More Like this

1. Topical network embedding

   https://doi.org/10.1007/s10618-019-00659-7  

   Shi, Min ; Tang, Yufei ; Zhu, Xingquan ; Liu, Jianxun ; He, Haibo ( October 2019 , Data Mining and Knowledge Discovery)

   Networked data involve complex information from multifaceted channels, including topology structures, node content, and/or node labels etc., where structure and content are often correlated but are not always consistent. A typical scenario is the citation relationships in scholarly publications where a paper is cited by others not because they have the same content, but because they share one or multiple subject matters. To date, while many network embedding methods exist to take the node content into consideration, they all consider node content as simple flat word/attribute set and nodes sharing connections are assumed to have dependency with respect to all words or attributes. In this paper, we argue that considering topic-level semantic interactions between nodes is crucial to learn discriminative node embedding vectors. In order to model pairwise topic relevance between linked text nodes, we propose topical network embedding, where interactions between nodes are built on the shared latent topics. Accordingly, we propose a unified optimization framework to simultaneously learn topic and node representations from the network text contents and structures, respectively. Meanwhile, the structure modeling takes the learned topic representations as conditional context under the principle that two nodes can infer each other contingent on the shared latent topics.more »Experiments on three real-world datasets demonstrate that our approach can learn significantly better network representations, i.e., 4.1% improvement over the state-of-the-art methods in terms of Micro-F1 on Cora dataset. (The source code of the proposed method is available through the github link: https:// github.com/codeshareabc/TopicalNE.)« less
2. Unsupervised Attributed Network Embedding via Cross Fusion

   https://doi.org/10.1145/3437963.3441763  

   Pan, Guosheng ; Yao, Yuan ; Tong, Hanghang ; Xu, Feng ; Lu, Jian ( March 2021 , WSDM)

   Attributed network embedding aims to learn low dimensional node representations by combining both the network's topological structure and node attributes. Most of the existing methods either propagate the attributes over the network structure or learn the node representations by an encoder-decoder framework. However, propagation based methods tend to prefer network structure to node attributes, whereas encoder-decoder methods tend to ignore the longer connections beyond the immediate neighbors. In order to address these limitations while enjoying the best of the two worlds, we design cross fusion layers for unsupervised attributed network embedding. Specifically, we first construct two separate views to handle network structure and node attributes, and then design cross fusion layers to allow flexible information exchange and integration between the two views. The key design goals of the cross fusion layers are three-fold: 1) allowing critical information to be propagated along the network structure, 2) encoding the heterogeneity in the local neighborhood of each node during propagation, and 3) incorporating an additional node attribute channel so that the attribute information will not be overshadowed by the structure view. Extensive experiments on three datasets and three downstream tasks demonstrate the effectiveness of the proposed method.
3. Towards Interpretable Object Detection by Unfolding Latent Structures

   Wu, Tianfu ; Song, Xi ( October 2019 , IEEE International Conference on Computer Vision)

   This paper first proposes a method of formulating model interpretability in visual understanding tasks based on the idea of unfolding latent structures. It then presents a case study in object detection using popular two-stage region-based convolutional neural network (i.e., R-CNN) detection systems. The proposed method focuses on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations. It utilizes a top-down hierarchical and compositional grammar model embedded in a directed acyclic AND-OR Graph (AOG) to explore and unfold the space of latent part configurations of regions of interest (RoIs). It presents an AOGParsing operator that seamlessly integrates with the RoIPooling /RoIAlign operator widely used in R-CNN and is trained end-to-end. In object detection, a bounding box is interpreted by the best parse tree derived from the AOG on-the-fly, which is treated as the qualitatively extractive rationale generated for interpreting detection. In experiments, Faster R-CNN is used to test the proposed method on the PASCAL VOC 2007 and the COCO 2017 object detection datasets. The experimental results show that the proposed method can compute promising latent structures without hurting the performance.
4. Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation

   Fang, Hao-Shu ; Xu, Yuanlu ; Wang, Wenguan ; Liu, Xiaobai ; Zhu, Song-Chun ( January 2018 , AAAI Conference on Artificial Intelligence)

   In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation. Our model directly takes 2D pose as input and learns a generalized 2D-3D mapping function. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNN) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a pose sample simulator to augment training samples in virtual camera views, which further improves our model generalizability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods.We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges.
5. Re-identification for Online Person Tracking by Modeling Space-Time Continuum

   https://doi.org/10.1109/CVPRW.2018.00193  

   Narayan, Neeti ; Sankaran, Nishant ; Setlur, Srirangaraj ; Govindaraju, Venu ( June 2018 , 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW))

   We present a novel approach to multi-person multi-camera tracking based on learning the space-time continuum of a camera network. Some challenges involved in tracking multiple people in real scenarios include a) ensuring reliable continuous association of all persons, and b) accounting for presence of blind-spots or entry/exit points. Most of the existing methods design sophisticated models that require heavy tuning of parameters and it is a nontrivial task for deep learning approaches as they cannot be applied directly to address the above challenges. Here, we deal with the above points in a coherent way by proposing a discriminative spatio-temporal learning approach for tracking based on person re-identification using LSTM networks. This approach is more robust when no a-priori information about the aspect of an individual or the number of individuals is known. The idea is to identify detections as belonging to the same individual by continuous association and recovering from past errors in associating different individuals to a particular trajectory. We exploit LSTM's ability to infuse temporal information to predict the likelihood that new detections belong to the same tracked entity by jointly incorporating visual appearance features and location information. The proposed approach gives a 50% improvement in the errormore »rate compared to the previous state-of-the-art method on the CamNeT dataset and 18% improvement as compared to the baseline approach on DukeMTMC dataset.« less