Learning Video Retrieval Models With Relevance-aware Online Mining

Abstract

Due to the amount of videos and related captions uploaded every hour, deep learning-based solutions for cross-modal video retrieval are attracting more and more attention. A typical approach consists in learning a joint text-video embedding space, where the similarity of a video and its associated caption is maximized, whereas a lower similarity is enforced with all the other captions, called negatives. This approach assumes that only the video and caption pairs in the dataset are valid, but different captions - positives - may also describe its visual contents, hence some of them may be wrongly penalized. To address this shortcoming, we propose the Relevance-Aware Negatives and Positives mining (RANP) which, based on the semantics of the negatives, improves their selection while also increasing the similarity of other valid positives. We explore the influence of these techniques on two video-text datasets: EPIC-Kitchens-100 and MSR-VTT. By using the proposed techniques, we achieve con

Stats

• citations3
• S2 citations—
• github stars5
• HF likes0
• heat score6.07
• arxiv keyfalcon2022learning

Related papers

• On Semantic Similarity In Video Retrieval (2021)12.81
• Feature Re-learning With Data Augmentation For Video Relevance Prediction (2020)6.34
• Nv-retriever: Improving Text Embedding Models With Effective Hard-negative Mining (2024)0.00
• Relevance-based Margin For Contrastively-trained Video Retrieval Models (2022)7.74
• Fighting Fire With FIRE: Assessing The Validity Of Text-to-video Retrieval Benchmarks (2022)0.00
• Learning Audio-video Modalities From Image Captions (2022)12.54
• Improving Video Retrieval By Adaptive Margin (2023)9.92
• Dual-modal Attention-enhanced Text-video Retrieval With Triplet Partial Margin Contrastive Learning (2023)8.82