Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Mita NasipuriSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works23 from public data
- Recognizing Emotion Cause in Conversations174
This work introduces a new task highly relevant for (explainable) emotion-aware artificial intelligence: recognizing emotion cause in conversations, provides a new highly challenging publicly available dialogue-level dataset for this task, and gives strong baseline results on this dataset.
- KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis71
A new framework is introduced, KinGDOM, which utilizes the ConceptNet knowledge graph to enrich the semantics of a document by providing both domain-specific and domain-general background concepts, and conditioning a popular domain-adversarial baseline method with these learned concepts helps improve its performance over state-of-the-art approaches.
- Improving Zero-Shot Learning Baselines with Commonsense Knowledge32
This work takes advantage of explicit relations between nodes defined in ConceptNet, a commonsense knowledge graph, to generate commonsense embeddings of the class labels by using a graph convolution network-based autoencoder.
- An Axiomatic Fuzzy Set Theory Based Feature Selection Methodology for Handwritten Numeral Recognition27
From the experimental results, it has been found that the methodology provides higher recognition accuracies with lesser or equal numbers of features selected for each dataset.
- JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata25
A retrieval system that leverages both musical features and metadata to identify similar songs, which is then used to fill in missing metadata using a local large language model (LLLM) allows for a more comprehensive and informative dataset for researchers working on music-language understanding tasks.
- 21
- 19
- 10
- Discriminative Dictionary Design for Action Classification in Still Images and Videos7
This work poses the selection of potent local descriptors as filtering-based feature selection problem, which ranks the local features per category based on a novel measure of distinctiveness, and proves the effectiveness of adaptive ranking methodology presented in this work.
- A Comparative Study of Feature Ranking Methods in Recognition of Handwritten Numerals7
This paper compute and compare the strengths of five most widely used feature ranking techniques in identifying the optimal subset of features for best classification results.
- Leveraging LLM Embeddings for Cross Dataset Label Alignment and Zero Shot Music Emotion Prediction6
This work compute LLM embeddings for emotion labels and apply non-parametric clustering to group similar labels, across multiple datasets containing disjoint labels, and introduces an alignment regularization that enables dissociation of MERT embeddings from different clusters.
- A Novel Dictionary Learning based Multiple Instance Learning Approach to Action Recognition from Videos5
This paper proposes a dictionary learning based strategy to MIL which first identifies class-specific discriminative codewords, and then projects the bag-level instances into a probabilistic embedding space with respect to the selected codeword.
- 3
- 3
- Visually-Driven Semantic Augmentation for Zero-Shot Learning.3
This paper proposes to augment the semantic information of attributes/DWEs with semantic representations directly extracted from visual data by means of soft labels and when combined in a novel ZSL paradigm based on latent attributes, this approach achieves favourable performances on three public benchmark datasets.
- SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning2
A multi-task music captioning model that integrates caption generation with auxiliary music feature detection tasks such as key detection, vocals detection, and more, so as to directly capture both low-level acoustic details as well as high-level musical attributes is introduced.
- 2
- 1
- Discriminative body part interaction mining for mid-level action representation and classification1
A novel mid-level feature representation that proves to posses relevant discriminative power when used in a generic action recognition pipeline is proposed and validated on four public datasets, reporting increased classification accuracies with respect to the state of the art.
- –
- –
- –
- Data Driven Approaches for Image & Video Understanding: from Traditional to Zero-shot Supervised Learning–
This work investigates data driven approaches that cater to traditional supervised learning setup as well as an extreme case of data scarcity where no data from test classes are available during training, known as zero-shot learning and proposes robust mid-level feature representations for action videos that are equally effective in traditional supervisedlearning as wellAs zero- shot learning.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.