Search Results for author:
Found 43 papers, 8 papers with code
IIITD-20K: Dense captioning for Text-Image ReID
IIITD-20K comprises of 20, 000 unique identities captured in the wild and provides a rich dataset for text-to-image ReID.
A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic Segmentation
To this end, we propose a novel unified weakly supervised OVSS pipeline that can perform ZSS, FSS and Cross-dataset segmentation on novel classes without using pixel-level labels for either the base (seen) or the novel (unseen) classes in an inductive setting.
Knowledge Distillation in Vision Transformers: A Critical Review
A number of model compression methods have been proposed in the literature such as weight quantization, weight multiplexing, pruning and Knowledge Distillation (KD).
KL Regularized Normalization Framework for Low Resource Tasks
A lot of normalization techniques have been proposed but the success of normalization in low resource downstream NLP and speech tasks is limited.
Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs
We show that our framework is more robust compared to traditional adversarial defense mechanisms such as adversarial training.
Matrix Adaptive Synthesis Filter for Uniform Filter Bank
In this paper, we use a matrix adaptive filter as the synthesis stage of a Uniform Filter Bank (UFB) to reconstruct the input signal.
Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs
We further demonstrate that while many existing Deep CNN based methods tend to be extremely vulnerable to adversarial attacks, R-PNODE exhibits increased adversarial robustness for a wide array of these attacks.
MaskMTL: Attribute prediction in masked facial images with deep multitask learning
Predicting attributes in the landmark free facial images is itself a challenging task which gets further complicated when the face gets occluded due to the usage of masks.
Altering Backward Pass Gradients improves Convergence
In standard neural network training, the gradients in the backward pass are determined by the forward pass.
Estimation and Prediction of Deterministic Human Intent Signal to augment Haptic Glove aided Control of Robotic Hand
Hence, a method is proposed to estimate the human intent from the high dimensional HG motion signal and reconstruct the signal at the RH to ensure object relocation.
ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation
We utilise a ResNet18 encoder, learning features for prediction of both depth and pose.
One Shot Audio to Animated Video Generation
We propose a novel method OneShotAu2AV to generate an animated video of arbitrary length using an audio clip and a single unseen image of a person as an input.
Few Shot Adaptive Normalization Driven Multi-Speaker Speech Synthesis
High quality multi-speaker speech synthesis while considering prosody and in a few shot manner is an area of active research with many real-world applications.
Multi Modal Adaptive Normalization for Audio to Video Generation
The multi-modal adaptive normalization uses the various features of audio and video such as Mel spectrogram, pitch, energy from audio signals and predicted keypoint heatmap/optical flow and a single image to learn the respective affine parameters to generate highly expressive video.
Deep Learning for Automated Screening of Tuberculosis from Indian Chest X-rays: Analysis and Update
Methods: The proposed work explores the performance of convolutional neural networks (CNNs) for the diagnosis of TB in Indian chest x-ray images.
Deep LF-Net: Semantic Lung Segmentation from Indian Chest Radiographs Including Severely Unhealthy Images
A chest radiograph, commonly called chest x-ray (CxR), plays a vital role in the diagnosis of various lung diseases, such as lung cancer, tuberculosis, pneumonia, and many more.
Semantics Preserving Hierarchy based Retrieval of Indian heritage monuments
We have curated a large, novel Indian heritage monuments dataset comprising of images of historical, cultural and religious importance with subtypes of eras, dynasties and architectural styles.
Multimedia
PerceptionGAN: Real-world Image Construction from Provided Text through Perceptual Understanding
This initial image is then improved by conditioning on the text.
Deep feature fusion for self-supervised monocular depth prediction
Recent advances in end-to-end unsupervised learning has significantly improved the performance of monocular depth prediction and alleviated the requirement of ground truth depth.
Image fusion using symmetric skip autoencodervia an Adversarial Regulariser
The spectral information in the infrared image is incorporated by adding the feature maps over several layers in the encoder part of the fusion structure, which makes inference on both the visual and infrared images separately.
Compressive sensing based privacy for fall detection
Fall detection holds immense importance in the field of healthcare, where timely detection allows for instant medical assistance.
Automatically Optimized Gradient Boosting Trees for Classifying Large Volume High Cardinality Data Streams Under Concept Drift
Data abundance along with scarcity of machine learning experts and domain specialists necessitates progressive automation of end-to-end machine learning workflows.
Aerial multi-object tracking by detection using deep association networks
Using the RetinaNet model as our base, we modify the anchor scales to better handle the detection of dense distribution and small size of the objects.
Learning Activation Functions: A new paradigm for understanding Neural Networks
Since the optimization of SLNNs is still a challenge, we show that using SLAF along with standard activations (like ReLU) can provide performance improvements with only a small increase in number of parameters.
Few Shot Speaker Recognition using Deep Neural Networks
The recent advances in deep learning are mostly driven by availability of large amount of training data.
VayuAnukulani: Adaptive Memory Networks for Air Pollution Forecasting
Extensive experiments on data sources obtained in Delhi demonstrate that the proposed adaptive attention based Bidirectional LSTM Network outperforms several baselines for classification and regression models.
DSAL-GAN: Denoising based Saliency Prediction with Generative Adversarial Networks
In this paper, we present a novel end-to-end coupled Denoising based Saliency Prediction with Generative Adversarial Network (DSAL-GAN) framework to address the problem of salient object detection in noisy images.
Performance Evalution of 3D Keypoint Detectors and Descriptors for Plants Health Classification
Plant Phenomics based on imaging based techniques can be used to monitor the health and the diseases of plants and crops.
DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds
The method constitutes a deep network for learning permutation invariant representation of 3D points.
Fast Hierarchical Depth Map Computation from Stereo
Disparity by Block Matching stereo is usually used in applications with limited computational power in order to get depth estimates.
Nrityantar: Pose oblivious Indian classical dance sequence classification system
To circumvent this problem, we construct a pose-oblivious shape signature which is fed to a sequence learning framework.
IIT Delhi at SemEval-2018 Task 1 : Emotion Intensity Prediction
This paper discusses the experiments performed for predicting the emotion intensity in tweets using a generalized supervised learning approach.
Object cosegmentation using deep Siamese network
Object cosegmentation addresses the problem of discovering similar objects from multiple images and segmenting them as foreground simultaneously.
Object Classification using Ensemble of Local and Deep Features
In this paper we propose an ensemble of local and deep features for object classification.
Enhanced Characterness for Text Detection in the Wild
We show that a simple combination of characterness cues help in rejecting the non text regions.
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
Drought Stress Classification using 3D Plant Models
Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner.
3D Binary Signatures
3DBS describes keypoints from point clouds with a binary vector resulting in extremely fast matching.
SalProp: Salient object proposals via aggregated edge cues
In this paper, we propose a novel object proposal generation scheme by formulating a graph-based salient edge classification framework that utilizes the edge context.
Large Scale Novel Object Discovery in 3D
We test on unknown objects, which were not seen during training, and perform clustering in the learned embedding space of supervoxels to effectively perform novel object discovery.
Ranking academic institutions on potential paper acceptance in upcoming conferences
The crux of the problem in KDD Cup 2016 involves developing data mining techniques to rank research institutions based on publications.
Benchmarking KAZE and MCM for Multiclass Classification
In this paper, we propose a novel approach for feature generation by appropriately fusing KAZE and SIFT features.
Improving Collaborative Filtering based Recommenders using Topic Modelling
While computing similarity between users, we make use of a combined similarity measure involving rating overlap as well as similarity in the latent topic space.
