Browsing Computer Sciences by Author "Lee, Yong Jae"
Now showing items 1-2 of 2
-
Resolution Matters: An Effective Approach to Anomaly Detection
Zou, Bocheng (2025)Unsupervised anomaly detection has been profoundly impacted by the advent of large-scale Vision Foundation Models (VFMs). The prevailing paradigm leverages features from a pre-trained encoder, where anomalies manifest as ... -
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
Nguyen, Le Thien Phuc (2025)"Multimodal large language models (MLLMs) are expected to jointly interpret vision, audio, and language, yet existing video benchmarks rarely assess fine-grained reasoning about human speech. Many tasks remain visually ...