Search Results for author:
Found 22 papers, 7 papers with code
Quantifying Interpretability in CLIP Models with Concept Consistency
We propose Concept Consistency Score (CCS), a novel interpretability metric that measures how consistently individual attention heads in CLIP models align with specific concepts.
Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review
To address this deficiency, we propose a new detection approach which surpasses existing methods in the identification of GPT-4o written peer reviews at low levels of false positive classifications.
Quantifying and Enabling the Interpretability of CLIP-like Models
However, little is known about the inner workings of CLIP.
SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples
Our approach utilizes Stable Diffusion with cross attention control to produce sets of counterfactual image-text pairs that are highly similar in their depiction of a subject (e. g., a given occupation) while differing only in their depiction of intersectional social attributes (e. g., race & gender).
Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks
We investigate 9 foundational image-text models on a diverse set of video tasks that include video action recognition (video AR), video retrieval (video RT), video question answering (video QA), video multiple choice (video MC) and video captioning (video CP).
Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples
While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect to social attributes such as gender and race.
Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
We introduce Affective Visual Dialog, an emotion explanation and reasoning task as a testbed for research on understanding the formation of emotions in visually grounded conversations.
ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models
The study is performed on two categories of video retrieval models: (i) which are pre-trained on video-text pairs and fine-tuned on downstream video retrieval datasets (Eg.
A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System
Lastly, a decoder generates the corresponding response for the given dialogue context and the extracted slot values.
Is Multimodal Vision Supervision Beneficial to Language?
We compare the performance of language representations of stand-alone text encoders of these models to the language representations of text encoders learnt through vision supervision.
What do Large Language Models Learn beyond Language?
Large language models (LMs) have rapidly become a mainstay in Natural Language Processing.
MuMUR : Multilingual Multimodal Universal Retrieval
In this paper, we propose a framework MuMUR, that utilizes knowledge transfer from a multilingual model to boost the performance of multi-modal (image and video) retrieval.
A Syntax Aware BERT for Identifying Well-Formed Queries in a Curriculum Framework
A well formed query is defined as a query which is formulated in the manner of an inquiry, and with correct interrogatives, spelling and grammar.
A Unified Framework for Emotion Identification and Generation in Dialogues
Social chatbots have gained immense popularity, and their appeal lies not just in their capacity to respond to the diverse requests from users, but also in the ability to develop an emotional connection with users.
Learning to Retrieve Videos by Asking Questions
To overcome this limitation, we propose a novel framework for Video Retrieval using Dialog (ViReD), which enables the user to interact with an AI agent via multiple rounds of dialog, where the user refines retrieved results by answering questions generated by an AI agent.
Sequential Domain Adaptation through Elastic Weight Consolidation for Sentiment Analysis
SDA draws on EWC for training on successive source domains to move towards a general domain solution, thereby solving the problem of domain adaptation.
A Position Aware Decay Weighted Network for Aspect based Sentiment Analysis
Aspect Term Sentiment Analysis (ATSA) is a subtask of ABSA, in which aspect terms are contained within the given sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Efficient Feature Selection techniques for Sentiment Analysis
Feature selection is a crucial process in machine learning.
Sequential Learning of Convolutional Features for Effective Text Classification
With the advent of deep learning, convolutional neural network (CNN) has been a popular solution to this task.
A Study of Feature Extraction techniques for Sentiment Analysis
Sentiment Analysis refers to the study of systematically extracting the meaning of subjective text .
Gated Convolutional Neural Networks for Domain Adaptation
In this paper, we show that Gated Convolutional Neural Networks (GCN) perform effectively at learning sentiment analysis in a manner where domain dependant knowledge is filtered out using its gates.
Effectiveness of Self Normalizing Neural Networks for Text Classification
In this paper we aim to show the effectiveness of proposed, Self Normalizing Convolutional Neural Networks(SCNN) on text classification.
