Yang Feng

Ruizhe Chen, Tianxiang Hu, Yang Feng et al.

Concerns regarding Large Language Models (LLMs) to memorize and disclose private information, particularly Personally Identifiable Information (PII), become prominent within the community. Many efforts have been made to mitigate the privacy risks. However, the mechanism through which LLMs memorize PII remains poorly understood. To bridge this gap, we introduce a pioneering method for pinpointing PII-sensitive neurons (privacy neurons) within LLMs. Our method employs learnable binary weight masks to localize specific neurons that account for the memorization of PII in LLMs through adversarial training. Our investigations discover that PII is memorized by a small subset of neurons across all layers, which shows the property of PII specificity. Furthermore, we propose to validate the potential in PII risk mitigation by deactivating the localized privacy neurons. Both quantitative and qualitative experiments demonstrate the effectiveness of our neuron localization algorithm.

Yang Feng, Yu Wang, Jiebo Luo

Deep neural networks have been successfully applied to solving the video-based person re-identification problem with impressive results reported. The existing networks for person re-id are designed to extract discriminative features that preserve the identity information. Usually, whole video frames are fed into the neural networks and all the regions in a frame are equally treated. This may be a suboptimal choice because many regions, e.g., background regions in the video, are not related to the person. Furthermore, the person of interest may be occluded by another person or something else. These unrelated regions may hinder person re-identification. In this paper, we introduce a novel gating mechanism to deep neural networks. Our gating mechanism will learn which regions are helpful for person re-identification and let these regions pass the gate. The unrelated background regions or occluding regions are filtered out by the gate. In each frame, the color channels and optical flow channels provide quite different information. To better leverage such information, we generate one gate using the color channels and another gate using the optical flow channels. These two gates are combined to provide a more reliable gate with a novel fusion method. Experimental results on two major datasets demonstrate the performance improvements due to the proposed gating mechanism.

Yang Feng, Lin Ma, Wei Liu et al.

The need for efficiently finding the video content a user wants is increasing because of the erupting of user-generated videos on the Web. Existing keyword-based or content-based video retrieval methods usually determine what occurs in a video but not when and where. In this paper, we make an answer to the question of when and where by formulating a new task, namely spatio-temporal video re-localization. Specifically, given a query video and a reference video, spatio-temporal video re-localization aims to localize tubelets in the reference video such that the tubelets semantically correspond to the query. To accurately localize the desired tubelets in the reference video, we propose a novel warp LSTM network, which propagates the spatio-temporal information for a long period and thereby captures the corresponding long-term dependencies. Another issue for spatio-temporal video re-localization is the lack of properly labeled video datasets. Therefore, we reorganize the videos in the AVA dataset to form a new dataset for spatio-temporal video re-localization research. Extensive experimental results show that the proposed model achieves superior performances over the designed baselines on the spatio-temporal video re-localization task.

Yang Feng, Lin Ma, Wei Liu et al.

Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first attempt to train an image captioning model in an unsupervised manner. Instead of relying on manually labeled image-sentence pairs, our proposed model merely requires an image set, a sentence corpus, and an existing visual concept detector. The sentence corpus is used to teach the captioning model how to generate plausible sentences. Meanwhile, the knowledge in the visual concept detector is distilled into the captioning model to guide the model to recognize the visual concepts in an image. In order to further encourage the generated captions to be semantically consistent with the image, the image and caption are projected into a common latent space so that they can reconstruct each other. Given that the existing sentence corpora are mainly designed for linguistic research and are thus with little reference to image contents, we crawl a large-scale image description corpus of two million natural sentences to facilitate the unsupervised image captioning scenario. Experimental results show that our proposed model is able to produce quite promising results without any caption annotations.

Yu Wang, Haofu Liao, Yang Feng et al.

We study to what extend Chinese, Japanese and Korean faces can be classified and which facial attributes offer the most important cues. First, we propose a novel way of obtaining large numbers of facial images with nationality labels. Then we train state-of-the-art neural networks with these labeled images. We are able to achieve an accuracy of 75.03% in the classification task, with chances being 33.33% and human accuracy 38.89% . Further, we train multiple facial attribute classifiers to identify the most distinctive features for each group. We find that Chinese, Japanese and Koreans do exhibit substantial differences in certain attributes, such as bangs, smiling, and bushy eyebrows. Along the way, we uncover several gender-related cross-country patterns as well. Our work, which complements existing APIs such as Microsoft Cognitive Services and Face++, could find potential applications in tourism, e-commerce, social media marketing, criminal justice and even counter-terrorism.

Yang Feng, Jiebo Luo

In this paper, we focus on studying the appearing time of different kinds of cars on the road. This information will enable us to infer the life style of the car owners. The results can further be used to guide marketing towards car owners. Conventionally, this kind of study is carried out by sending out questionnaires, which is limited in scale and diversity. To solve this problem, we propose a fully automatic method to carry out this study. Our study is based on publicly available surveillance camera data. To make the results reliable, we only use the high resolution cameras (i.e. resolution greater than $1280 \times 720$). Images from the public cameras are downloaded every minute. After obtaining 50,000 images, we apply faster R-CNN (region-based convoluntional neural network) to detect the cars in the downloaded images and a fine-tuned VGG16 model is used to recognize the car makes. Based on the recognition results, we present a data-driven analysis on the relationship between car makes and their appearing times, with implications on lifestyles.