Tzu-Heng Lin

Tzu-Heng Lin

Landmark detection for clothes is a fundamental problem for many applications. In this paper, a new training scheme for clothes landmark detection: $\textit{Aggregation and Finetuning}$, is proposed. We investigate the homogeneity among landmarks of different categories of clothes, and utilize it to design the procedure of training. Extensive experiments show that our method outperforms current state-of-the-art methods by a large margin. Our method also won the 1st place in the DeepFashion2 Challenge 2020 - Clothes Landmark Estimation Track with an AP of 0.590 on the test set, and 0.615 on the validation set. Code will be publicly available at https://github.com/lzhbrian/deepfashion2-kps-agg-finetune .

Tzu-Heng Lin, Chen Gao

In this paper, we detailedly describe our solution for the IEEE BigData Cup 2021: RL-based RecSys (Track 1: Item Combination Prediction). We first conduct an exploratory data analysis on the dataset and then utilize the findings to design our framework. Specifically, we use a two-headed transformer-based network to predict user feedback and unlocked sessions, along with the proposed session-aware reweighted loss, multi-tasking with click behavior prediction, and randomness-in-session augmentation. In the final private leaderboard on Kaggle, our method ranked 2nd with a categorization accuracy of 0.39224.

Tzu-Heng Lin, Chen Gao, Yong Li

Social recommendation, which utilizes social relations to enhance recommender systems, has been gaining increasing attention recently with the rapid development of online social network. Existing social recommendation methods are based on the fact that users preference or decision is influenced by their social friends' behaviors. However, they assume that the influences of social relation are always the same, which violates the fact that users are likely to share preference on diverse products with different friends. In this paper, we present a novel CSR (short for Characterized Social Regularization) model by designing a universal regularization term for modeling variable social influence. Our proposed model can be applied to both explicit and implicit iteration. Extensive experiments on a real-world dataset demonstrate that CSR significantly outperforms state-of-the-art social recommendation methods.