Key Publication Themes and Representative Works:

Multimodal Sentiment, Emotion, and Humor Analysis:

• "A Sentiment and Emotion Aware Multimodal Multiparty Humor Recognition in Multilingual Conversational Setting." (COLING 2022) - Explores deep contextual relationships in conversations for humor recognition.
• "COMMA-DEER: COmmon-sense Aware Multimodal Multitask Approach for Detection of Emotion and Emotional Reasoning in Conversations." (COLING 2022) - Introduces a novel task of detecting emotional reasoning and accompanying emotions in dialogues.
• "EmoInt-Trans: A Multimodal Transformer for Identifying Emotions and Intents in Social Conversations." (IEEE ACM Transactions on Audio, Speech, Language Processing 2023) - Focuses on identifying emotions and intents using multimodal transformers.
• "M2H2: A Multimodal Multiparty Hindi Dataset For Humor Recognition in Conversations." (ACM ICMI 2021) - A significant dataset contribution for humor recognition in Hindi conversations across text, audio, and visual modalities.
• "Well, Now We Know! Unveiling Sarcasm: Initiating and Exploring Multimodal Conversations with Reasoning." (AAAI 2024) - Delves into sarcasm detection and reasoning in multimodal conversations.

Hate Speech and Offensive Content Analysis:

• "Benchmarking Cyber Harassment Dialogue Comprehension through Emotion-Informed Manifestations-Determinants Demarcation." (EMNLP 2024, AAAI 2024) - Addresses the crucial issue of cyber harassment detection and comprehension.
• "MultiSEAO-Mix: A Multimodal Multitask Framework for Sentiment, Emotion, Support, and Offensive Analysis in Code-Mixed Setting." (IEEE Transactions on Computational Social Systems 2025) - A comprehensive approach for offensive content detection in code-mixed languages.

AI for Mental Health and Cognitive Computing:

• "Deciphering Cognitive Distortions in Patient-Doctor Mental Health Conversations: A Multimodal LLM-Based Detection and Reasoning Framework." (EMNLP 2024, IJCAI 2024) - A pioneering work on using multimodal LLMs to detect and reason about cognitive distortions in clinical dialogues.
• "Just a Scratch: Enhancing LLM Capabilities for Self-harm Detection through Intent Differentiation and Emoji Interpretation." (ACL 2025 - to be published) - Focuses on self-harm detection using LLMs, considering emojis and intent.
• "DeCoDE: Detection of Cognitive Distortion and Emotion Cause Extraction in Clinical Conversations." (European Conference on Information Retrieval 2023) - Addresses the detection of cognitive distortions and their emotional causes.

Dataset Contributions:

• "EmoInHindi: A Multi-label Emotion and Intensity Annotated Dataset in Hindi for Emotion Recognition in Dialogues." (LREC 2022) - A large conversational dataset for emotion recognition in Hindi.

M2H2 (mentioned above for Humor Recognition).

Other Notable Works:

• "Aspect-Based Multimodal Mining: Unveiling Sentiments, Complaints, and Beyond in User-Generated Content." (ACM Multimedia 2024)
• "Zero-shot multitask intent and emotion prediction from multimodal data: A benchmark study." (Neurocomputing 2024)