Picture for Avinash Madasu

Avinash Madasu

Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples

Add code
Nov 30, 2023
Viaarxiv icon

Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks

Oct 07, 2023
Figure 1 for Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks
Figure 2 for Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks
Figure 3 for Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks
Figure 4 for Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks
Viaarxiv icon

Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples

Oct 04, 2023
Viaarxiv icon

Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations

Add code
Sep 12, 2023
Figure 1 for Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
Figure 2 for Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
Figure 3 for Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
Figure 4 for Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
Viaarxiv icon

ICSVR: Investigating Compositional and Semantic Understanding in Video Retrieval Models

Jun 28, 2023
Figure 1 for ICSVR: Investigating Compositional and Semantic Understanding in Video Retrieval Models
Figure 2 for ICSVR: Investigating Compositional and Semantic Understanding in Video Retrieval Models
Figure 3 for ICSVR: Investigating Compositional and Semantic Understanding in Video Retrieval Models
Figure 4 for ICSVR: Investigating Compositional and Semantic Understanding in Video Retrieval Models
Viaarxiv icon

A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System

Add code
May 27, 2023
Figure 1 for A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System
Figure 2 for A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System
Figure 3 for A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System
Figure 4 for A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System
Viaarxiv icon

Is multi-modal vision supervision beneficial to language?

Add code
Feb 10, 2023
Figure 1 for Is multi-modal vision supervision beneficial to language?
Figure 2 for Is multi-modal vision supervision beneficial to language?
Figure 3 for Is multi-modal vision supervision beneficial to language?
Figure 4 for Is multi-modal vision supervision beneficial to language?
Viaarxiv icon

Improving video retrieval using multilingual knowledge transfer

Add code
Aug 28, 2022
Figure 1 for Improving video retrieval using multilingual knowledge transfer
Figure 2 for Improving video retrieval using multilingual knowledge transfer
Figure 3 for Improving video retrieval using multilingual knowledge transfer
Figure 4 for Improving video retrieval using multilingual knowledge transfer
Viaarxiv icon

A Syntax Aware BERT for Identifying Well-Formed Queries in a Curriculum Framework

Aug 21, 2022
Figure 1 for A Syntax Aware BERT for Identifying Well-Formed Queries in a Curriculum Framework
Figure 2 for A Syntax Aware BERT for Identifying Well-Formed Queries in a Curriculum Framework
Figure 3 for A Syntax Aware BERT for Identifying Well-Formed Queries in a Curriculum Framework
Figure 4 for A Syntax Aware BERT for Identifying Well-Formed Queries in a Curriculum Framework
Viaarxiv icon

A Unified Framework for Emotion Identification and Generation in Dialogues

May 31, 2022
Figure 1 for A Unified Framework for Emotion Identification and Generation in Dialogues
Figure 2 for A Unified Framework for Emotion Identification and Generation in Dialogues
Figure 3 for A Unified Framework for Emotion Identification and Generation in Dialogues
Viaarxiv icon