Search Results for author:
Found 5 papers, 1 papers with code
Integrating Listwise Ranking into Pairwise-based Image-Text Retrieval
Given a query caption, the goal is to rank candidate images by relevance, from large to small.
Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching
To alleviate the gradient vanishing problem, we propose a Selectively Hard Negative Mining (SelHN) strategy, which chooses whether to mine hard negative samples according to the gradient vanishing condition.
Image-Text Retrieval with Binary and Continuous Label Supervision
Such a binary indicator covers only a limited subset of image-text semantic relations, which is insufficient to represent relevance degrees between images and texts described by continuous labels such as image captions.
Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
More specifically, Triplet loss with Hard Negative mining (Triplet-HN), which is widely used in existing retrieval models to improve the discriminative ability, is easy to fall into local minima in training.
Exploiting Visual Semantic Reasoning for Video-Text Retrieval
Finally, the region features are aggregated to form frame-level features for further encoding to measure video-text similarity.
