Improving Video Retrieval By Adaptive Margin
2023 · Feng He, Qi Wang, Zhifan Feng, et al.
Abstract
Video retrieval is becoming increasingly important owing to the rapid emergence of videos on the Internet. The dominant paradigm for video retrieval learns video-text representations by pushing the distance between the similarity of positive pairs and that of negative pairs apart from a fixed margin. However, negative pairs used for training are sampled randomly, which indicates that the semantics between negative pairs may be related or even equivalent, while most methods still enforce dissimilar representations to decrease their similarity. This phenomenon leads to inaccurate supervision and poor performance in learning video-text representations. While most video retrieval methods overlook that phenomenon, we propose an adaptive margin changed with the distance between positive and negative pairs to solve the aforementioned issue. First, we design the calculation framework of the adaptive margin, including the method of distance measurement and the function between the distance an
Authors
(none)
Tags
Stats
Related papers
- Relevance-based Margin For Contrastively-trained Video Retrieval Models (2022)7.74
- Dual-modal Attention-enhanced Text-video Retrieval With Triplet Partial Margin Contrastive Learning (2023)8.82
- Modality-balanced Embedding For Video Retrieval (2022)7.16
- Not All Pairs Are Equal: Hierarchical Learning For Average-precision-oriented Video Retrieval (2024)7.50
- Learning Video Retrieval Models With Relevance-aware Online Mining (2022)6.07
- Rebalancing Contrastive Alignment With Bottlenecked Semantic Increments In Text-video Retrieval (2025)1.69
- Bridging Information Asymmetry In Text-video Retrieval: A Data-centric Approach (2024)0.00
- Semantic Video Moments Retrieval At Scale: A New Task And A Baseline (2022)0.00