The use of social media has made it easy to communicate and share information over the internet. However, it also brings issues such as data privacy leakage, which can be exploited by recipients with malicious intentions to harm the sender. In this paper, we propose a deep neural network that analyzes user’s image for privacy sensitive content and automatically locates sensitive regions for obfuscation. Our approach relies solely on image level annotations and learns to (a) predict an overall privacy score, (b) detect sensitive attributes and (c) demarcate the sensitive regions for obfuscation, in a given input image. We validated the performance of our proposed method on three large datasets, VISPR, PASCAL VOC 2012 and MS COCO 2014, in terms of privacy score, attribute prediction and obfuscation performance. On the VISPR dataset, we achieved a Pearson correlation of 0.88 and a Spearman correlation of 0.86, outperforming previous methods. On PASCAL VOC 2012 and MS COCO 2014, our model achieved a mean IOU of 71.5% and 43.9% respectively, and is among the state-of-the-art techniques using weakly supervised semantic segmentation learning.

Grasping and moving objects in a large cluster is a common real scenario. In such scenarios, tens of objects are adjacent to each other, even stacked layer by layer, so that simple grasp would not work due to obstruction. In this paper, we propose a well-designed strategy to use synergy of pushing and grasping to automatically push and grasp objects in a large tightly packed cluster of objects. Our strategy is to detect and grasp isolated graspable objects first before other actions. We then use a smart strategy that pushes objects at the narrowest edge of the clusters. For push action, the robot pushes the edge at the perpendicular direction relative to the cluster, thus improving the performance of isolation and minimizing collisions. We have conducted experiments in both simulation and real-world environments with more than 20 cluttered objects and demonstrated that our solution outperforms existing deep learning based methods, especially in challenging cases, and achieves significantly higher completion rate, grasp success rate, picked rate and efficiency.

Most person re-identification methods rely solely on the pedestrian identity for learning. Person attributes, such as gender, clothing colors, carried bags, etc, are however seldom used. These attributes are highly identity-related and should be capitalized fully. Thus, we propose Attribute Parsing Network (APNet), an architecture designed for both image and person attribute learning and retrievals. To further enhance the re-id performance, we propose to leverage saliency maps and human parsing to boost the foreground features, which when trained together with the global and local networks, resulted in more generic and robust encoded representations. This proposed method achieved state-of-the-art accuracy performance on both Market1501 (87.3% mAP and 95.2% Rank1) and DukeMTMC-reID (78.8% mAP and 89.2% Rank 1) datasets.

This paper proposes Attribute Attention Network (AANet), a new architecture that integrates person attributes and attribute attention maps into a classification framework to solve the person re-identification (re-ID) problem. Many person re-ID models typically employ semantic cues such as body parts or human pose to improve the re-ID performance. Attribute information, however, is often not utilized. The proposed AANet leverages on a baseline model that uses body parts and integrates the key attribute information in an unified learning framework. The AANet consists of a global person ID task, a part detection task and a crucial attribute detection task. By estimating the class responses of individual attributes and combining them to form the attribute attention map (AAM), a very strong discriminatory representation is constructed. The proposed AANet outperforms the best state-of-the-art method \cite{Sun_2018_ECCV} using ResNet-50 by 3.36\% in mAP and 3.12\% in Rank-1 accuracy on DukeMTMC-reID dataset. On Market1501 dataset, AANet achieves 92.38\% mAP and 95.10\% Rank-1 accuracy with re-ranking, outperforming~\cite{kalayeh2018human}, another state of the art method using ResNet-152, by 1.42\% in mAP and 0.47\% in Rank-1 accuracy. In addition, AANet can perform person attribute prediction (e.g., gender, hair length, clothing length etc.), and localize the attributes in the query image.

In this paper, we propose a new multitask neural network called Part Attribute Loss Net (PALNet) for person re-identification (re-id) with homoscedastic uncertainty learning. Currently, many person re-id algorithms use person identity as the main ground truth information to train and to perform prediction task. This single task approach is simple to setup but usually provides poor generalization performance. Some other person re-id works [1] [2] incorporate additional cues such as body parts to improve the learned representations. However, this requires additional body part annotations. Person attributes, which are present in some of the large person re-id datasets like Market1501 [3] and DukeMTMC-reID [4], are not used. Furthermore, the multitask networks found in some of the recent works use heuristic approach in weighing their task losses. Our PALNet seeks to address these issues by leveraging on person identity classification, body part detection and person attribute prediction, all built into a unified network. We also incorporate the homoscedastic uncertainty learning to automatically determine the weighing of the loss function of the different tasks. The PALNet consists of three tasks, with person identity classification as the main task. The body part detection and person attributes are two sub tasks to share different learning experience with the main task. The uncertainty learning provide us good indication of the observable task noises and allows us to optimize the accuracy performance without the time consuming grid search method. When benchmarking on DukeMTMC-reID dataset [4], our approach outperforms other state-of-the-art methods. On Market1501 dataset [3], we are on par with the best state-of-the-art method but outperforms the rest by at least 6.4% mAP and 3.5% Rank-1 accuracy. These results are reported without re-ranking.