Search Results for author:
Found 37 papers, 9 papers with code
SOA_NLP@LT-EDI-ACL2022: An Ensemble Model for Hope Speech Detection from YouTube Comments
The language of internet users has a big impact on peer users all over the world.
IIITSurat@LT-EDI-ACL2022: Hope Speech Detection using Machine Learning
This paper addresses the issue of Hope Speech detection using machine learning techniques.
Offensive language identification in Dravidian code mixed social media text
The data set used for this study are in Tanglish (Tamil and English), Manglish (Malayalam and English) code-mixed, and Malayalam script-mixed.
SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects.
3D Object Detection
3D Object Detection From Monocular Images
+3
UPNeRF: A Unified Framework for Monocular 3D Object Reconstruction and Pose Estimation
Monocular 3D reconstruction for categorical objects heavily relies on accurately perceiving each object's pose.
A Survey of Application of Machine Learning in Wireless Indoor Positioning Systems
Numerous attempts have been made in the literature to develop efficient indoor positioning systems (IPSs), with a growing focus on machine learning (ML) based techniques.
Echocardiogram Foundation Model -- Application 1: Estimating Ejection Fraction
Cardiovascular diseases stand as the primary global cause of mortality.
Causal Inference Using LLM-Guided Discovery
At the core of causal inference lies the challenge of determining reliable causal graphs solely based on observational data.
One-shot Imitation Learning via Interaction Warping
We propose a new method, Interaction Warping, for learning SE(3) robotic manipulation policies from a single demonstration.
Tame a Wild Camera: In-the-Wild Monocular Camera Calibration
3D sensing for monocular in-the-wild images, e. g., depth estimation and 3D object detection, has become increasingly important.
Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes
We prove that our method only requires that the ranking of estimated causal effects is correct across attributes to select the correct classifier.
A Generative Framework for Low-Cost Result Validation of Outsourced Machine Learning Tasks
Fides features a client-side attack detection model that uses statistical analysis and divergence measurements to identify, with a high likelihood, if the service model is under attack.
Disentangling Mixtures of Unknown Causal Interventions
In many real-world scenarios, such as gene knockout experiments, targeted interventions are often accompanied by unknown interventions at off-target sites.
Reference Resolution and Context Change in Multimodal Situated Dialogue for Exploring Data Visualizations
Our focus is on resolving references to visualizations on a large screen display in multimodal dialogue; crucially, reference resolution is directly involved in the process of creating new visualizations.
Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
In 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e. g. urban driving scenes.
3D Object Detection
3D Object Detection From Monocular Images
+2
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
As a result, DEVIANT is equivariant to the depth translations in the projective manifold whereas vanilla networks are not.
3D Object Detection From Monocular Images
Monocular 3D Object Detection
Probing Classifiers are Unreliable for Concept Removal and Detection
Even under the most favorable conditions for learning a probing classifier when a concept's relevant features in representation space alone can provide 100% accuracy, we prove that a probing classifier is likely to use non-concept features and thus post-hoc or adversarial methods will fail to remove the concept correctly.
Adaptive Multi-User Clustering and Power Allocation for NOMA Systems with Imperfect SIC
We consider a practical downlink NOMA system with imperfect successive interference cancellation and derive bounds on the power allocation factors for a given number of users in each cluster.
Bounds on Power and Common Message Fractions for RSMA with Imperfect SIC
However, it has been shown in the existing works that maximizing the sum rate can result in asymmetric user performance.
$α$-Fairness User Pairing for Downlink NOMA Systems with Imperfect Successive Interference Cancellation
Further, we show that the proposed optimal and sub-optimal algorithms achieve significant improvements in terms of fairness as compared to the state-of-the-art algorithms.
Impact of NOMA and CoMP Implementation Order on the Performance of Ultra-Dense Networks
Non-orthogonal multiple access (NOMA) is a promising multiple access technology to improve the throughput and spectral efficiency of the users for 5G and beyond cellular networks.
How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI
FPs are commonly used in quizzes and interviews to bring out and evaluate the creative reasoning abilities of humans.
The application of artificial intelligence in software engineering: a review challenging conventional wisdom
This survey chapter is a review of the most commonplace methods of AI applied to SE.
Misinformation Detection on YouTube Using Video Captions
Using caption dataset, the proposed models can classify videos among three classes (Misinformation, Debunking Misinformation, and Neutral) with 0. 85 to 0. 90 F1-score.
GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
In this paper, we present and integrate GrooMeD-NMS -- a novel Grouped Mathematically Differentiable NMS for monocular 3D object detection, such that the network is trained end-to-end with a loss on the boxes after NMS.
Ranked #10 on
3D Object Detection From Monocular Images
on KITTI-360
3D Object Detection From Monocular Images
Monocular 3D Object Detection
+2
Scaling Up Exact Neural Network Compression by ReLU Stability
We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable.
Adaptive User Pairing for Downlink NOMA System with Imperfect SIC
Non-orthogonal multiple access (NOMA) has been recognized as a key driving technology for the fifth generation (5G) and beyond 5G cellular networks.
NOMA for Multiple Access Channel and Broadcast Channel in Indoor VLC
We evaluate the performance of the proposed scheme for MAC using successive interference cancellation (SIC) based decoding, joint maximum likelihood (JML) decoding, and a combination of SIC and JML decoding.
Augmenting Small Data to Classify Contextualized Dialogue Acts for Exploratory Visualization
Our goal is to develop an intelligent assistant to support users explore data via visualizations.
LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
In this paper, we present a novel framework for jointly predicting landmark locations, associated uncertainties of these predicted locations, and landmark visibilities.
Ranked #1 on
Face Alignment
on Menpo
Lossless Compression of Deep Neural Networks
Deep neural networks have been successful in many predictive modeling tasks, such as image and language recognition, where large neural networks are often used to obtain good accuracy.
Equivalent and Approximate Transformations of Deep Neural Networks
On the practical side, we show that certain rectified linear units (ReLUs) can be safely removed from a network if they are always active or inactive for any valid input.
Location reference identification from tweets during emergencies: A deep learning approach
Twitter is recently being used during crises to communicate with officials and provide rescue and relief operation in real time.
Parametric Synthesis of Text on Stylized Backgrounds using PGGANs
We describe a novel method of generating high-resolution real-world images of text where the style and textual content of the images are described parametrically.
Neural Signatures for Licence Plate Re-identification
The template database is restricted to contain only a single signature per unique licence plate for our problem.
Estimation of Bandlimited Grayscale Images From the Single Bit Observations of Pixels Affected by Additive Gaussian Noise
The images are oversampled over their Nyquist rate in the FCT domain.
