Aiming at the poor network embedding performance of cross-social network user alignment algorithm and the inability to guarantee the quality of negative samples generated by negative sampling method, a cross-social network KGEUA (Knowledge Graph Embedding User Alignment) algorithm was proposed. In the embedding stage, some known anchor user pairs were used for the positive sample expansion, and the Near_K negative sampling method was proposed to generate negative examples. Finally, the two social networks were embedded into a unified low-dimensional vector space with the knowledge graph embedding method. In the alignment stage, the existing user similarity measurement method was improved, the proposed structural similarity was combined with the traditional cosine similarity to measure the user similarity jointly, and an adaptive threshold-based greedy matching method was proposed to align users. Finally, the newly aligned user pairs were added to the training set to continuously optimize the vector space. The experimental results show that the proposed algorithm has the hits@30 value of 67.7% on the Twitter-Foursquare dataset, which is 3.3 to 34.8 percentage points higher than that of the state-of-the-art algorithm, improving the user alignment performance effectively.

Concerning that most of the current methods for Multi-Instance Multi-Label (MIML) problem do not consider how to represent features of objects in an even better way, a new MIML approach combined with Probabilistic Latent Semantic Analysis (PLSA) model and Neural Network (NN) was proposed based on topic model. The proposed algorithm learned the latent topic allocation of all the training examples by using the PLSA model. The above process was equivalent to the feature learning for getting a better feature expression. Then it utilized the latent topic allocation of each training example to train the neural network. When a test example was given, the proposed algorithm learned its latent topic distribution, then regarded the learned latent topic allocation of the test example as an input of the trained neural network to get the multiple labels of the test example. The experimental results on comparison with two classical algorithms based on decomposition strategy show that the proposed method has superior performance on two real-world MIML tasks.

Since the single-criterion-based tracker can not adapt to the complex environment, a tracking approach based on adaptive fusion of dual-criteria was proposed. In the method, the second-order spatiogram was employed to represent the target, the similarity between the target candidate and the target model as well as the contrast between the target candidate and its neighboring background were used to evaluate its reliability, and the objective function (or likelihood function) was established by weighted fusion of the two criteria. The particle filter procedure was used to search the target, and the fuzzy logic was applied to adaptively adjust the weights of the similarity and contrast. Experiments were carried out on several challenging sequences such as person, animal, and the results show that, compared with other trackers such as incremental visual tracker, ι₁ tracker, the proposed algorithm obtains better comprehensive performance in handling occlusion, deformation, rotation, and appearance change, and its success rate and average overlap ratio are respectively more than 80% and 0.76.