activity
20222024
most citedUnified Loss of Pair Similarity Optimization for Vision-Language Retrieval

2 citations · 6 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2024

Disentangle and denoise: Tackling context misalignment for video moment retrieval

Kaijing Ma, Han Fang, Xianghao Zang +7

Video Moment Retrieval, which aims to locate in-context video moments according to a natural language query, is an essential task for cross-modal grounding. Existing methods focus…

cs.CV2024

ProTA: Probabilistic Token Aggregation for Text-Video Retrieval

Han Fang, Xianghao Zang, Chao Ban +5

Text-video retrieval aims to find the most relevant cross-modal samples for a given query. Recent methods focus on modeling the whole spatial-temporal relations. However, since vid…

cs.CV20232 cited

Integrating Listwise Ranking into Pairwise-based Image-Text Retrieval

Zheng Li, Caili Guo, Xin Wang +2

Image-Text Retrieval (ITR) is essentially a ranking problem. Given a query caption, the goal is to rank candidate images by relevance, from large to small. The current ITR datasets…

cs.CV20232 cited

Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching

Zheng Li, Caili Guo, Xin Wang +2

Recently, a series of Image-Text Matching (ITM) methods achieve impressive performance. However, we observe that most existing ITM models suffer from gradients vanishing at the beg…

cs.CV20222 cited

Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval

Zheng Li, Caili Guo, Xin Wang +3

There are two popular loss functions used for vision-language retrieval, i.e., triplet loss and contrastive learning loss, both of them essentially minimize the difference between…