Search Results for author:
Found 6 papers, 3 papers with code
Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation
Recent advent of vision-based foundation models has enabled efficient and high-quality object detection at ease.
Visual Contexts Clarify Ambiguous Expressions: A Benchmark Dataset
Our work aims to delve deeper into the ability of models to understand indirect communication and seek to contribute to the development of models capable of more refined and human-like interactions.
Solution for SMART-101 Challenge of CVPR Multi-modal Algorithmic Reasoning Task 2024
Second, due to the nature of puzzle images, which often contain various geometric visual patterns, we utilize an object detection algorithm to ensure these patterns are not overlooked in the captioning process.
Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting
Our preliminary results show that majority of questions that LLMs fail to respond correctly can be answered using R-CoF without any sample data outlining the logical process.
Compositional Video Understanding with Spatiotemporal Structure-based Transformers
In this paper we suggest a new novel method to understand complex semantic structures through long video inputs.
Goal Driven Discovery of Distributional Differences via Language Descriptions
Mining large corpora can generate useful discoveries but is time-consuming for humans.
