English

(Un)likelihood Training for Interpretable Embedding

Computer Vision and Pattern Recognition 2023-11-13 v3 Information Retrieval Multimedia

Abstract

Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box data-driven training process. It is well-known that the effectiveness of representation learning depends heavily on the quality and scale of training data. For video representation learning, having a complete set of labels that annotate the full spectrum of video content for training is highly difficult if not impossible. These issues, black-box training and dataset bias, make representation learning practically challenging to be deployed for video understanding due to unexplainable and unpredictable results. In this paper, we propose two novel training objectives, likelihood and unlikelihood functions, to unroll semantics behind embeddings while addressing the label sparsity problem in training. The likelihood training aims to interpret semantics of embeddings beyond training labels, while the unlikelihood training leverages prior knowledge for regularization to ensure semantically coherent interpretation. With both training objectives, a new encoder-decoder network, which learns interpretable cross-modal representation, is proposed for ad-hoc video search. Extensive experiments on TRECVid and MSR-VTT datasets show the proposed network outperforms several state-of-the-art retrieval models with a statistically significant performance margin.

Keywords

Cite

@article{arxiv.2207.00282,
  title  = {(Un)likelihood Training for Interpretable Embedding},
  author = {Jiaxin Wu and Chong-Wah Ngo and Wing-Kwong Chan and Zhijian Hou},
  journal= {arXiv preprint arXiv:2207.00282},
  year   = {2023}
}

Comments

accepted in ACM Transactions on Information Systems

R2 v1 2026-06-24T12:10:51.063Z