Text-Video Retrieval (TVR) aims to align relevant video content with natural
language queries. To date, most state-of-the-art TVR methods learn
image-to-video transfer learning based on large-scale pre-trained
visionlanguage models (e.g., CLIP). However, fully fine-tuning these
pre-trained models for TVR incurs prohibitively expensive computation costs. To
this end, we propose to conduct efficient text-video Retrieval with a
sparse-andcorrelated AdaPter (RAP), i.e., fine-tuning the pre-trained model
with a few parameterized layers. To accommodate the text-video scenario, we
equip our RAP with two indispensable characteristics: temporal sparsity and
correlation. Specifically, we propose a low-rank modulation module to refine
the per-image features from the frozen CLIP backbone, which accentuates salient
frames within the video features while alleviating temporal redundancy.
Besides, we introduce an asynchronous self-attention mechanism that first
selects the top responsive visual patches and augments the correlation modeling
between them with learnable temporal and patch offsets. Extensive experiments
on four TVR datasets demonstrate that RAP achieves superior or comparable
performance compared to the fully fine-tuned counterpart and other
parameter-efficient fine-tuning methods.

使用一种称为 RAP 的稀疏且相关的 AdaPter 模型，通过在少数参数化层上进行预训练模型的微调，以提供高效的文本视频检索。RAP 配备了两个必要特征：时间稀疏性和相关性建模。通过引入低秩调制模块和异步自注意力机制，RAP 能够在四个文本视频检索数据集上表现出优越或可比较的性能。

基于稀疏相关适配器的高效文本 - 视频检索

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter

Multi-task learning leverages potential correlations among related tasks to
extract common features and yield performance gains. However, most previous
works only consider simple or weak interactions, thereby failing to model
complex correlations among three or more tasks. In this paper, we propose a
multi-task learning architecture with four types of recurrent neural layers to
fuse information across multiple related tasks. The architecture is
structurally flexible and considers various interactions among tasks, which can
be regarded as a generalized case of many previous works. Extensive experiments
on five benchmark datasets for text classification show that our model can
significantly improve performances of related tasks with additional information
from others.

通过引入四种递归神经层实现多任务结构信息融合，对多个相关任务间的复杂互动进行建模，从而在文本分类任务中显著提升相关任务的性能。