Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Although previous respectable works have made decent success, they only focus on high-level visual features extracted from the consecutive decoded frames and fail to handle the compressed videos for query modelling, suffering from insufficient representation capability and significant computational complexity during training and testing. In this paper, we pose a new setting, compressed-domain TSG, which directly utilizes compressed videos rather than fully-decompressed frames as the visual input. To handle the raw video bit-stream input, we propose a novel Three-branch Compressed-domain Spatial-temporal Fusion (TCSF) framework, which extracts and aggregates three kinds of low-level visual features (I-frame, motion vector and residual features) for effective and efficient grounding. Particularly, instead of encoding the whole decoded frames like previous works, we capture the appearance representation by only learning the I-frame feature to reduce delay or latency. Besides, we explore the motion information not only by learning the motion vector feature, but also by exploring the relations of neighboring frames via the residual feature. In this way, a three-branch spatial-temporal attention layer with an adaptive motion-appearance fusion module is further designed to extract and aggregate both appearance and motion information for the final grounding. Experiments on three challenging datasets shows that our TCSF achieves better performance than other state-of-the-art methods with lower complexity.

翻译：给定一个未经裁剪的视频，时序句子定位（TSG）旨在根据一个句子查询，在语义上定位目标时刻。尽管之前可敬的工作已取得了不错的成功，但它们仅关注从连续解码帧中提取的高层视觉特征，而未能处理用于查询建模的压缩视频，导致在训练和测试过程中表示能力不足且计算复杂度显著。本文提出了一种新设定——压缩域时序句子定位，该设定直接利用压缩视频而非完全解压的帧作为视觉输入。为处理原始视频比特流输入，我们提出了一种新颖的三分支压缩域时空融合（TCSF）框架，该框架提取并聚合三种类型的低层视觉特征（I帧、运动向量和残差特征），以实现高效且有效的定位。特别地，与之前工作对整个解码帧进行编码不同，我们仅通过学习I帧特征来捕获外观表示，以减少延迟或等待时间。此外，我们不仅通过学习运动向量特征来探索运动信息，还通过残差特征探索相邻帧之间的关系。通过这种方式，进一步设计了一个带有自适应运动-外观融合模块的三分支时空注意力层，以提取并聚合外观和运动信息用于最终的定位。在三个具有挑战性的数据集上的实验表明，我们的TCSF以更低的复杂度实现了优于其他最先进方法的性能。