Detecting small signs in complex real-world environments remains challenging due to limited feature information and interference from other objects. In this article, we propose a novel text feature-guided network (TFG-Net) to improve the performance of the small signs detection not only enhancing the feature information of small signs but also avoiding the influence of other objects. As the name suggests, TFG-Net incorporates a text detection branch, which extracts additional textual features from the signs and supplies them to the object detection branch. Furthermore, the object detection branch of TFG-Net optimizes the backbone network's output structure by merging deep features and introducing a high-resolution feature layer. Finally, a fusion method that enhances both overall and local features is proposed to fully integrate detailed and semantic information. Experimental results display that our TFG-Net reaches the highest mean average precision (mAP) of 92.5% on the public datasets Tsinghua-Tencent 100K (TT100K), 83.7% on CCTSDB2021, and 79.1% on DFG, surpassing current state-of-the-art object detectors.

As the self-attention mechanism offers powerful capabilities for capturing sequential relationships, it has become increasingly popular to use it for modeling user behavior sequences in recommender systems. However, the self-attention mechanism has a quadratic computational complexity of O(n^2), as it conducts interactions among all item pairs in the sequence. This can lead to expensive model training and slow inference speeds, which may hinder practical deployment. To this end, we pursue to develop alternative approaches to improve the efficiency of the self-attention mechanism. We observe that the attention scores calculated from each item interacting with other items (including itself) are sparse, indicating that there are limited valuable item pairs (with non-zero attention weight) that contribute to the final output. This motivates us to develop effective strategies for discerning valuable items and computing attention scores solely for these items, thereby minimizing the consumption of unnecessary computations. Herein, we present a novel Progressive Sampling-based Self-Attention (PS-SA) mechanism, which utilizes a learnable progressive sampling strategy to identify the most valuable items. Subsequently, we solely utilize these selected items to produce the final output. Experiments on academic and production datasets demonstrate PS-SA could still achieve promising results while reducing computational costs. It is notable that we have successfully deployed it on Alibaba display advertising system, resulting in a 2.6% CTR and 1.3% RPM increase.

Conversion rate (CVR) prediction is one of the core components in online recommender systems, and various approaches have been proposed to obtain accurate and well-calibrated CVR estimation. However, we observe that a well-trained CVR prediction model often performs sub-optimally during sales promotions. This can be largely ascribed to the problem of the data distribution shift, in which the conventional methods no longer work. To this end, we seek to develop alternative modeling techniques for CVR prediction. Observing similar purchase patterns across different promotions, we propose reusing the historical promotion data to capture the promotional conversion patterns. Herein, we propose a novel Historical Data Reuse (HDR) approach that first retrieves historically similar promotion data and then fine-tunes the CVR prediction model with the acquired data for better adaptation to the promotion mode. HDR consists of three components: an automated data retrieval module that seeks similar data from historical promotions, a distribution shift correction module that re-weights the retrieved data for better aligning with the target promotion, and a TransBlock module that quickly fine-tunes the original model for better adaptation to the promotion mode. Experiments conducted with real-world data demonstrate the effectiveness of HDR, as it improves both ranking and calibration metrics to a large extent. HDR has also been deployed on the display advertising system in Alibaba, bringing a lift of 9% RPM and 16% CVR during Double 11 Sales in 2022.

Using a convolutional neural network to build visual encoding and decoding models of the human brain is a good starting point for the study on relationship between deep learning and human visual cognitive mechanism. However, related studies have not fully considered their differences. In this paper, we assume that only a portion of neural network features is directly related to human brain signals, which we call shared features. In the encoding process, we extract shared features from the lower and higher layers of the neural network, and then build a non-negative sparse map to predict brain activities. In the decoding process, we use back-propagation to reconstruct visual stimuli, and use dictionary learning and a deep image prior to improve the robustness and accuracy of the algorithm. Experiments on a public fMRI dataset confirm the rationality of the encoding models, and comparing with a recently proposed method, our reconstruction results obtain significantly higher accuracy.