3 papers
cs.CV2025
Two Causally Related Needles in a Video Haystack
Miaoyu Li, Qin Chao, Boyang Li
Properly evaluating the ability of Video-Language Models (VLMs) to understand long videos remains a challenge. We propose a long-context video understanding benchmark, Causal2Needl…
cs.CL2024
Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA
Miaoyu Li, Haoxin Li, Zilin Du +1
Knowledge-based Visual Question-answering (K-VQA) often requires the use of background knowledge beyond the image. However, we discover that a single knowledge generation strategy…
cs.CV2024
The First Competition on Resource-Limited Infrared Small Target Detection Challenge: Methods and Results
Boyang Li, Xinyi Ying, Ruojing Li +3
In this paper, we briefly summarize the first competition on resource-limited infrared small target detection (namely, LimitIRSTD). This competition has two tracks, including weakl…