-handshape research and for developing more accessible sign-language technologies.

cs.CV↗

arXiv2026

Analysis of Federated Aggregation under Model Poisoning and Backdoor Attacks: A Reconstructed Cross-Dataset and Cross-Architecture Benchmark

Robust comparisons of federated aggregation methods require joint consideration of predictive performance, threat definitions, metric semantics, and execution provenance. A 500-cell seed-1 evaluation matrix was reconstructed across five aggregation methods, five datasets, five architectures, and four recorded conditions: clean, sign-flipping, Gaussian, and BadNets. Successful execution logs were identified for 454 original runs and 36 repaired or rerun executions, whereas 10 clean SVHN cells were supported by summary-only provenance. Trimmed Mean achieved the highest clean macro-mean accuracy (76.02%) and the lowest mean within-task rank (1.70). Krum attained the highest recorded accuracy under both sign-flipping and Gaussian configurations. These relative rankings remained unchanged when analysis was restricted to 21 task pairs for which original successful logs were available for every method-condition combination. Audit of the supplied BadNets metric implementation established that every test input is triggered prior to target-label counting; consequently, the retained metric represents Triggered Target-Label Rate (TTLR) rather than a conventional target-excluding attack success rate. An audit of the supplied FedPARETO scaffold further identified a pathway in which predictive summaries may characterize an uncorrupted local model while the aggregation weight is applied to a separately corrupted update, introducing a potential discrepancy between reported predictive outcomes and the updates used for aggregation. The canonical matrix contains a single identified seed for each cell, and exact attack and configuration lineage is incomplete. Accordingly, the findings should be interpreted as descriptive comparisons within the recorded configurations and not as statistical estimates or universal claims regarding robustness.

cs.LG↗

arXiv2026

DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting

Federated learning repeatedly incurs local optimization and model-update transmission. We study DG-FedReuse, a simulator-level mechanism that allows selected clients to contribute age-decayed cached updates when a stochastic head-gradient discrepancy proxy remains below a round-dependent threshold. A hard cache-age limit and minimum fresh-client quota constrain reuse, while fresh updates use an adaptive per-tensor Top-K numerical-field representation. Experiments cover six image-classification datasets, 50 virtual clients, Dirichlet label heterogeneity ({\alpha}=0.5), and three seeds. At a common 90-round budget, DG-FedReuse yields 83.36-85.42% modeled update-data-field uplink saving, compared with 76.88% for matched Top-K FedAvg; the seed-aligned accuracy differences range from -5.29 to -0.14 percentage points. Best-observed test accuracies obtained under test-controlled checkpointing are retained only as exploratory archival evidence and range from -2.38 to +0.45 percentage points relative to matched FedAvg. A symmetric dense-model-downlink sensitivity reduces the headline saving to 41.68-F42.71% and the incremental gain over Top-K FedAvg to 3.24-4.27 percentage points, demonstrating the dependence of communication conclusions on the accounting boundary. The study characterizes the proposed reuse rule in the implemented simulator; it does not establish unbiased generalization, end-to-end bandwidth reduction, runtime or energy savings, faster convergence, or superiority over existing stale-update and lazy-aggregation methods.

cs.LG↗

arXiv2026

RES-DARE: Failure-Aware Expert Adaptation and Rollback-Safe Self-Repair for Intrusion Detection

Intrusion detection systems are often trained under static benchmark conditions, although deployed network environments are affected by traffic drift, sensor noise, changing workloads, and evolving attack behaviour. Under such distribution shifts, static detectors may produce confident but incorrect predictions, leading to silent and unsafe failure modes. In this paper, RES-DARE (Recursive Evolving Specialists-Digital Adaptive Reasoning Engine) is proposed as a failure-aware continual intrusion detection framework with rollback-safe self-repair. Difficult, uncertain, and misclassified samples are treated as failure signals for expert specialisation rather than being discarded as noise. A supervised contrastive encoder, two-pass expert router, failure-buffer mechanism, HDBSCAN-based failure-region discovery, and trust-risk monitor are integrated to support adaptive IDS behaviour. AEHM-v2 is introduced as a rollback-safe repair mechanism, where candidate adaptations are provisionally activated and committed only when macro-F1 is preserved or improved while trust risk remains stable. Otherwise, the system is rolled back to its last validated state. RES-DARE is evaluated on CICIDS2017, UNSW-NB15, and TON\_IoT, achieving macro-F1 scores of 0.9850, 0.9736, and 0.9691, respectively. Under Gaussian feature corruption at strength 0.10, RES-DARE retains an Attack-F1 of 0.7920 on CICIDS2017 and achieves near-zero catastrophic forgetting with F = 0.0015. The results show that RES-DARE improves robustness, warning capability, and deployment safety under degraded conditions.

cs.CR↗

arXiv2026

PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation

Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech datasets, raising major privacy concerns. The problem is more acute for personalized talking-head generation, where identity-specific data are highly sensitive and often cannot be pooled across users or devices. PrivFedTalk is presented as a privacy-aware federated framework for personalized talking-head generation that combines conditional latent diffusion with parameter-efficient identity adaptation. A shared diffusion backbone is trained across clients, while each client learns lightweight LoRA identity adapters from local private audio-visual data, avoiding raw data sharing and reducing communication cost. To address heterogeneous client distributions, Identity-Stable Federated Aggregation (ISFA) weights client updates using privacy-safe scalar reliability signals computed from on-device identity consistency and temporal stability estimates. Temporal-Denoising Consistency (TDC) regularization is introduced to reduce inter-frame drift, flicker, and identity drift during federated denoising. To limit update-side privacy risk, secure aggregation and client-level differential privacy are applied to adapter updates. The implementation supports both low-memory GPU execution and multi-GPU client-parallel training on heterogeneous shared hardware. Comparative experiments on the present setup across multiple training and aggregation conditions with PrivFedTalk, FedAvg, and FedProx show stable federated optimization and successful end-to-end training and evaluation under constrained resources. The results support the feasibility of privacy-aware personalized talking-head training in federated environments, while suggesting that stronger component-wise, privacy-utility, and qualitative claims need further standardized evaluation.

cs.CR↗

arXiv2026

BayesFusion-SDF: Probabilistic Signed Distance Fusion with View Planning on CPU

Key part of robotics, augmented reality, and digital inspection is dense 3D reconstruction from depth observations. Traditional volumetric fusion techniques, including truncated signed distance functions (TSDF), enable efficient and deterministic geometry reconstruction; however, they depend on heuristic weighting and fail to transparently convey uncertainty in a systematic way. Recent neural implicit methods, on the other hand, get very high fidelity but usually need a lot of GPU power for optimization and aren't very easy to understand for making decisions later on. This work presents BayesFusion-SDF, a CPU-centric probabilistic signed distance fusion framework that conceptualizes geometry as a sparse Gaussian random field with a defined posterior distribution over voxel distances. First, a rough TSDF reconstruction is used to create an adaptive narrow-band domain. Then, depth observations are combined using a heteroscedastic Bayesian formulation that is solved using sparse linear algebra and preconditioned conjugate gradients. Randomized diagonal estimators are a quick way to get an idea of posterior uncertainty. This makes it possible to extract surfaces and plan the next best view while taking into account uncertainty. Tests on a controlled ablation scene and a CO3D object sequence show that the new method is more accurate geometrically than TSDF baselines and gives useful estimates of uncertainty for active sensing. The proposed formulation provides a clear and easy-to-use alternative to GPU-heavy neural reconstruction methods while still being able to be understood in a probabilistic way and acting in a predictable way. GitHub: https://mazumdarsoumya.github.io/BayesFusionSDF

cs.CV↗

arXiv2026

VineetVC: Adaptive Video Conferencing Under Severe Bandwidth Constraints Using Audio-Driven Talking-Head Reconstruction

Intense bandwidth depletion within consumer and constrained networks has the potential to undermine the stability of real-time video conferencing: encoder rate management becomes saturated, packet loss escalates, frame rates deteriorate, and end-to-end latency significantly increases. This work delineates an adaptive conferencing system that integrates WebRTC media delivery with a supplementary audio-driven talking-head reconstruction pathway and telemetry-driven mode regulation. The system consists of a WebSocket signaling service, an optional SFU for multi-party transmission, a browser client capable of real-time WebRTC statistics extraction and CSV telemetry export, and an AI REST service that processes a reference face image and recorded audio to produce a synthesized MP4; the browser can substitute its outbound camera track with the synthesized stream with a median bandwidth of 32.80 kbps. The solution incorporates a bandwidth-mode switching strategy and a client-side mode-state logger.

eess.IV↗

arXiv2026

VedicTHG: Symbolic Vedic Computation for Low-Resource Talking-Head Generation in Educational Avatars

Talking-head avatars are increasingly adopted in educational technology to deliver content with social presence and improved engagement. However, many recent talking-head generation (THG) methods rely on GPU-centric neural rendering, large training sets, or high-capacity diffusion models, which limits deployment in offline or resource-constrained learning environments. A deterministic and CPU-oriented THG framework is described, termed Symbolic Vedic Computation, that converts speech to a time-aligned phoneme stream, maps phonemes to a compact viseme inventory, and produces smooth viseme trajectories through symbolic coarticulation inspired by Vedic sutra Urdhva Tiryakbhyam. A lightweight 2D renderer performs region-of-interest (ROI) warping and mouth compositing with stabilization to support real-time synthesis on commodity CPUs. Experiments report synchronization accuracy, temporal stability, and identity consistency under CPU-only execution, alongside benchmarking against representative CPU-feasible baselines. Results indicate that acceptable lip-sync quality can be achieved while substantially reducing computational load and latency, supporting practical educational avatars on low-end hardware. GitHub: https://vineetkumarrakesh.github.io/vedicthg

cs.CV↗

arXiv2025

Fostering Innovation: Streamlining Magnetocaloric Materials Research by Digitalization

Refrigeration based on the magnetocaloric effect (MCE) can contribute to energysaving, environmentally friendly cooling in private households, or industrial application. The cooling is based on the reversible heat release or uptake during a phase-transformation of the materials that can be controlled by a magnetic field. This process could replace conventional compression-based refrigeration, which often relies on environmentally harmful refrigerants. Here we show, how to digitalize the process chain for the synthesis, theoretical and experimental characterization, and prototypical application of magnetocaloric alloy. Different Heusler alloys are examined experimentally as model systems for potential application in magnetic cooling. OTTR templates are used for the acquisition and semantic representation of knowledge in the development of an ontology. The ontology, when combined with unstructured data, can be exploited to train a model that can then be used to predict missing facts, which can help to gain new insights and to generate new hypotheses. Furthermore, tools are developed that automate data acquisition into ontological structures and workflows are implemented that provide an easy-to-use theoretical and experimental evaluation of the MCE from first principles and raw data.

cond-mat.mtrl-sci↗

arXiv2025

Analysis of Hyperparameter Optimization Effects on Lightweight Deep Models for Real-Time Image Classification

Lightweight convolutional and transformer-based networks are increasingly preferred for real-time image classification, especially on resource-constrained devices. This study evaluates the impact of hyperparameter optimization on the accuracy and deployment feasibility of seven modern lightweight architectures: ConvNeXt-T, EfficientNetV2-S, MobileNetV3-L, MobileViT v2 (S/XS), RepVGG-A2, and TinyViT-21M, trained on a class-balanced subset of 90,000 images from ImageNet-1K. Under standardized training settings, this paper investigates the influence of learning rate schedules, augmentation, optimizers, and initialization on model performance. Inference benchmarks are performed using an NVIDIA L40s GPU with batch sizes ranging from 1 to 512, capturing latency and throughput in real-time conditions. This work demonstrates that controlled hyperparameter variation significantly alters convergence dynamics in lightweight CNN and transformer backbones, providing insight into stability regions and deployment feasibility in edge artificial intelligence. Our results reveal that tuning alone leads to a top-1 accuracy improvement of 1.5 to 3.5 percent over baselines, and select models (e.g., RepVGG-A2, MobileNetV3-L) deliver latency under 5 milliseconds and over 9,800 frames per second, making them ideal for edge deployment. This work provides reproducible, subset-based insights into lightweight hyperparameter tuning and its role in balancing speed and accuracy. The code and logs may be seen at: https://vineetkumarrakesh.github.io/lcnn-opt

cs.CV↗

arXiv2025

Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions

Talking Head Generation (THG) has emerged as a transformative technology in computer vision, enabling the synthesis of realistic human faces synchronized with image, audio, text, or video inputs. This paper provides a comprehensive review of methodologies and frameworks for talking head generation, categorizing approaches into 2D--based, 3D--based, Neural Radiance Fields (NeRF)--based, diffusion--based, parameter-driven techniques and many other techniques. It evaluates algorithms, datasets, and evaluation metrics while highlighting advancements in perceptual realism and technical efficiency critical for applications such as digital avatars, video dubbing, ultra-low bitrate video conferencing, and online education. The study identifies challenges such as reliance on pre--trained models, extreme pose handling, multilingual synthesis, and temporal consistency. Future directions include modular architectures, multilingual datasets, hybrid models blending pre--trained and task-specific layers, and innovative loss functions. By synthesizing existing research and exploring emerging trends, this paper aims to provide actionable insights for researchers and practitioners in the field of talking head generation. For the complete survey, code, and curated resource list, visit our GitHub repository: https://github.com/VineetKumarRakesh/thg.

cs.CV↗

arXiv2025

Observation of magnetic skyrmion lattice in Cr$_{0.82}$Mn$_{0.18}$Ge by small-angle neutron scattering

Incommensurate magnetic phases in chiral cubic crystals are an established source of topological spin textures such as skyrmion and hedgehog lattices, with potential applications in spintronics and information storage. We report a comprehensive small-angle neutron scattering (SANS) study on the $B20$-type chiral magnet Cr$_{0.82}$Mn$_{0.18}$Ge, exploring its magnetic phase diagram and confirming the stabilization of a skyrmion lattice under low magnetic fields. Our results reveal a helical ground state with a decreasing pitch from 40 nm to 35 nm upon cooling, and a skyrmion phase stable in applied magnetic fields of 10-30 mT, and over an unusually wide temperature range for chiral magnets of 6 K ($\sim T_\textrm{C}/2 < T < T_\textrm{C}$, $T_\textrm{C}=13$ K). The skyrmion lattice forms a standard two-dimensional hexagonal coordination that can be trained into a single domain, distinguishing it from the three-dimensional hedgehog lattice observed in MnGe-based systems. Additionally, we demonstrate the persistence of a metastable SkL at 2 K, even at zero field. These findings advance our understanding of magnetic textures in Cr-based $B20$ compounds, highlighting Cr$_{0.82}$Mn$_{0.18}$Ge~as a promising material for further exploration in topological magnetism.

cond-mat.mes-hall↗

arXiv2024

Enhancing ASL Recognition with GCNs and Successive Residual Connections

This study presents a novel approach for enhancing American Sign Language (ASL) recognition using Graph Convolutional Networks (GCNs) integrated with successive residual connections. The method leverages the MediaPipe framework to extract key landmarks from each hand gesture, which are then used to construct graph representations. A robust preprocessing pipeline, including translational and scale normalization techniques, ensures consistency across the dataset. The constructed graphs are fed into a GCN-based neural architecture with residual connections to improve network stability. The architecture achieves state-of-the-art results, demonstrating superior generalization capabilities with a validation accuracy of 99.14%.

cs.CV↗

arXiv2016

The emergence of giant multicaloric phenomena near room temperature

Caloric responses (temperature changes) can be induced in solid-state materials by applying external stimuli such as stress, pressure, and electric and magnetic fields. The magnetic-field-stimulated response is called the magnetocaloric effect, and materials that exhibit this property have long been sought for applications in room temperature magnetic cooling due to their potentially superior efficiency and low impact on the environment. Other solid-state caloric phenomena are less developed, but are likewise under intense investigation. Here we introduce a new material that not only displays giant barocaloric (hydrostatic-pressure-induced) properties, but also a large magnetocaloric response near room temperature. It is unprecedented that two caloric effects of such extreme magnitude occur in the same material and at the same temperature. These effects originate from a magnetostructural transition and a magneto-volume (magnetostriction) effect where the volume change is large enough to force the system from a localized ordered state into an itinerant paramagnetic state.

cond-mat.mtrl-sci↗

arXiv2015

Effects of pressure on the magnetostructural and magnetocaloric properties of isostructurally alloyed (MnNiSi)1-x(FeCoGe)x

The isostructural alloying of two compounds with extremely different magnetic and thermo-structural properties has resulted in a new system, (MnNiSi)1-x(FeCoGe)x, that exhibits extraordinary magnetocaloric properties with an acute sensitivity to applied hydrostatic pressure (P). Application of hydrostatic pressure shifts the first-order phase transition to lower temperature ($\Delta$ T=-41 K with P=3.43 kbar) but preserves the giant value of isothermal entropy change (-$\Delta$S$\max$=143.7 J/kg K for a field change of {\Delta}B=5 T at atmospheric pressure). Together with the magnetic field, this pressure-induced temperature shift can be used to significantly increase the effective relative cooling power.

cond-mat.mtrl-sci↗

arXiv2014

Pressure-induced giant enhancement of magnetocaloric effects in MnNiSi-based systems

A remarkable decrease of the structural transition temperature of MnNiSi from 1200 K to <300 K by chemically alloying it with MnFeGe results in a coupling of the magnetic and structural transitions, leading to a large magnetocaloric effect near room temperature. It was found that the magnetostructural transition is highly sensitive to external (hydrostatic) pressure: relatively low hydrostatic pressures (~2.4 kbar) lead to an extraordinary enhancement of the isothermal entropy change from $-$Δ$S$ = 44 to 89 J/kg K at ambient (atmospheric) and 2.4 kbar applied pressures, respectively, for a field change of Δ$H$ = 5 T. This giant entropy change is associated with a large relative volume change of about 7% induced by 2.4 kbar applied pressure during the magnetostructural transition. The pressure-enhanced magnetocaloric effects are accompanied by a shift in transition temperature, an effect that may be exploited to tune the transition to the required working temperature, and thereby eliminate the need for a given material to possess a large magnetocaloric effect (i.e., entropy change) over a wide temperature range. Furthermore, this material also possesses negligible hysteresis losses.

cond-mat.mtrl-sci↗

arXiv2009

Inverse magnetocaloric effect in polycrystalline La$_{0.125}$Ca$_{0.875}$MnO$_{3}$

Recently the inverse magnetocaloric effect is observed for different compounds. However there is very rare for any manifestation of the effect to be seen in manganites. We have found inverse magnetocaloric effect in the case of polycrystalline La$_{0.125}$Ca$_{0.875}$MnO$_{3}$. Such phenomenon is attributed to the stabilization of antiferromagnetic state associated with inherent magnetic inhomogeneous phases for this compound.

cond-mat.mtrl-sci↗

arXiv2009

Magnetocaloric properties of nanocrystalline La$_{0.125}$Ca$_{0.875}$MnO$_{3}$

Some recent experimental studies show the invisibility of antiferromagnetic transition in the cases of manganites when their particle size is reduced to nanometer scale. In complete contrast to these cases, we have observed the signature of antiferromagnetic transition in the magnetocaloric properties of nanocrystalline La$_{0.125}$Ca$_{0.875}$MnO$_{3}$ of average particle size 70 and 60 nm similar to its polycrystalline bulk form. The system exhibit inverse magnetocaloric effect in its polycrystalline and nanocrystalline form. An extra ferromagnetic phase is stabilized at low temperature for the sample with particle size $\sim 60$ nm.

cond-mat.mtrl-sci↗