Watch time is widely used as a proxy for user satisfaction in video recommendation platforms. However, raw watch times are influenced by confounding factors such as video duration, popularity, and individual user behaviors, potentially distorting preference signals and resulting in biased recommendation models. We propose a novel relative advantage debiasing framework that corrects watch time by comparing it to empirically derived reference distributions conditioned on user and item groups. This approach yields a quantile-based preference signal and introduces a two-stage architecture that explicitly separates distribution estimation from preference learning. Additionally, we present distributional embeddings to efficiently parameterize watch-time quantiles without requiring online sampling or storage of historical data. Both offline and online experiments demonstrate significant improvements in recommendation accuracy and robustness compared to existing baseline methods.

Cross-media retrieval, which uses a text query to search for images and vice-versa, has attracted a wide attention in recent years. The mostly existing cross-media retrieval methods aim at finding a common subspace and maximizing different modalities correlations. But these approaches do not directly capture the underlying semantic information of different modalities. This paper proposes a novel cross-media retrieval by semantics clustering and enhancement, where a semantic-preserved mapping is learned from the original space to the target semantic space. Meanwhile, In order to improve the demarcation of semantic space, we enhance the semantic manifold by learning a dimension invariant matrix. Our approach not only maximizes the correlation between different modalities, but also increases the discriminative ability among different categories. Experiments show that our approach outperforms the popular methods on two real word datasets.