Picture for Nasib Ullah

Nasib Ullah

Labels in Extremes: How Well Calibrated are Extreme Multi-label Classifiers?

Add code
Nov 06, 2024
Viaarxiv icon

Navigating Extremes: Dynamic Sparsity in Large Output Space

Add code
Nov 05, 2024
Viaarxiv icon

Zero-Shot Learning Over Large Output Spaces : Utilizing Indirect Knowledge Extraction from Large Language Models

Add code
Jun 13, 2024
Viaarxiv icon

Thinking Hallucination for Video Captioning

Add code
Sep 28, 2022
Figure 1 for Thinking Hallucination for Video Captioning
Figure 2 for Thinking Hallucination for Video Captioning
Figure 3 for Thinking Hallucination for Video Captioning
Figure 4 for Thinking Hallucination for Video Captioning
Viaarxiv icon

A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition

Add code
Apr 04, 2022
Figure 1 for A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
Figure 2 for A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
Figure 3 for A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
Figure 4 for A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
Viaarxiv icon