CoReTab: Improving Multimodal Table Understanding with Code-driven Reasoning
Improving multimodal table understanding with code-driven reasoning.
360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method
A comprehensive benchmark and a training-free method for 360° image perception using MLLMs.
Huyen Tran
TB-Bench: Training and Testing Multi-Modal AI for Understanding Spatio-Temporal Traffic Behaviors from Dashcam Images/Videos
Introduces TB-Bench to train and evaluate multimodal agents for understanding complex traffic behaviors captured by dashcams.
Korawat Charoenpitaks
GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features
Presents GRIT, a dual-feature transformer that improves both speed and accuracy for image captioning.
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks
Enhances interactive instruction following agents with wide-context perception and iterative reasoning.
Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs
Introduces an efficient attention design capturing full interactions in visual dialog systems.
CapsuleNet for Micro-expression Recognition
Applies capsule networks to the challenging task of recognizing subtle micro-expressions.