Search

Generative AI has transformed the fields of Design and Manufacturing by providing efficient and automated methods for generating and modifying 3D objects. One approach involves using Large Language Models (LLMs) to generate Computer- Aided Design (CAD) scripting code, which can then be executed to render a 3D object; however, the resulting 3D object may not meet the specified requirements. Testing the correctness of CAD generated code is challenging due to the complexity and structure of 3D objects (e.g., shapes, surfaces, and dimensions) that are not feasible in code. In this paper, we introduce CADCodeVerify, a novel approach to iteratively verify and improve 3D objects generated from CAD code. Our approach works by producing ameliorative feedback by prompting a Vision-Language Model (VLM) to generate and answer a set of validation questions to verify the generated object and prompt the VLM to correct deviations. To evaluate CADCodeVerify, we introduce, CADPrompt, the first benchmark for CAD code generation, consisting of 200 natural language prompts paired with expert-annotated scripting code for 3D objects to benchmark progress. Our findings show that CADCodeVerify improves VLM performance by providing visual feedback, enhancing the structure of the 3D objects, and increasing the success rate of the compiled program. When applied to GPT-4, CADCodeVerify achieved a 7.30% reduction in Point Cloud distance and a 5.0% improvement in success rate compared to prior work, Comment

In this paper, we propose a novel and generalizable zero-shot knowledge transfer framework that distills expert sports navigation strategies from web videos into robotic systems with adversarial constraints and out-of-distribution image trajectories. Our pipeline enables diffusion-based imitation learning by reconstructing the full 3D task space from multiple partial views, warping it into 2D image space, closing the planning loop within this 2D space, and transfer constrained motion of interest back to task space. Additionally, we demonstrate that the learned policy can serve as a local planner in conjunction with position control. We apply this framework in the wheelchair tennis navigation problem to guide the wheelchair into the ball-hitting region. Our pipeline achieves a navigation success rate of 97.67% in reaching real-world recorded tennis ball trajectories with a physical robot wheelchair, and achieve a success rate of 68.49% in a real-world, real-time experiment on a full-sized tennis court., Comment: This manuscript has been submitted to 2025 IEEE International Conference on Robotics & Automation (ICRA)

Advances in robot learning have enabled robots to generate skills for a variety of tasks. Yet, robot learning is typically sample inefficient, struggles to learn from data sources exhibiting varied behaviors, and does not naturally incorporate constraints. These properties are critical for fast, agile tasks such as playing table tennis. Modern techniques for learning from demonstration improve sample efficiency and scale to diverse data, but are rarely evaluated on agile tasks. In the case of reinforcement learning, achieving good performance requires training on high-fidelity simulators. To overcome these limitations, we develop a novel diffusion modeling approach that is offline, constraint-guided, and expressive of diverse agile behaviors. The key to our approach is a kinematic constraint gradient guidance (KCGG) technique that computes gradients through both the forward kinematics of the robot arm and the diffusion model to direct the sampling process. KCGG minimizes the cost of violating constraints while simultaneously keeping the sampled trajectory in-distribution of the training data. We demonstrate the effectiveness of our approach for time-critical robotic tasks by evaluating KCGG in two challenging domains: simulated air hockey and real table tennis. In simulated air hockey, we achieved a 25.4% increase in block rate, while in table tennis, we saw a 17.3% increase in success rate compared to imitation learning baselines.

We give a refined description of the dominant spectrum of a non-local operator that models growth and equal mitosis of cells. More precisely we look at the spectrum in half planes at the right hand side of the first accumulation point of eigenvalues and give criteria on the weight of weighted $L^1$ spaces for this spectrum to be made of explicit simple eigenvalues. The method relies on a high order long time asymptotic expansion of the solutions to the associated evolution equation obtained in [Zaidi, van Brunt, Wake, Proc. A, R. Soc. Lond., 2015] combined with a Weyl theorem taken from [Mischler, Scher, Ann. Inst. Henri Poincar\'e, Anal. Non Lin\'eaire, 2016].

In this work, we study the charged current induced neutrino and antineutrino scattering from the free nucleon target. This study has been performed in the energy range of a few GeV, relevant for the (anti)neutrino oscillation experiments with accelerator and atmospheric neutrinos. For a few GeV neutrino, the contribution to the cross section mainly comes from the quasielastic, the inelastic production of mesons like pion, kaon, eta, and hyperons as well as from the deep inelastic scattering by the weak currents in $\Delta S$=0 and $\Delta S$=1 sectors. The numerical results are presented for the $Q^2$ distribution of the differential cross section for all the aforementioned processes. The effect of the cut on the center of mass energy $W$ has been explicitly discussed., Comment: Submitted to Eur. Phys. J. ST special issue "Radio detection of ultra-high energy neutrino and cosmic ray"; 17 pages, 12 figures, 3 tables

In this paper, we introduce bi-slant Riemannian maps from Riemannian manifolds to Kenmotsu manifolds, which are the natural generalizations of invariant, anti-invariant, semi-invariant, slant, semi-slant and hemi-slant Riemannian maps, with nontrivial examples. We study these maps and give some curvature relations for $(rangeF_*)^\perp$. We construct Chen-Ricci inequalities, DDVV inequalities, and further some optimal inequalities involving Casorati curvatures from bi-slant Riemannian manifolds to Kenmotsu space forms.

Discovering a lexicon from unlabeled audio is a longstanding challenge for zero-resource speech processing. One approach is to search for frequently occurring patterns in speech. We revisit this idea with DUSTED: Discrete Unit Spoken-TErm Discovery. Leveraging self-supervised models, we encode input audio into sequences of discrete units. Next, we find repeated patterns by searching for similar unit sub-sequences, inspired by alignment algorithms from bioinformatics. Since discretization discards speaker information, DUSTED finds better matches across speakers, improving the coverage and consistency of the discovered patterns. We demonstrate these improvements on the ZeroSpeech Challenge, achieving state-of-the-art results on the spoken-term discovery track. Finally, we analyze the duration distribution of the patterns, showing that our method finds longer word- or phrase-like terms., Comment: Accepted to Interspeech 2024

We present results from the molecular dynamics (MD) simulation of surface-directed spinodal decomposition (SDSD) in binary fluid mixtures ($A+B$) with off-critical compositions. The aim is to elucidate the role of composition ratio in the early-time wetting kinetics under the influence of long-range surface potential. In our simulations, the attractive part of surface potential varies as $V(z)= -\epsilon_a/z^{n}$, with $\epsilon_{a}$ being the surface-potential strength. The surface prefers `$A$' species to form the wetting layer. Its thickness [$R_1(t)$] for the majority wetting (number of $A$-type particles [$N_A$] > number of $B$-type particles [$N_B$]), grows as a power-law with an exponent $1/(n+2)$. This is consistent with the early-time kinetics in the form of potential-dependent growth present in the Puri-Binder model. However, for minority wetting ($N_A$ < $N_B$), the growth exponent in $R_1(t)$ is less than $1/(n+2)$. Furthermore, on decreasing the field strength $\epsilon_{a}$, we recover $1/(n+2)$ for a minority wetting case. We provide phenomenological arguments to explain the early-time wetting kinetics for both cases., Comment: 11 pages, 7 figures

The internet of things (IoT) and other emerging ubiquitous technologies are supporting the rapid spread of smart systems, which has underlined the need for safe, open, and decentralized data storage solutions. With its inherent decentralization and immutability, blockchain offers itself as a potential solution for these requirements. However, the practicality of incorporating blockchain into real-time sensor data storage systems is a topic that demands in-depth examination. While blockchain promises unmatched data security and auditability, some intrinsic qualities, namely scalability restrictions, transactional delays, and escalating storage demands, impede its seamless deployment in high-frequency, voluminous data contexts typical of real-time sensors. This essay launches a methodical investigation into these difficulties, illuminating their underlying causes, potential effects, and potential countermeasures. In addition, we present a novel pragmatic experimental setup and analysis of blockchain for smart system applications, with an extended discussion of the benefits and disadvantages of deploying blockchain based solutions for smart system ecosystems.

We have studied the deep inelastic scattering of polarized charged leptons from polarized nucleon targets and evaluated the polarized structure functions $g_{1,2}(x,Q^2)$ for protons and neutrons as well as the nucleon asymmetries $A_{1p}(x,Q^2)$ and $A_{2p}(x,Q^2)$ for protons. The higher order perturbative corrections up to the next-to-next-to-the-leading order (NNLO) using the parameterization of LSS05 polarized parton distribution functions in the 3-flavor MSbar scheme and the nonperturbative corrections viz. the twist-3 corrections and target mass corrections (TMC) have been included in the calculations. The numerical results for the polarized nucleon structure functions and the proton asymmetries are presented and compared with the experimental results. The sum rule integrals of the nucleon structure functions corresponding to the Ellis-Jaffe, Bjorken, Gottfried and Burkhardt-Cottingham sum rules have been evaluated numerically and are compared with the experimental results., Comment: 22 pages, 13 figures

The proliferation of misinformation and disinformation on social media networks has become increasingly concerning. With a significant portion of the population using social media on a regular basis, there are growing efforts by malicious organizations to manipulate public opinion through coordinated campaigns. Current methods for identifying coordinated user accounts typically rely on either similarities in user behaviour, latent coordination in activity traces, or classification techniques. In our study, we propose a framework based on the hypothesis that coordinated users will demonstrate abnormal growth in their behavioural patterns over time relative to the wider population. Specifically, we utilize the EPClose algorithm to extract contrasting patterns of user behaviour during a time window of malicious activity, which we then compare to a historical time window. We evaluated the effectiveness of our approach using real-world data, and our results show a minimum increase of 10% in the F1 score compared to existing approaches., Comment: Accepted and presented on International Joint Conference on Neural Networks (IJCNN 2024)

The rise of social media has been accompanied by a dark side with the ease of creating fake accounts and disseminating misinformation through coordinated attacks. Existing methods to identify such attacks often rely on thematic similarities or network-based approaches, overlooking the intricate causal relationships that underlie coordinated actions. This work introduces a novel approach for detecting coordinated attacks using Convergent Cross Mapping (CCM), a technique that infers causality from temporal relationships between user activity. We build on the theoretical framework of CCM by incorporating topic modelling as a basis for further optimizing its performance. We apply CCM to real-world data from the infamous IRA attack on US elections, achieving F1 scores up to 75.3% in identifying coordinated accounts. Furthermore, we analyse the output of our model to identify the most influential users in a community. We apply our model to a case study involving COVID-19 anti-vax related discussions on Twitter. Our results demonstrate the effectiveness of our model in uncovering causal structures of coordinated behaviour, offering a promising avenue for mitigating the threat of malicious campaigns on social media platforms., Comment: Accepted for International AAAI Conference on Web and Social Media (ICWSM 2025)

The objective of this study was to develop an automated pipeline that enhances thyroid disease classification using thyroid scintigraphy images, aiming to decrease assessment time and increase diagnostic accuracy. Anterior thyroid scintigraphy images from 2,643 patients were collected and categorized into diffuse goiter (DG), multinodal goiter (MNG), and thyroiditis (TH) based on clinical reports, and then segmented by an expert. A ResUNet model was trained to perform auto-segmentation. Radiomic features were extracted from both physician (scenario 1) and ResUNet segmentations (scenario 2), followed by omitting highly correlated features using Spearman's correlation, and feature selection using Recursive Feature Elimination (RFE) with XGBoost as the core. All models were trained under leave-one-center-out cross-validation (LOCOCV) scheme, where nine instances of algorithms were iteratively trained and validated on data from eight centers and tested on the ninth for both scenarios separately. Segmentation performance was assessed using the Dice similarity coefficient (DSC), while classification performance was assessed using metrics, such as precision, recall, F1-score, accuracy, area under the Receiver Operating Characteristic (ROC AUC), and area under the precision-recall curve (PRC AUC). ResUNet achieved DSC values of 0.84$\pm$0.03, 0.71$\pm$0.06, and 0.86$\pm$0.02 for MNG, TH, and DG, respectively. Classification in scenario 1 achieved an accuracy of 0.76$\pm$0.04 and a ROC AUC of 0.92$\pm$0.02 while in scenario 2, classification yielded an accuracy of 0.74$\pm$0.05 and a ROC AUC of 0.90$\pm$0.02. The automated pipeline demonstrated comparable performance to physician segmentations on several classification metrics across different classes, effectively reducing assessment time while maintaining high diagnostic accuracy. Code available at: https://github.com/ahxmeds/thyroidiomics.git., Comment: 7 pages, 4 figures, 2 tables

AI research in chess has been primarily focused on producing stronger agents that can maximize the probability of winning. However, there is another aspect to chess that has largely gone unexamined: its aesthetic appeal. Specifically, there exists a category of chess moves called ``brilliant" moves. These moves are appreciated and admired by players for their high intellectual aesthetics. We demonstrate the first system for classifying chess moves as brilliant. The system uses a neural network, using the output of a chess engine as well as features that describe the shape of the game tree. The system achieves an accuracy of 79% (with 50% base-rate), a PPV of 83%, and an NPV of 75%. We demonstrate that what humans perceive as ``brilliant" moves is not merely the best possible move. We show that a move is more likely to be predicted as brilliant, all things being equal, if a weaker engine considers it lower-quality (for the same rating by a stronger engine). Our system opens the avenues for computer chess engines to (appear to) display human-like brilliance, and, hence, creativity., Comment: Accepted at the International Conference for Computational Creativity (ICCC) 2024

A client device which has access to $n$ training data samples needs to obtain a statistical hypothesis or model $W$ and then to send it to a remote server. The client and the server devices share some common randomness sequence as well as a prior on the hypothesis space. In this problem a suitable hypothesis or model $W$ should meet two distinct design criteria simultaneously: (i) small (population) risk during the inference phase and (ii) small 'complexity' for it to be conveyed to the server with minimum communication cost. In this paper, we propose a joint training and source coding scheme with provable in-expectation guarantees, where the expectation is over the encoder's output message. Specifically, we show that by imposing a constraint on a suitable Kullback-Leibler divergence between the conditional distribution induced by a compressed learning model $\widehat{W}$ given $W$ and the prior, one guarantees simultaneously small average empirical risk (aka training loss), small average generalization error and small average communication cost. We also consider a one-shot scenario in which the guarantees on the empirical risk and generalization error are obtained for every encoder's output message., Comment: Accepted at ISIT 2024

The fruit identification process involves analyzing and categorizing different types of fruits based on their visual characteristics. This activity can be achieved using a range of methodologies, encompassing manual examination, conventional computer vision methodologies, and more sophisticated methodologies employing machine learning and deep learning. Our study identified a total of 15 distinct categories of fruit, consisting of class Avocado, Banana, Cherry, Apple Braeburn, Apple golden 1, Apricot, Grape, Kiwi, Mango, Orange, Papaya, Peach, Pineapple, Pomegranate and Strawberry. Neural Architecture Search (NAS) is a technological advancement employed within the realm of deep learning and artificial intelligence, to automate conceptualizing and refining neural network topologies. NAS aims to identify neural network structures that are highly suitable for tasks, such as the detection of fruits. Our suggested model with 99.98% mAP increased the detection performance of the preceding research study that used Fruit datasets. In addition, after the completion of the study, a comparative analysis was carried out to assess the findings in conjunction with those of another research that is connected to the topic. When compared to the findings of earlier studies, the detector that was proposed exhibited higher performance in terms of both its accuracy and its precision.

Using Unmanned Aerial Vehicles (UAVs) in Search and rescue operations (SAR) to navigate challenging terrain while maintaining reliable communication with the cellular network is a promising approach. This paper suggests a novel technique employing a reinforcement learning multi Q-learning algorithm to optimize UAV connectivity in such scenarios. We introduce a Strategic Planning Agent for efficient path planning and collision awareness and a Real-time Adaptive Agent to maintain optimal connection with the cellular base station. The agents trained in a simulated environment using multi Q-learning, encouraging them to learn from experience and adjust their decision-making to diverse terrain complexities and communication scenarios. Evaluation results reveal the significance of the approach, highlighting successful navigation in environments with varying obstacle densities and the ability to perform optimal connectivity using different frequency bands. This work paves the way for enhanced UAV autonomy and enhanced communication reliability in search and rescue operations.

We introduce an innovative, simple, effective segmentation-free approach for outcome prediction in head \& neck cancer (HNC) patients. By harnessing deep learning-based feature extraction techniques and multi-angle maximum intensity projections (MA-MIPs) applied to Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) volumes, our proposed method eliminates the need for manual segmentations of regions-of-interest (ROIs) such as primary tumors and involved lymph nodes. Instead, a state-of-the-art object detection model is trained to perform automatic cropping of the head and neck region on the PET volumes. A pre-trained deep convolutional neural network backbone is then utilized to extract deep features from MA-MIPs obtained from 72 multi-angel axial rotations of the cropped PET volumes. These deep features extracted from multiple projection views of the PET volumes are then aggregated and fused, and employed to perform recurrence-free survival analysis on a cohort of 489 HNC patients. The proposed approach outperforms the best performing method on the target dataset for the task of recurrence-free survival analysis. By circumventing the manual delineation of the malignancies on the FDG PET-CT images, our approach eliminates the dependency on subjective interpretations and highly enhances the reproducibility of the proposed survival analysis method., Comment: 15 pages, 4 tables, 4 figures. Submitted for European Journal of Nuclear Medicine and Medical Imaging

In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the transformer model. Our framework can be used to understand and mitigate vanishing/exploding gradients, rank collapse, and instability associated with high attention scores. We also propose DeepScaleLM, an initialization and scaling scheme that conserves unit output/gradient moments throughout the model, enabling the training of very deep models with 1000 layers. We find that transformer models could be much deeper - our deep models with fewer parameters outperform shallow models in Language Modeling, Speech Translation, and Image Classification, across encoder-only, decoder-only and encoder-decoder variants, for both Pre-LN and Post-LN transformers, for multiple datasets and model sizes. These improvements also translate into improved performance on downstream Question Answering tasks and improved robustness for Image Classification., Comment: Accepted at ICML 2024. Source code is available at https://github.com/akhilkedia/TranformersGetStable. Akhil Kedia, Mohd Abbas Zaidi, Sushil Khyalia equal contribution

This paper presents a novel and efficient wireless channel estimation scheme based on a tapped delay line (TDL) model of wireless signal propagation, where a data-driven machine learning approach is used to estimate the path delays and gains. The key motivation for our novel channel estimation model is to gain environment awareness, i.e., detecting changes in path delays and gains related to interesting objects and events in the field. The estimated channel state provides a more detailed measure to sense the field than the single-tap channel state indicator (CSI) in current OFDM systems. Advantages of this approach also include low computation time and training data requirements, making it suitable for environment awareness applications. We evaluate this model's performance using Matlab's ray-tracing tool under static and dynamic conditions for increased realism instead of the standard evaluation approaches that rely on classical statistical channel models. Our results show that our TDL-based model can accurately estimate the path delays and associated gains for a broad-range of locations and operating conditions. Root-mean-square estimation error was less than $10^{-4}$, or $-40$dB, for SNR $\geq 60$dB in all of our experiments. Our results show that interference of a flying drone on signal multipaths, in a preliminary experiment, can be detected in estimated channel states which, otherwise, remains obscured in conventional CSI.

A major challenge in designing efficient statistical supervised learning algorithms is finding representations that perform well not only on available training samples but also on unseen data. While the study of representation learning has spurred much interest, most existing such approaches are heuristic; and very little is known about theoretical generalization guarantees. In this paper, we establish a compressibility framework that allows us to derive upper bounds on the generalization error of a representation learning algorithm in terms of the "Minimum Description Length" (MDL) of the labels or the latent variables (representations). Rather than the mutual information between the encoder's input and the representation, which is often believed to reflect the algorithm's generalization capability in the related literature but in fact, falls short of doing so, our new bounds involve the "multi-letter" relative entropy between the distribution of the representations (or labels) of the training and test sets and a fixed prior. In particular, these new bounds reflect the structure of the encoder and are not vacuous for deterministic algorithms. Our compressibility approach, which is information-theoretic in nature, builds upon that of Blum-Langford for PAC-MDL bounds and introduces two essential ingredients: block-coding and lossy-compression. The latter allows our approach to subsume the so-called geometrical compressibility as a special case. To the best knowledge of the authors, the established generalization bounds are the first of their kind for Information Bottleneck (IB) type encoders and representation learning. Finally, we partly exploit the theoretical results by introducing a new data-dependent prior. Numerical simulations illustrate the advantages of well-chosen such priors over classical priors used in IB., Comment: Accepted and presented at NeurIPS 2023

In this paper, we investigate the geometry of Clairaut anti-invariant Riemannnian maps whose base space are Sasakian manifolds. We obtain the necessary and sufficient conditions for a curve on a base manifold to be geodesic. We obtain conditions for an anti-invariant Riemannian map to be Clairaut. Further, we discuss the biharmonicity of such maps and construct some illustrative examples., Comment: 13 pages

The rapid and precise localization and prediction of a ball are critical for developing agile robots in ball sports, particularly in sports like tennis characterized by high-speed ball movements and powerful spins. The Magnus effect induced by spin adds complexity to trajectory prediction during flight and bounce dynamics upon contact with the ground. In this study, we introduce an innovative approach that combines a multi-camera system with factor graphs for real-time and asynchronous 3D tennis ball localization. Additionally, we estimate hidden states like velocity and spin for trajectory prediction. Furthermore, to enhance spin inference early in the ball's flight, where limited observations are available, we integrate human pose data using a temporal convolutional network (TCN) to compute spin priors within the factor graph. This refinement provides more accurate spin priors at the beginning of the factor graph, leading to improved early-stage hidden state inference for prediction. Our result shows the trained TCN can predict the spin priors with RMSE of 5.27 Hz. Integrating TCN into the factor graph reduces the prediction error of landing positions by over 63.6% compared to a baseline method that utilized an adaptive extended Kalman filter., Comment: Accepted by ICRA 2024

We present the construction of a deep multi-wavelength PSF-matched photometric catalog in the UDS field following the final UKIDSS UDS DR11 release. The catalog includes photometry in 24 filters, from the MegaCam-uS (0.38 microns) band to the Spitzer-IRAC (8 microns) band, over ~ 0.9 sq. deg. and with a 5-sigma depth of 25.3 AB in the K-band detection image. The catalog, containing approximately 188,564 (136,235) galaxies at 0.2 < z < 8.0 with stellar mass > 10$^{8}$ solar masses and K-band total magnitude K < 25.2 (24.3) AB, enables a range of extragalactic studies. We also provide photometric redshifts, corresponding redshift probability distributions, and rest-frame absolute magnitudes and colors derived using the template-fitting code eazy-py. Photometric redshift errors are less than 3 to 4 percent at z < 4 across the full brightness range in K-band and stellar mass range 10$^{8}$-10$^{12}$ solar masses. Stellar population properties (e.g., stellar mass, star-formation rate, dust extinction) are derived from the modeling of the spectral energy distributions (SEDs) using the codes FAST and Dense Basis., Comment: 26 pages, 18 figures, accepted in ApJ. Photometric Catalog, catalogs of stellar population properties derived using Eazy and Dense Basis and other high-level products available for public use at the following webpage - https://www.zaidikumail.com/feniks-uds-catalogs (DOI:10.5281/zenodo.11002298)

Global visual localization in LiDAR-maps, crucial for autonomous driving applications, remains largely unexplored due to the challenging issue of bridging the cross-modal heterogeneity gap. Popular multi-modal learning approach Contrastive Language-Image Pre-Training (CLIP) has popularized contrastive symmetric loss using batch construction technique by applying it to multi-modal domains of text and image. We apply this approach to the domains of 2D image and 3D LiDAR points on the task of cross-modal localization. Our method is explained as follows: A batch of N (image, LiDAR) pairs is constructed so as to predict what is the right match between N X N possible pairings across the batch by jointly training an image encoder and LiDAR encoder to learn a multi-modal embedding space. In this way, the cosine similarity between N positive pairings is maximized, whereas that between the remaining negative pairings is minimized. Finally, over the obtained similarity scores, a symmetric cross-entropy loss is optimized. To the best of our knowledge, this is the first work to apply batched loss approach to a cross-modal setting of image & LiDAR data and also to show Zero-shot transfer in a visual localization setting. We conduct extensive analyses on standard autonomous driving datasets such as KITTI and KITTI-360 datasets. Our method outperforms state-of-the-art recall@1 accuracy on the KITTI-360 dataset by 22.4%, using only perspective images, in contrast to the state-of-the-art approach, which utilizes the more informative fisheye images. Additionally, this superior performance is achieved without resorting to complex architectures. Moreover, we demonstrate the zero-shot capabilities of our model and we beat SOTA by 8% without even training on it. Furthermore, we establish the first benchmark for cross-modal localization on the KITTI dataset., Comment: To be presented at WACV-W 2024. Project page: https://shubodhs.ai/liploc