Minwoo Tae

Debiasing Temporal Sentence Grounding via Semantic-Aware Multimodal Query Reconstruction

Temporal Sentence Grounding in Videos (TSGV) aims to identify the temporal segment in a video that semantically corresponds to a given textual query. Although effective semantic alignment across modalities is crucial for this task, existing TSGV benchmarks exhibit annotation biases such as an over-reliance on specific...