Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
Dec 12, 2024
A Multi-Stage Vision-Language Framework for Knowledge-based Visual Question Answering
Devised a two-stage VLM-based pipeline by utilizing knowledge of LMs to first sample multiple candidate answers and then using CLIP to select the most likely choice.
Dec 5, 2023
Multimodal Personality Recognition using Cross-attention Transformer and Behaviour Encoding
Jul 1, 2022
FLAME: Facial Landmark Heatmap Activated Multimodal Gaze Estimation
Nov 16, 2021
Drowsiness Detection in Drivers
Designed a CNN-based neural network to detect drowsiness in drivers frame-by-frame using RGB videos.
Jul 5, 2020