Search Results for author:
Found 11 papers, 0 papers with code
PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination
In this study, we explicitly address this problem by employing class-aware prototype alignment weighted by mean class probabilities obtained for the test sample and filtered augmented views.
RePoseDM: Recurrent Pose Alignment and Gradient Guidance for Pose Guided Image Synthesis
Inspired by the ability of the diffusion model to generate photorealistic images from the given conditional guidance, we propose recurrent pose alignment to provide pose-aligned texture features as conditional guidance.
FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing
To address the long-tail issue of visual relationships, we propose correlation debiasing and a label correlation-based loss to learn unbiased relation representations for long-tailed classes.
SegDA: Maximum Separable Segment Mask with Pseudo Labels for Domain Adaptive Semantic Segmentation
To address this problem we propose SegDA module to enhance transfer performance of UDA methods by learning the maximum separable segment representation.
InFusion: Inject and Attention Fusion for Multi Concept Zero-Shot Text-based Video Editing
When these are combined with injected attention features, it becomes feasible to query the source contents and scale edited concepts along with the injection of unedited parts.
Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributes
In a popular e-commerce store, we have deployed our models for 1000s of (product-type, attribute) pairs.
DomainInv: Domain Invariant Fine Tuning and Adversarial Label Correction For QA Domain Adaptation
Existing Question Answering (QA) systems limited by the capability of answering questions from unseen domain or any out-of-domain distributions making them less reliable for deployment to real scenarios.
MASIL: Towards Maximum Separable Class Representation for Few Shot Class Incremental Learning
We propose the idea of concept factorization explaining the collapsed features for base session classes in terms of concept basis and use these to induce classifier simplex for few shot classes.
WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue
An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue.
Fine-Tune Longformer for Jointly Predicting Rumor Stance and Veracity
Due to widely available social media platforms and increased usage caused the data to be available in huge amounts. The manual methods to process such large data is costly and time-taking, so there has been an increased attention to process and verify such content automatically for the presence of rumors.
Ranked #1 on
Stance Classification
on SemEval 2019
A Unified System for Aggression Identification in English Code-Mixed and Uni-Lingual Texts
To solve these problems, we have introduced a unified and robust multi-modal deep learning architecture which works for English code-mixed dataset and uni-lingual English dataset both. The devised system, uses psycho-linguistic features and very ba-sic linguistic features.
Ranked #1 on
Text Classification
on Facebook Media
