CVA：面向视频时序定位的上下文感知视频-文本对齐
CVA: Context-aware Video-text Alignment for Video Temporal Grounding
QCD 的「只混入语义无关片段」的替换池构造方式，可直接迁移到任何视频-文本对比学习（如视频检索、片段定位）中，用来避免 query-agnostic 混合带来的假负样本；CBD 损失在时序边界处强制语义一致性，是提升边界敏感任务的通用手段。
原文依据 a contrastive loss that enforces semantic consistency at challenging temporal boundaries
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出上下文感知视频-文本对齐（CVA），一种用于解决视频时序定位中一项重要挑战的新框架：实现既对时序敏感、又对无关背景上下文保持鲁棒的视频-文本对齐。CVA 融合了以数据为中心与架构层面的互补创新，以增强上下文鲁棒性。该框架建立在三个关键组件之上。第一，我们提出查询感知上下文多样化（QCD），一种新的数据增强策略，确保只混入语义上无关的内容。它构建一个基于视频-文本相似度的替换片段池，以在模拟多样化上下文的同时，避免因与查询无关的混合而造成的假负样本。第二，我们引入上下文不变边界判别（CBD）损失，这是一种对比损失，在具有挑战性的时序边界处强制语义一致性，使其表示对上下文偏移与难负样本保持鲁棒。第三，我们引入上下文增强 Transformer 编码器（CTE），这是一种分层架构，结合了窗口化自注意力与带可学习查询的双向交叉注意力，以捕获多尺度的时序上下文。通过上述以数据为中心与架构层面增强的协同作用，CVA 在 QVHighlights 与 Charades-STA 等主要 VTG 基准上取得了最优性能。值得注意的是，我们的方法在 Recall@1（R1）指标上相较最优方法取得了约 5 个点的显著提升，凸显了其在缓解假负样本方面的有效性。
英文原文摘要 1573 字符
We propose Context-aware Video-text Alignment (CVA), a novel framework to address a significant challenge in video temporal grounding: achieving temporally sensitive video-text alignment that remains robust to irrelevant background context. %CVA integrates complementary data-centric and architectural innovations to enhance contextual robustness. Our framework is built on three key components. First, we propose Query-aware Context Diversification (QCD), a new data augmentation strategy that ensures only semantically unrelated content is mixed in. It builds a video-text similarity-based pool of replacement clips to simulate diverse contexts while preventing the false negative caused by query-agnostic mixing. Second, we introduce the Context-invariant Boundary Discrimination (CBD) loss, a contrastive loss that enforces semantic consistency at challenging temporal boundaries, making their representations robust to contextual shifts and hard negatives. Third, we introduce the Context-enhanced Transformer Encoder (CTE), a hierarchical architecture that combines windowed self-attention and bidirectional cross-attention with learnable queries to capture multi-scale temporal context. Through the synergy of these data-centric and architectural enhancements, CVA achieves state-of-the-art performance on major VTG benchmarks, including QVHighlights and Charades-STA. Notably, our method achieves a significant improvement of approximately 5 points in Recall@1 (R1) scores over state-of-the-art methods, highlighting its effectiveness in mitigating false negatives.